CN110674665B

CN110674665B - Image processing method and device, forest fire prevention system and electronic equipment

Info

Publication number: CN110674665B
Application number: CN201810721160.3A
Authority: CN
Inventors: 项鹏
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2018-07-03
Filing date: 2018-07-03
Publication date: 2023-06-30
Anticipated expiration: 2038-07-03
Also published as: CN110674665A

Abstract

The embodiment of the invention discloses an image processing method and device, a forest fire prevention system and electronic equipment, relates to the technical field of image processing, and is convenient for obtaining an image recognition result of a target area more accurately. The image processing method comprises the following steps: acquiring the jitter amplitude and jitter direction of a lens of a camera relative to the jitter amplitude and jitter direction of a shooting reference image when shooting a current image; and determining an edge clipping region of the current image shot by the lens according to the jitter amplitude, the jitter direction and a preset edge clipping threshold. The method is suitable for identifying the images shot by the camera in the environment with larger wind potential.

Description

Image processing method and device, forest fire prevention system and electronic equipment

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to an image processing method and apparatus, a forest fire prevention system, and an electronic device.

Background

At present, forest fires are one of important disasters in the world forestry, and occur in a certain amount each year, so that the forest resources are seriously lost and the global environment is polluted. Forest fires have the characteristics of sudden and random occurrence of disasters, and can cause larger loss in a shorter time. Therefore, once a fire alarm occurs, a fire extinguishing measure must be taken at a very fast speed, whether the fire is extinguished timely or not is decided properly, and the important reasons depend on whether the forest fire behavior is found timely or not, and whether the fire extinguishing measure is proper or not is decided properly. How to realize standardization, scientization and informatization of forest fire prevention work, really realize early discovery and early resolution of fire extinction. Digital forest fire prevention monitoring has become an essential means for early detection and elimination of forest fire extinction.

In the existing forest fire prevention system, because the environment of a camera deployment site is severe and wind is large, the camera shake is serious, the analysis of an intelligent algorithm is greatly influenced, the error of the intelligent algorithm for smoke analysis is directly caused, and more alarming false alarms are generated.

Disclosure of Invention

In view of the above, embodiments of the present invention provide an image processing method, an image processing device, a forest fire prevention system, and an electronic apparatus, which are convenient for obtaining an image recognition result of a target area more accurately when image recognition is performed subsequently.

In a first aspect, an embodiment of the present invention provides an image processing method, including: acquiring the jitter amplitude and jitter direction of a lens of a camera relative to the jitter amplitude and jitter direction of a shooting reference image when shooting a current image; and determining an edge clipping region of the current image shot by the lens according to the jitter amplitude, the jitter direction and a preset edge clipping threshold.

According to a specific implementation manner of the embodiment of the present invention, when the current image is captured by the lens of the camera, the method includes: acquiring a shake angle or shake displacement amount of a lens of a camera in a horizontal direction relative to a reference image when a current image is shot, and a shake direction to the right or left in the horizontal direction; and/or acquiring a shake angle or a shake displacement amount of a lens of the camera in an up-down direction and a shake direction in an up-down direction or a down direction relative to a reference image when shooting a current image.

According to a specific implementation manner of the embodiment of the present invention, the obtaining a shake angle of a lens of a camera in a horizontal direction relative to a reference image when the lens of the camera captures a current image includes: acquiring a shooting horizontal angle of a lens of a camera at a reference position and a shooting horizontal angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in a horizontal direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting horizontal angle of the lens of the camera at the reference position and the shooting horizontal angle of the lens of the camera at the current position; the shooting horizontal angle of the lens of the camera at the current position is an included angle of the optical axis of the lens between the current position and the initial position in the horizontal direction, and the shooting horizontal angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens between the reference position and the initial position in the horizontal direction; or acquiring a horizontal angle of the cradle head at the reference position and a horizontal angle of the cradle head at the current position, and obtaining a shake angle of a lens of the camera in the horizontal direction relative to the reference image when the current image is shot according to a difference value between the horizontal angle of the cradle head at the reference position and the horizontal angle of the cradle head at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image;

The obtaining the shake angle of the lens of the camera in the up-down direction relative to the shooting reference image when shooting the current image comprises the following steps: acquiring a shooting pitch angle of a lens of a camera at a reference position and a shooting pitch angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in the up-down direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting pitch angle of the lens of the camera at the reference position and the shooting pitch angle of the lens of the camera at the current position; the shooting pitch angle of the lens of the camera at the current position is an included angle of the optical axis of the lens in the up-down direction between the current position and the initial position, and the shooting pitch angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens in the up-down direction between the reference position and the initial position; or acquiring a pitch angle of the cradle head at a reference position and a pitch angle of the cradle head at a current position, and obtaining a shake angle of a lens of the camera in the up-down direction relative to the reference image when shooting a current image according to a difference value between the pitch angle of the cradle head at the reference position and the pitch angle at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image.

According to a specific implementation manner of the embodiment of the present invention, the obtaining the shake displacement amount of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image includes: acquiring a reference image and a current image shot by a lens of a camera; comparing the reference point in the image, the horizontal coordinate value in the reference image and the horizontal coordinate value in the current image to obtain the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image;

the obtaining of the shake displacement amount of the lens of the camera in the up-down direction relative to the shooting of the reference image when shooting the current image comprises the following steps: acquiring a reference image and a current image shot by a lens of a camera; and comparing the vertical coordinate value of the reference point in the image with the vertical coordinate value in the current image to obtain the jitter displacement of the lens of the camera in the up-down direction relative to the moment of shooting the reference image when shooting the current image.

According to a specific implementation manner of the embodiment of the present invention, the determining the edge clipping area of the current image shot by the lens according to the jitter amplitude and the jitter direction and the preset edge clipping threshold includes: determining the edge cutting proportion or cutting size of the left edge and the right edge of the current image shot by the camera according to the shake angle or shake displacement amount of the camera lens in the horizontal direction relative to the shake direction of the camera lens in the shooting reference image when the current image is shot, and presetting an edge cutting threshold value in the horizontal direction; and/or determining the edge clipping proportion or clipping size of the upper side edge and the lower side edge of the current image shot by the camera according to the dithering angle or dithering displacement amount of the camera lens in the up-down direction relative to the dithering direction in the up-down direction when shooting the reference image and the preset edge clipping threshold value.

According to a specific implementation manner of the embodiment of the present invention, the determining the edge clipping ratio of the left edge and the right edge of the current image shot by the lens includes: if the current image shakes to the right side in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking to the right side in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot; subtracting the jitter proportion of the current image to the right side of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the left side edge clipping proportion of the current image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the right side jitter of the reference image in the horizontal direction to obtain a right side edge clipping proportion of the current image; if the current image shakes leftwards in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking leftwards in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction when the current image is shot relative to the reference image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction to obtain a left side edge clipping proportion of the current image; subtracting the jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the right side edge clipping proportion of the current image;

The determining the edge clipping proportion of the upper side edge and the lower side edge of the current image shot by the lens comprises the following steps: if the current image shakes upwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking upwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; adding a preset upper and lower edge clipping proportion threshold value of the image and a dithering proportion of the current image to the upper side dithering of the reference image in the up-down direction to obtain an upper edge clipping proportion of the current image; subtracting the dithering proportion of the upper side dithering of the current image relative to the reference image in the upper and lower directions from a preset image upper and lower edge trimming proportion threshold value to obtain the lower edge trimming proportion of the current image; if the current image shakes downwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking downwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; subtracting the dithering proportion of the dithering of the current image to the lower side of the reference image in the up-down direction from the preset image upper and lower edge trimming proportion threshold value to obtain the upper edge trimming proportion of the current image; adding a preset image upper and lower edge clipping proportion threshold value and a dithering proportion of the current image to the dithering of the reference image to the lower side in the upper and lower direction to obtain a lower edge clipping proportion of the current image;

The determining the edge clipping size of the left side edge and the right side edge of the current image shot by the lens comprises the following steps: if the current image shakes to the right side in the horizontal direction relative to the reference image, subtracting a shake displacement amount of a lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot from a preset image horizontal edge cutting size threshold value to obtain a left side edge cutting size of the current image; adding a preset image horizontal edge clipping size threshold value and a jitter displacement amount of a lens of a camera in a horizontal direction relative to that of a shooting reference image when shooting a current image to obtain a right edge clipping size of the current image; if the current image shakes leftwards relative to the reference image in the horizontal direction, adding a preset image horizontal edge cutting size threshold value and a shake displacement amount of a lens of a camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image to obtain a left edge cutting size of the current image; subtracting the jitter displacement of the lens of the camera in the horizontal direction relative to the jitter displacement of the lens of the camera in the horizontal direction when shooting the current image from a preset horizontal edge clipping size threshold of the image to obtain the right edge clipping size of the current image;

The determining the edge clipping size of the upper side edge and the lower side edge of the current image shot by the lens comprises the following steps: if the current image is dithered upwards in the up-down direction relative to the reference image, adding a preset upper and lower edge clipping size threshold value of the image and a dithered displacement quantity of the current image dithered upwards in the up-down direction relative to the reference image to obtain an upper edge clipping size of the current image; subtracting the jitter displacement amount of the upper side jitter of the current image relative to the reference image in the up-down direction from the preset upper and lower edge clipping size threshold of the image to obtain the lower edge clipping size of the current image; if the current image shakes downwards in the up-down direction relative to the reference image, subtracting the shake displacement amount of the current image shaking downwards in the up-down direction relative to the reference image from a preset image upper and lower edge cutting size threshold value to obtain the upper edge cutting size of the current image; and adding a preset upper and lower edge cutting size threshold value of the image and a dithering displacement amount of dithering the current image to the lower side in the upper and lower direction relative to the reference image to obtain the lower edge cutting size of the current image.

According to a specific implementation manner of the embodiment of the invention, a dithering ratio F1:F1= |P2-P1|/PV of the current image dithering to the right or left in the horizontal direction relative to the reference image is determined according to the following formula; wherein P1 is the shooting horizontal angle of the lens of the camera at the reference position, and P2 is the shooting horizontal angle of the lens of the camera at the current position; or, P1 is the horizontal angle of the cradle head at the reference position, and P2 is the horizontal angle of the cradle head at the current position; PV is the horizontal visual angle of the camera, P2 is smaller than P1 and represents right shake, and P2 is larger than P1 and represents left shake; and/or the number of the groups of groups,

determining a dithering ratio F2:F2= |T2-T1|/TV of dithering of the current image to the upper side or the lower side in the up-down direction relative to the reference image according to the following formula; wherein T1 is a shooting pitch angle of a lens of the camera at a reference position, and T2 is a shooting pitch angle of the lens of the camera at a current position; or, T1 is the pitch angle of the cradle head at the reference position, and T2 is the pitch angle of the cradle head at the current position; TV is the vertical view angle of the camera, T2 is smaller than T1 indicating downward shake, and T2 is larger than T1 indicating upward shake.

According to a specific implementation manner of the embodiment of the present invention, after determining the dithering proportion of the current image dithering to the right or left in the horizontal direction relative to the reference image, before determining the left or right edge clipping region of the current image, the method further includes: determining whether the jitter proportion of the current image to the right side or the left side of the reference image in the horizontal direction is smaller than the image horizontal edge clipping proportion threshold value, and if so, executing the step of determining the left side or the right side edge clipping area of the current image; and/or, after determining a jitter ratio of the current image to the reference image, the current image being jittered upward or downward in the up-down direction, before determining the upper or lower edge clipping region of the current image, the method further comprises: determining whether a jitter ratio of the current image to the reference image in the up-down direction to the up-down or down direction is smaller than an image up-down edge clipping ratio threshold, and if so, executing the step of determining an up-down edge clipping area of the current image.

In a second aspect, an embodiment of the present invention provides an image processing apparatus including: a shake acquiring unit for acquiring a shake amplitude and a shake direction of a lens of the camera relative to a reference image when the current image is shot; and the clipping region determining unit is used for determining the edge clipping region of the current image shot by the lens according to the jitter amplitude, the jitter direction and the preset edge clipping threshold value.

According to a specific implementation manner of the embodiment of the present invention, the jitter obtaining unit includes: the horizontal shake acquisition module is used for acquiring a shake angle or shake displacement amount of a lens of the camera in a horizontal direction relative to a reference image when the lens of the camera shoots a current image and a shake direction to the right or left in the horizontal direction; and/or an up-and-down shake acquiring module for acquiring a shake angle or a shake displacement amount of a lens of the camera in an up-and-down direction and a shake direction in an up-and-down direction relative to a reference image when the current image is captured.

According to a specific implementation manner of the embodiment of the present invention, the horizontal shake obtaining module includes: a horizontal shake angle acquisition sub-module and/or an up-down shake angle acquisition sub-module; wherein,,

The horizontal shake angle acquisition sub-module is used for:

acquiring a shooting horizontal angle of a lens of a camera at a reference position and a shooting horizontal angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in a horizontal direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting horizontal angle of the lens of the camera at the reference position and the shooting horizontal angle of the lens of the camera at the current position; the shooting horizontal angle of the lens of the camera at the current position is an included angle of the optical axis of the lens between the current position and the initial position in the horizontal direction, and the shooting horizontal angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens between the reference position and the initial position in the horizontal direction; or acquiring a horizontal angle of the cradle head at the reference position and a horizontal angle of the cradle head at the current position, and obtaining a shake angle of a lens of the camera in the horizontal direction relative to the reference image when the current image is shot according to a difference value between the horizontal angle of the cradle head at the reference position and the horizontal angle of the cradle head at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image;

The up-down shaking angle obtaining sub-module is used for: acquiring a shooting pitch angle of a lens of a camera at a reference position and a shooting pitch angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in the up-down direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting pitch angle of the lens of the camera at the reference position and the shooting pitch angle of the lens of the camera at the current position; the shooting pitch angle of the lens of the camera at the current position is an included angle of the optical axis of the lens in the up-down direction between the current position and the initial position, and the shooting pitch angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens in the up-down direction between the reference position and the initial position; or acquiring a pitch angle of the cradle head at a reference position and a pitch angle of the cradle head at a current position, and obtaining a shake angle of a lens of the camera in the up-down direction relative to the reference image when shooting a current image according to a difference value between the pitch angle of the cradle head at the reference position and the pitch angle at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image.

According to a specific implementation manner of the embodiment of the present invention, the horizontal shake obtaining module includes: a horizontal shake displacement amount acquisition sub-module and an up-down shake displacement amount acquisition sub-module; the horizontal shake displacement acquisition submodule is used for acquiring a reference image and a current image shot by a lens of the camera; comparing the reference point in the image, the horizontal coordinate value in the reference image and the horizontal coordinate value in the current image to obtain the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image; the up-down shaking displacement obtaining submodule is used for obtaining a reference image and a current image shot by a lens of the camera; and comparing the vertical coordinate value of the reference point in the image with the vertical coordinate value in the current image to obtain the jitter displacement of the lens of the camera in the up-down direction relative to the moment of shooting the reference image when shooting the current image.

According to a specific implementation manner of the embodiment of the present invention, the clipping region determining unit includes: a left-right clipping region determining module and/or an up-down clipping region determining module; the left and right clipping region determining module is used for determining the edge clipping proportion or clipping size of the left side edge and the right side edge of the current image shot by the camera according to the shake angle or shake displacement amount of the camera lens in the horizontal direction relative to the shake direction of the camera lens in the horizontal direction to the right or left direction when the reference image is shot and preset edge clipping threshold values; the upper and lower clipping region determining module is used for determining the edge clipping proportion or clipping size of the upper side edge and the lower side edge of the current image shot by the camera according to the upper and lower jitter angle or jitter displacement amount of the camera lens relative to the upper and lower jitter direction when the reference image is shot and the preset edge clipping threshold value.

According to a specific implementation manner of the embodiment of the present invention, the left and right clipping region determining module includes: a left-right clipping proportion determining sub-module, a left-right clipping size determining sub-module, an up-down clipping proportion determining sub-module and an up-down clipping size determining sub-module; the left-right clipping proportion determining submodule is used for: if the current image shakes to the right side in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking to the right side in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot; subtracting the jitter proportion of the current image to the right side of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the left side edge clipping proportion of the current image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the right side jitter of the reference image in the horizontal direction to obtain a right side edge clipping proportion of the current image; if the current image shakes leftwards in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking leftwards in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction when the current image is shot relative to the reference image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction to obtain a left side edge clipping proportion of the current image; subtracting the jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the right side edge clipping proportion of the current image;

The up-down clipping proportion determining submodule is used for: if the current image shakes upwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking upwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; adding a preset upper and lower edge clipping proportion threshold value of the image and a dithering proportion of the current image to the upper side dithering of the reference image in the up-down direction to obtain an upper edge clipping proportion of the current image; subtracting the dithering proportion of the upper side dithering of the current image relative to the reference image in the upper and lower directions from a preset image upper and lower edge trimming proportion threshold value to obtain the lower edge trimming proportion of the current image; if the current image shakes downwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking downwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; subtracting the dithering proportion of the dithering of the current image to the lower side of the reference image in the up-down direction from the preset image upper and lower edge trimming proportion threshold value to obtain the upper edge trimming proportion of the current image; adding a preset image upper and lower edge clipping proportion threshold value and a dithering proportion of the current image to the dithering of the reference image to the lower side in the upper and lower direction to obtain a lower edge clipping proportion of the current image;

The left-right clipping size determining submodule is used for: if the current image shakes to the right side in the horizontal direction relative to the reference image, subtracting a shake displacement amount of a lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot from a preset image horizontal edge cutting size threshold value to obtain a left side edge cutting size of the current image; adding a preset image horizontal edge clipping size threshold value and a jitter displacement amount of a lens of a camera in a horizontal direction relative to that of a shooting reference image when shooting a current image to obtain a right edge clipping size of the current image; if the current image shakes leftwards relative to the reference image in the horizontal direction, adding a preset image horizontal edge cutting size threshold value and a shake displacement amount of a lens of a camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image to obtain a left edge cutting size of the current image; subtracting the jitter displacement of the lens of the camera in the horizontal direction relative to the jitter displacement of the lens of the camera in the horizontal direction when shooting the current image from a preset horizontal edge clipping size threshold of the image to obtain the right edge clipping size of the current image;

The up-down clipping size determining submodule is used for: if the current image is dithered upwards in the up-down direction relative to the reference image, adding a preset upper and lower edge clipping size threshold value of the image and a dithered displacement quantity of the current image dithered upwards in the up-down direction relative to the reference image to obtain an upper edge clipping size of the current image; subtracting the jitter displacement amount of the upper side jitter of the current image relative to the reference image in the up-down direction from the preset upper and lower edge clipping size threshold of the image to obtain the lower edge clipping size of the current image; if the current image shakes downwards in the up-down direction relative to the reference image, subtracting the shake displacement amount of the current image shaking downwards in the up-down direction relative to the reference image from a preset image upper and lower edge cutting size threshold value to obtain the upper edge cutting size of the current image; and adding a preset upper and lower edge cutting size threshold value of the image and a dithering displacement amount of dithering the current image to the lower side in the upper and lower direction relative to the reference image to obtain the lower edge cutting size of the current image.

According to a specific implementation manner of the embodiment of the present invention, the left-right clipping ratio determining submodule determines a jitter ratio f1:f1= |p2-p1|/PV of the current image jittering to the right side or the left side in the horizontal direction relative to the reference image according to the following formula; wherein P1 is the shooting horizontal angle of the lens of the camera at the reference position, and P2 is the shooting horizontal angle of the lens of the camera at the current position; or, P1 is the horizontal angle of the cradle head at the reference position, and P2 is the horizontal angle of the cradle head at the current position; PV is the horizontal visual angle of the camera, P2 is smaller than P1 and represents right shake, and P2 is larger than P1 and represents left shake; and/or the number of the groups of groups,

The up-down clipping proportion determining submodule determines a jitter proportion F2:F2= |T2-T1|/TV of the current image jittering upwards or downwards in the up-down direction relative to the reference image according to the following formula; wherein T1 is a shooting pitch angle of a lens of the camera at a reference position, and T2 is a shooting pitch angle of the lens of the camera at a current position; or, T1 is the pitch angle of the cradle head at the reference position, and T2 is the pitch angle of the cradle head at the current position; TV is the vertical view angle of the camera, T2 is smaller than T1 indicating downward shake, and T2 is larger than T1 indicating upward shake.

According to a specific implementation manner of the embodiment of the present invention, the image processing apparatus further includes: a threshold judgment unit configured to: after determining the jitter proportion of the current image to the right or left in the horizontal direction relative to the reference image, before determining the left or right edge clipping region of the current image, determining whether the jitter proportion of the current image to the right or left in the horizontal direction relative to the reference image is smaller than the image horizontal edge clipping proportion threshold value, and if so, determining the left or right edge clipping region of the current image by a left or right clipping region determining module;

And/or the number of the groups of groups,

after the jitter proportion of the current image to the upper side or the lower side of the reference image in the up-down direction is determined, before the upper side or the lower side edge clipping area of the current image is determined, whether the jitter proportion of the current image to the upper side or the lower side of the reference image in the up-down direction is smaller than the image upper and lower edge clipping proportion threshold value or not is determined, and if the jitter proportion is smaller than the image upper and lower edge clipping proportion threshold value, the upper and lower side edge clipping area of the current image is determined by an upper and lower clipping area determining module.

In a third aspect, an embodiment of the present invention provides a forest fire protection system, including a camera, an image processing device, and a fire recognition device; the camera is arranged on shooting of a forest scene and used for acquiring images of the forest scene; the image processing device is used for processing the image acquired by the camera; the fire identification device is used for identifying the image processed by the image processing device so as to determine whether fire exists in the forest scene; the image processing device is any one of the image processing devices described in the foregoing embodiments.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space surrounded by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, for executing the image processing method described in any one of the foregoing embodiments.

In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium storing one or more programs executable by one or more processors to implement the image processing method according to any one of the foregoing embodiments.

According to the image processing method, the device, the forest fire prevention system and the electronic equipment, when the current image is shot by the lens of the camera, the edge cutting area of the current image shot by the lens is determined according to the jitter amplitude and the jitter direction and the preset edge cutting threshold value relative to the jitter amplitude and the jitter direction of the shot reference image, so that the current image can be cut according to the edge cutting area of the current image, the cut current image is obtained, and because the cut current image is an image of the middle area of the target area shot by the camera, namely, a stable image, the image recognition result of the target area can be obtained more accurately when the follow-up image recognition processing is carried out according to the cut current image, namely, the monitoring result of the target area can be obtained more accurately.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of an image processing method according to an embodiment of the invention;

FIG. 2 is a schematic flow chart of step 11 in FIG. 1;

FIG. 3 is a schematic flow chart of step 12 in FIG. 1;

FIG. 4 is a schematic diagram of determining an edge clipping region of a current image according to an embodiment of the present invention;

FIG. 5 is a schematic diagram illustrating an image processing apparatus according to an embodiment of the invention;

FIG. 6 is a schematic diagram of an image processing apparatus according to another embodiment of the present invention;

fig. 7 is a schematic view of a forest fire prevention system according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the invention.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are merely some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Fig. 1 is a flow chart of an image processing method according to an embodiment of the present invention, as shown in fig. 1, an apparatus of this embodiment may include:

and 11, acquiring the jitter amplitude and the jitter direction of a lens of the camera when shooting a current image relative to those of a shooting reference image.

In this embodiment, the target monitoring area is image-captured by the camera. The target area may be a forest fire monitoring area, a road traffic monitoring area, or the like.

In this embodiment, the images shot by the camera are a plurality of continuous images, and the image shot at a certain moment can be used as a reference image, for example, the first shot image is used as the reference image, and the image shot at the current moment after that is used as the current image.

When the camera is installed in a site with a severe environment and a large wind force, the camera may swing with wind, thereby causing a phenomenon of transmitting shake of an image photographed by the camera.

And step 12, determining an edge clipping area of the current image shot by the lens according to the jitter amplitude, the jitter direction and a preset edge clipping threshold.

And step 13, cutting the current image according to the edge cutting area of the current image to obtain a cut current image.

In this embodiment, step 13 is an optional step. And automatically cutting the current image according to the edge cutting area of the current image, namely automatically cutting the edge cutting area, and obtaining the cut current image. For example, if the edge clipping area of the current image is 20 pixels in size, the edge of the current image, which is 20 pixels in size, is automatically clipped.

According to the embodiment, when the current image is shot by the lens of the camera, the edge cutting area of the current image shot by the lens is determined according to the jitter amplitude and the jitter direction relative to the jitter direction when the reference image is shot and the preset edge cutting threshold value, so that the current image can be cut according to the edge cutting area of the current image, the cut current image is obtained, and the cut current image is an image of the middle area of the target area shot by the camera, namely, a stable image, so that the image recognition result of the target area can be obtained more accurately when the subsequent image recognition processing is carried out according to the cut current image, namely, the monitoring result of the target area can be obtained more accurately.

In this embodiment, a plurality of current images, for example, 100 images after clipping, may be obtained over time in a period of time, so that the overall dimension of each image after clipping is kept consistent in order to obtain the image recognition result (i.e., the monitoring result) of the target area more accurately.

In the above embodiment, the shake amplitude may be the shake angle or the shake displacement amount of the lens of the camera when capturing the current image, and the shake direction may be the left-right shake in the horizontal direction or the up-down shake in the vertical direction, and specifically referring to fig. 2, in an embodiment of the present invention, the capturing of the current image, relative to the shake amplitude and the shake direction when capturing the reference image, includes:

step 111, obtaining a shake angle or shake displacement amount of a lens of a camera in a horizontal direction relative to a reference image when shooting a current image, and a shake direction to the right or left in the horizontal direction;

and/or the number of the groups of groups,

step 112, obtaining a shake angle or a shake displacement amount of a lens of the camera in an up-down direction and a shake direction in an up-down direction or a down direction relative to a reference image when capturing a current image.

In this embodiment, the horizontal dithering direction of the current image with respect to the reference image may be determined according to the offset direction of the reference point (e.g., the upper left corner of the image) on the current image with respect to the same reference point on the reference image. For example, if the upper left corner of the current image is shifted to the right with respect to the upper left corner of the reference image, it may be determined that the current image is dithered to the right in the horizontal direction with respect to the reference image. Accordingly, if the upper left corner of the current image is offset to the left with respect to the upper left corner of the reference image, it may be determined that the current image is dithered to the left in the horizontal direction with respect to the reference image.

Similarly, the up-down jitter direction of the current image relative to the reference image may be determined based on the offset direction of the reference point (e.g., the upper left corner of the image) on the current image relative to the same reference point on the reference image. For example, if the upper left corner of the current image is shifted upward relative to the upper left corner of the reference image, it may be determined that the current image is dithered upward in the up-down direction (i.e., vertical direction) relative to the reference image. Accordingly, if the upper left corner of the current image is shifted downward with respect to the upper left corner of the reference image, it can be determined that the current image is dithered downward in the up-down direction with respect to the reference image.

The shake angle of the lens of the camera in the horizontal direction relative to the reference image is obtained according to the difference between the shooting horizontal angle of the camera at the reference position and the shooting horizontal angle at the current position when the current image is shot, specifically, in one embodiment of the invention, in step 111, the shake angle of the lens of the camera in the horizontal direction relative to the reference image when the current image is shot may include:

acquiring a shooting horizontal angle of a lens of a camera at a reference position and a shooting horizontal angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in a horizontal direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting horizontal angle of the lens of the camera at the reference position and the shooting horizontal angle of the lens of the camera at the current position; the shooting horizontal angle of the lens of the camera at the current position is an included angle of the optical axis of the lens between the current position and the initial position in the horizontal direction, and the shooting horizontal angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens between the reference position and the initial position in the horizontal direction.

When the camera is mounted on the pan/tilt head, the shake angle of the lens of the camera in the horizontal direction relative to the reference image is obtained when the current image is captured, and may also be obtained according to the difference between the horizontal angle of the pan/tilt head at the reference position and the horizontal angle at the current position, specifically, in another embodiment of the present invention, in step 111, the shake angle of the lens of the camera in the horizontal direction relative to the reference image is obtained when the current image is captured may include: acquiring a horizontal angle of a tripod head at a reference position and a horizontal angle of the tripod head at a current position, and acquiring a shake angle of a lens of a camera in a horizontal direction relative to a reference image when the lens of the camera shoots a current image according to a difference value between the horizontal angle of the tripod head at the reference position and the horizontal angle of the tripod head at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image.

Similarly, when the current image is captured, the shake angle of the lens of the camera with respect to the up-down direction when the reference image is captured may be obtained according to the difference between the capturing pitch angle of the camera at the reference position and the capturing pitch angle at the current position, and specifically, in one embodiment of the present invention, in step 112, the obtaining the shake angle of the lens of the camera with respect to the up-down direction when the current image is captured may include: acquiring a shooting pitch angle of a lens of a camera at a reference position and a shooting pitch angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in the up-down direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting pitch angle of the lens of the camera at the reference position and the shooting pitch angle of the lens of the camera at the current position; the shooting pitch angle of the lens of the camera at the current position is an included angle of the optical axis of the lens in the up-down direction between the current position and the initial position, and the shooting pitch angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens in the up-down direction between the reference position and the initial position.

When the camera is mounted on the tripod head, the shake angle of the lens of the camera in the up-down direction relative to the time of shooting the reference image when shooting the current image can be obtained according to the difference between the pitch angle of the tripod head at the reference position and the pitch angle at the current position, specifically, in one embodiment of the invention, in step 112, the pitch angle of the tripod head at the reference position and the pitch angle at the current position are obtained, and the shake angle of the lens of the camera in the up-down direction relative to the time of shooting the reference image is obtained according to the difference between the pitch angle of the tripod head at the reference position and the pitch angle at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image.

The amount of shake displacement of the lens of the camera in the horizontal direction when the current image is captured with respect to the amount of shake displacement in the horizontal direction when the reference image is captured can be obtained by comparing the horizontal coordinate value of the reference point in the image in the reference image with the horizontal coordinate value in the current image, specifically, in one embodiment of the present invention, in step 111, the obtaining the amount of shake displacement of the lens of the camera in the horizontal direction when the current image is captured with respect to the amount of shake displacement in the horizontal direction when the reference image is captured may include: acquiring a reference image and a current image shot by a lens of a camera; and comparing the horizontal coordinate value of the reference point in the image with the horizontal coordinate value in the current image to obtain the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image.

In the present invention, when the current image is captured, the lens of the camera may be obtained by comparing a reference point in the image (such as a vertex at an upper left corner in the image) with a vertical coordinate value in the current image, with respect to a shake displacement amount in an up-down direction when the reference image is captured, and specifically, in step 112, the obtaining the shake displacement amount in the up-down direction when the lens of the camera is captured with respect to the shake displacement amount in the up-down direction when the reference image is captured may include: acquiring a reference image and a current image shot by a lens of a camera; and comparing the vertical coordinate value of the reference point in the image with the vertical coordinate value in the current image to obtain the jitter displacement of the lens of the camera in the up-down direction relative to the moment of shooting the reference image when shooting the current image.

Referring to fig. 3, in an embodiment of the present invention, the determining the edge clipping area of the current image shot by the lens according to the jitter amplitude and the jitter direction and the preset edge clipping threshold (step 12) may include:

step 121, determining the edge cutting proportion or cutting size of the left edge and the right edge of the current image shot by the camera according to the shake angle or shake displacement amount of the camera lens in the horizontal direction relative to the shake displacement amount in the horizontal direction when shooting the current image, and presetting an edge cutting threshold in the right or left direction; and/or the number of the groups of groups,

Step 122, determining the edge clipping ratio or clipping size of the upper side edge and the lower side edge of the current image shot by the camera according to the dithering angle or dithering displacement amount of the camera lens in the up-down direction relative to the dithering direction in the up-down direction when shooting the reference image and the preset edge clipping threshold value.

After the edge cutting proportion or the cutting size is determined, the edge cutting area can be determined according to the edge cutting proportion or the cutting size.

In an embodiment of the present invention, in step 121, the determining the edge clipping ratio of the left edge and the right edge of the current image captured by the lens includes:

step 1211a, if the current image shakes to the right in the horizontal direction relative to the reference image, determining a shake ratio of the current image to the right in the horizontal direction relative to the reference image according to a shake angle of the lens of the camera in the horizontal direction when the current image is shot relative to the reference image; subtracting the jitter proportion of the current image to the right side of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the left side edge clipping proportion of the current image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the right side jitter of the reference image in the horizontal direction to obtain a right side edge clipping proportion of the current image;

Step 1212a, if the current image shakes to the left in the horizontal direction relative to the reference image, determining a shake ratio of the current image to the left in the horizontal direction relative to the reference image according to a shake angle of the lens of the camera in the horizontal direction when the current image is shot relative to the reference image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction to obtain a left side edge clipping proportion of the current image; and subtracting the jitter proportion of the current image relative to the left side jitter of the reference image in the horizontal direction from the preset image horizontal edge clipping proportion threshold value to obtain the right side edge clipping proportion of the current image.

In one embodiment of the present invention, in step 122, the determining the edge clipping ratio of the upper edge and the lower edge of the current image captured by the lens includes:

step 1221a, if the current image is dithered up and down with respect to the reference image, determining a dithering ratio of the current image dithered up and down with respect to the reference image according to a dithering angle of the lens of the camera in the up and down direction when the current image is captured with respect to the reference image; adding a preset upper and lower edge clipping proportion threshold value of the image and a dithering proportion of the current image to the upper side dithering of the reference image in the up-down direction to obtain an upper edge clipping proportion of the current image; subtracting the dithering proportion of the upper side dithering of the current image relative to the reference image in the upper and lower directions from a preset image upper and lower edge trimming proportion threshold value to obtain the lower edge trimming proportion of the current image;

Step 1222a, if the current image shakes downward in the up-down direction relative to the reference image, determining a shake ratio of the current image to shake downward in the up-down direction relative to the reference image according to a shake angle of the lens of the camera in the up-down direction when the current image is shot relative to the reference image; subtracting the dithering proportion of the dithering of the current image to the lower side of the reference image in the up-down direction from the preset image upper and lower edge trimming proportion threshold value to obtain the upper edge trimming proportion of the current image; and adding a preset image upper and lower edge clipping proportion threshold value and a dithering proportion of the current image to the dithering of the reference image to the lower side in the upper and lower direction to obtain the lower edge clipping proportion of the current image.

In an alternative embodiment, in particular clipping, to determine the clipping region more conveniently, the left edge clipping ratio and the right edge clipping ratio of the current image may be converted into clipping pixels, and then clipping is performed on the current image according to the clipping pixels, so as to obtain a clipped current image. Specifically, the clipping the current image according to the edge clipping region of the current image to obtain a clipped current image may include: determining the left edge cutting size of the current image according to the left edge cutting proportion of the current image and the transverse pixels of the current image, and cutting the left edge of the current image according to the left edge cutting size of the current image to obtain a cut current image; or determining the right edge clipping size of the current image according to the right edge clipping proportion of the current image and the transverse pixels of the current image, and clipping the right edge of the current image according to the right edge clipping size of the current image to obtain a clipped current image.

As an example, the left edge clipping ratio of the current image may be converted into a pixel size to be clipped for the left edge according to the following formula: s1=x1×pp; s1 is the pixel size to be cut out on the left edge of the current image; x1 is the left edge clipping proportion of the current image; PP is the horizontal pixel size of the current image.

If the screen size of the current image is 1920×1080 pixels, the horizontal pixel (horizontal pixel) size PP is 1920 pixels, and the vertical pixel (also referred to as vertical pixel) size ZZ is 1080 pixels. For example, if the left edge clipping pixel size of the current image is 20 pixels and the right edge clipping pixel size is 25 pixels after conversion, the edge of the current image with the left 20 pixels is automatically clipped and the edge of the current image with the right 25 pixels is automatically clipped.

The manner of converting the clipping ratio of the right side edge, the upper side edge and the lower side edge of the current image into the pixel size to be clipped is similar to the manner of converting the clipping ratio of the left side edge of the current image into the pixel size to be clipped of the left side edge, and will not be repeated.

In an embodiment of the present invention, in step 121, the determining edge clipping dimensions of the left edge and the right edge of the current image captured by the lens includes:

Step 1211b, if the current image shakes to the right in the horizontal direction relative to the reference image, subtracting the shake displacement amount of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image from the preset image horizontal edge clipping size threshold value to obtain the left edge clipping size of the current image; adding a preset image horizontal edge clipping size threshold value and a jitter displacement amount of a lens of a camera in a horizontal direction relative to that of a shooting reference image when shooting a current image to obtain a right edge clipping size of the current image;

step 1212b, if the current image shakes to the left in the horizontal direction relative to the reference image, adding a preset image horizontal edge clipping size threshold to the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image, so as to obtain the left edge clipping size of the current image; and subtracting the jitter displacement amount of the lens of the camera in the horizontal direction relative to the jitter displacement amount of the lens of the camera in the horizontal direction when the current image is shot from the preset horizontal edge clipping size threshold of the image to obtain the right edge clipping size of the current image.

In one embodiment of the present invention, in step 122, the determining the edge clipping sizes of the upper side edge and the lower side edge of the current image captured by the lens includes:

step 1221b, if the current image is dithered upward in the up-down direction relative to the reference image, adding a preset upper and lower edge clipping size threshold to the dithering displacement of the current image relative to the reference image, to obtain an upper edge clipping size of the current image; subtracting the jitter displacement amount of the upper side jitter of the current image relative to the reference image in the up-down direction from the preset upper and lower edge clipping size threshold of the image to obtain the lower edge clipping size of the current image;

step 1222b, if the current image shakes downwards in the up-down direction relative to the reference image, subtracting the shake displacement of the current image shaking downwards in the up-down direction relative to the reference image from the preset image upper and lower edge cutting size threshold value to obtain the upper edge cutting size of the current image; and adding a preset upper and lower edge cutting size threshold value of the image and a dithering displacement amount of dithering the current image to the lower side in the upper and lower direction relative to the reference image to obtain the lower edge cutting size of the current image.

In the above embodiment, the image edge clipping ratio threshold or clipping size threshold may be preset, and the specific size thereof may be configured according to the on-site jitter condition, if the jitter is stronger, the threshold may be properly enlarged, the jitter is smaller, and the threshold may also be properly reduced.

Referring to fig. 4, in an embodiment of the present invention, in step 1211a or step 1212a, a dithering ratio f1:f1= |p2-p1|/PV of the current image dithering to the right or left in the horizontal direction with respect to the reference image may be determined according to the following formula; wherein P1 is the shooting horizontal angle of the lens of the camera at the reference position, and P2 is the shooting horizontal angle of the lens of the camera at the current position; PV is the horizontal view angle of the camera, P2 is smaller than P1 indicating a right shake, and P2 is larger than P1 indicating a left shake. When the camera is mounted on the pan-tilt, P1 may be a horizontal angle of the pan-tilt at the reference position, and P2 may be a horizontal angle of the pan-tilt at the current position.

In this embodiment, when it is determined that the shake direction in the horizontal direction is right shake, the left edge clipping ratio x1:x1=px_p2_p1|/PV of the current image may be obtained according to the following formula; the right edge clipping ratio x2:x2=px+|p2-p1|/PV of the current image can be obtained according to the following formula.

When the dithering direction in the horizontal direction is determined to be dithering left, the left edge clipping ratio x3:x3=px+|p2-p1|/PV of the current image can be obtained according to the following formula; the right edge clipping ratio x4:x4=px- |p2-p1|/PV of the current image can be obtained according to the following formula. In the above formula, the meanings of P1, P2 and PV are the same as the meanings of the corresponding parameters in the above formula; PX is an image horizontal edge clipping scale threshold.

The image horizontal edge clipping proportion threshold PX can be preset, the specific size of the image horizontal edge clipping proportion threshold PX can be configured according to the on-site jitter condition, if the jitter is stronger, the proportion threshold PX can be properly enlarged, the jitter is smaller, and the proportion threshold PX can also be properly reduced.

Referring to fig. 4, in an embodiment of the present invention, in step 1221a or step 1222a, a dithering ratio f2:f2= |t2-t1|/TV of the current image dithering to the upper side or the lower side in the up-down direction with respect to the reference image may be determined according to the following formula; wherein T1 is a shooting pitch angle of a lens of the camera at a reference position, and T2 is a shooting pitch angle of the lens of the camera at a current position; TV is the vertical view angle of the camera, T2 is smaller than T1 indicating downward shake, and T2 is larger than T1 indicating upward shake. When the camera is mounted on the cradle head, T1 can be the pitch angle of the cradle head at the reference position, and T2 can be the pitch angle of the cradle head at the current position.

In this embodiment, when it is determined that the shake direction in the up-down direction is up-shake, the upper side edge clipping ratio y1:y1=tx+|t2-t1|/TV of the current image can be obtained according to the following formula;

the lower edge clipping ratio y2:y2=tx- |t2-t1|/TV of the current image can be obtained according to the following formula.

When the dithering direction in the up-down direction is determined to be dithering downwards, the upper side edge clipping ratio Y3:Y3=TX- |T2-T1|/TV of the current image can be obtained according to the following formula;

the lower edge clipping ratio y4:y4=tx+|t2-t1|/TV of the current image can be obtained according to the following formula.

In the above formula, the meanings of T1, T2 and TV are the same as those in the above formula. TX is the image upper and lower edge clipping scale threshold.

The ratio threshold TX of the clipping of the upper and lower edges of the image may be preset, the specific size of the ratio threshold TX may be configured according to the scene jitter condition, if the jitter is strong, the ratio threshold may be properly enlarged, the jitter is small, and the ratio threshold may also be properly reduced.

In an embodiment of the present invention, in step 1211a or step 1212a, after determining a shake scale in which the current image is shake-ed to the right or left in the horizontal direction with respect to the reference image, before determining the left or right edge clipping region of the current image, the method further includes: determining whether a jitter ratio of the current image to the right or left of the reference image in the horizontal direction is smaller than the image horizontal edge clipping ratio threshold, and if so, executing the step of determining the left or right edge clipping area of the current image.

The jitter proportion of the current image to the right side or the left side of the reference image in the horizontal direction is smaller than the threshold value of the horizontal edge clipping proportion of the image, which indicates that the image jitter is within an acceptable range; if the jitter proportion of the current image to the right side or the left side of the reference image in the horizontal direction is larger than the image horizontal edge clipping proportion threshold value, the image jitter is too large, the current image can be discarded, clipping is not performed on the current image and the current image is not used for subsequent image recognition, and therefore the accuracy of subsequent image recognition can be further improved.

In an embodiment of the present invention, in step 1221a or step 1222a, after determining a dithering scale of the current image dithering upward or downward in an up-down direction with respect to the reference image, before determining the upper or lower edge clipping region of the current image, the method further includes: determining whether a jitter ratio of the current image to the reference image in the up-down direction to the up-down or down direction is smaller than an image up-down edge clipping ratio threshold, and if so, executing the step of determining an up-down edge clipping area of the current image.

The jitter proportion of the current image, relative to the reference image, in the up-down direction, to the upper side or the lower side is smaller than the clipping proportion threshold value of the upper edge and the lower edge of the image, which indicates that the image jitter is within an acceptable range; if the jitter proportion of the current image to the upper side or the lower side of the reference image in the up-down direction is larger than the cutting proportion threshold value of the upper edge and the lower edge of the image, the image jitter is too large, the current image can be discarded, cutting is not performed on the current image, the current image is not used for subsequent image recognition, and therefore the accuracy of subsequent image recognition can be further improved.

Referring to fig. 5, an embodiment of the present invention further provides an image processing apparatus, including: a shake acquiring unit 11, a clipping region determining unit 12, and a clipping unit 13; a shake acquiring unit 11, configured to acquire a shake magnitude and a shake direction of a lens of the camera when capturing a current image, relative to a shake magnitude and a shake direction when capturing a reference image; and a clipping region determining unit 12, configured to determine an edge clipping region of the current image captured by the lens according to the jitter amplitude and jitter direction and a preset edge clipping threshold. And a clipping unit 13 for processing the current image according to the edge clipping region of the current image.

In this embodiment, the clipping unit 13 is an optional module. The device of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and are not described here again.

Referring to fig. 6, in an embodiment of the present invention, the jitter obtaining unit 11 includes a horizontal jitter obtaining module 111, and/or an up-down jitter obtaining module 112; wherein, the horizontal shake obtaining module 111 is configured to obtain a shake angle or a shake displacement amount of a lens of the camera in a horizontal direction and a shake direction to the right or left in the horizontal direction when the lens of the camera captures a current image, relative to a reference image; the up-down shake acquiring module 112 is configured to acquire a shake angle or a shake displacement amount of a lens of the camera in an up-down direction and a shake direction in an up-down direction or a down direction when capturing a current image, with respect to a reference image.

In an embodiment of the present invention, the horizontal shake obtaining module 111 includes: a horizontal shake angle acquisition sub-module and/or an up-down shake angle acquisition sub-module; wherein,,

the horizontal shake angle acquisition sub-module is used for:

acquiring a shooting horizontal angle of a lens of a camera at a reference position and a shooting horizontal angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in a horizontal direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting horizontal angle of the lens of the camera at the reference position and the shooting horizontal angle of the lens of the camera at the current position; the shooting horizontal angle of the lens of the camera at the current position is an included angle of the optical axis of the lens between the current position and the initial position in the horizontal direction, and the shooting horizontal angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens between the reference position and the initial position in the horizontal direction; or,

Acquiring a horizontal angle of a tripod head at a reference position and a horizontal angle of the tripod head at a current position, and acquiring a shake angle of a lens of a camera in a horizontal direction relative to a reference image when the lens of the camera shoots a current image according to a difference value between the horizontal angle of the tripod head at the reference position and the horizontal angle of the tripod head at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image;

the up-down shaking angle obtaining sub-module is used for:

acquiring a shooting pitch angle of a lens of a camera at a reference position and a shooting pitch angle of the lens of the camera at a current position, and acquiring a shake angle of the lens of the camera in the up-down direction relative to a shooting reference image when shooting the current image according to a difference value between the shooting pitch angle of the lens of the camera at the reference position and the shooting pitch angle of the lens of the camera at the current position; the shooting pitch angle of the lens of the camera at the current position is an included angle of the optical axis of the lens in the up-down direction between the current position and the initial position, and the shooting pitch angle of the lens of the camera at the reference position is an included angle of the optical axis of the lens in the up-down direction between the reference position and the initial position; or,

Acquiring a pitch angle of a holder at a reference position and a pitch angle of the holder at a current position, and acquiring a shake angle of a lens of a camera in the up-down direction relative to a reference image when the lens of the camera shoots a current image according to a difference value between the pitch angle of the holder at the reference position and the pitch angle of the holder at the current position; the camera is arranged on the holder, when the holder is at a reference position, an image shot by the camera is a reference image, and when the holder is at a current position, the image shot by the camera is a current image.

In an embodiment of the present invention, the horizontal shake obtaining module 111 includes: a horizontal shake displacement amount acquisition sub-module and an up-down shake displacement amount acquisition sub-module; wherein,,

the horizontal shake displacement obtaining submodule is used for obtaining a reference image and a current image shot by a lens of the camera; comparing the reference point in the image, the horizontal coordinate value in the reference image and the horizontal coordinate value in the current image to obtain the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image;

the up-down shaking displacement obtaining submodule is used for obtaining a reference image and a current image shot by a lens of the camera; and comparing the vertical coordinate value of the reference point in the image with the vertical coordinate value in the current image to obtain the jitter displacement of the lens of the camera in the up-down direction relative to the moment of shooting the reference image when shooting the current image.

Referring to fig. 6, in an embodiment of the present invention, the clipping region determining unit 12 includes: a left-right clipping region determining module 121, and/or an up-down clipping region determining module 122; wherein,,

a left-right clipping region determining module 121, configured to determine, according to a shake angle or a shake displacement amount of a lens of a camera in a horizontal direction when capturing a current image, a shake direction to the right or left in the horizontal direction relative to a shake direction when capturing a reference image, and a preset edge clipping threshold, a clipping ratio or clipping size of left and right edges of the current image captured by the lens;

the up-down clipping region determining module 122 is configured to determine an edge clipping ratio or clipping size of an upper side edge and a lower side edge of a current image captured by a lens of a camera according to a shake angle or a shake displacement amount in an up-down direction relative to a shake direction in an up-down direction when capturing a reference image, and a preset edge clipping threshold.

In an embodiment of the present invention, the left and right clipping region determining module 121 includes: a left-right clipping proportion determining sub-module, a left-right clipping size determining sub-module, an up-down clipping proportion determining sub-module and an up-down clipping size determining sub-module; wherein,,

The left-right clipping proportion determination submodule is used for:

if the current image shakes to the right side in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking to the right side in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot; subtracting the jitter proportion of the current image to the right side of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the left side edge clipping proportion of the current image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the right side jitter of the reference image in the horizontal direction to obtain a right side edge clipping proportion of the current image;

if the current image shakes leftwards in the horizontal direction relative to the reference image, determining the shake proportion of the current image shaking leftwards in the horizontal direction relative to the reference image according to the shake angle of the lens of the camera in the horizontal direction when the current image is shot relative to the reference image; adding a preset image horizontal edge clipping proportion threshold value and a jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction to obtain a left side edge clipping proportion of the current image; subtracting the jitter proportion of the current image to the left side jitter of the reference image in the horizontal direction from a preset image horizontal edge clipping proportion threshold value to obtain the right side edge clipping proportion of the current image;

The up-down clipping proportion determining submodule is used for:

if the current image shakes upwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking upwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; adding a preset upper and lower edge clipping proportion threshold value of the image and a dithering proportion of the current image to the upper side dithering of the reference image in the up-down direction to obtain an upper edge clipping proportion of the current image; subtracting the dithering proportion of the upper side dithering of the current image relative to the reference image in the upper and lower directions from a preset image upper and lower edge trimming proportion threshold value to obtain the lower edge trimming proportion of the current image;

if the current image shakes downwards in the up-down direction relative to the reference image, determining the shake proportion of the current image shaking downwards in the up-down direction relative to the reference image according to the shake angle of the camera lens in the up-down direction when the current image is shot relative to the reference image; subtracting the dithering proportion of the dithering of the current image to the lower side of the reference image in the up-down direction from the preset image upper and lower edge trimming proportion threshold value to obtain the upper edge trimming proportion of the current image; adding a preset image upper and lower edge clipping proportion threshold value and a dithering proportion of the current image to the dithering of the reference image to the lower side in the upper and lower direction to obtain a lower edge clipping proportion of the current image;

The left-right clipping size determining submodule is used for:

if the current image shakes to the right side in the horizontal direction relative to the reference image, subtracting a shake displacement amount of a lens of the camera in the horizontal direction relative to the time of shooting the reference image when the current image is shot from a preset image horizontal edge cutting size threshold value to obtain a left side edge cutting size of the current image; adding a preset image horizontal edge clipping size threshold value and a jitter displacement amount of a lens of a camera in a horizontal direction relative to that of a shooting reference image when shooting a current image to obtain a right edge clipping size of the current image;

if the current image shakes leftwards relative to the reference image in the horizontal direction, adding a preset image horizontal edge cutting size threshold value and a shake displacement amount of a lens of a camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image to obtain a left edge cutting size of the current image; subtracting the jitter displacement of the lens of the camera in the horizontal direction relative to the jitter displacement of the lens of the camera in the horizontal direction when shooting the current image from a preset horizontal edge clipping size threshold of the image to obtain the right edge clipping size of the current image;

The up-down clipping size determining submodule is used for:

if the current image is dithered upwards in the up-down direction relative to the reference image, adding a preset upper and lower edge clipping size threshold value of the image and a dithered displacement quantity of the current image dithered upwards in the up-down direction relative to the reference image to obtain an upper edge clipping size of the current image; subtracting the jitter displacement amount of the upper side jitter of the current image relative to the reference image in the up-down direction from the preset upper and lower edge clipping size threshold of the image to obtain the lower edge clipping size of the current image;

if the current image shakes downwards in the up-down direction relative to the reference image, subtracting the shake displacement amount of the current image shaking downwards in the up-down direction relative to the reference image from a preset image upper and lower edge cutting size threshold value to obtain the upper edge cutting size of the current image; and adding a preset upper and lower edge cutting size threshold value of the image and a dithering displacement amount of dithering the current image to the lower side in the upper and lower direction relative to the reference image to obtain the lower edge cutting size of the current image.

Referring to fig. 4, in an embodiment of the present invention, the left-right clipping ratio determining submodule determines a jitter ratio f1:f1= |p2-p1|/PV of the current image jittering to the right or left in the horizontal direction with respect to the reference image according to the following formula; wherein P1 is the shooting horizontal angle of the lens of the camera at the reference position, and P2 is the shooting horizontal angle of the lens of the camera at the current position; or, P1 is the horizontal angle of the cradle head at the reference position, and P2 is the horizontal angle of the cradle head at the current position; PV is the horizontal visual angle of the camera, P2 is smaller than P1 and represents right shake, and P2 is larger than P1 and represents left shake; and/or the number of the groups of groups,

In this embodiment, when it is determined that the shake direction in the horizontal direction is right shake, the left edge clipping ratio x1:x1=px_p2_p1|/PV of the current image may be obtained according to the following formula;

the right edge clipping ratio x2:x2=px+|p2-p1|/PV of the current image can be obtained according to the following formula.

When the dithering direction in the horizontal direction is determined to be dithering left, the left edge clipping ratio x3:x3=px+|p2-p1|/PV of the current image can be obtained according to the following formula;

the right edge clipping ratio x4:x4=px- |p2-p1|/PV of the current image can be obtained according to the following formula.

In the above formula, the meanings of P1, P2 and PV are the same as the meanings of the corresponding parameters in the above formula; PX is an image horizontal edge clipping scale threshold.

In the above formula, the meanings of T1, T2 and TV are the same as those of the corresponding parameters in the above formula. TX is the image upper and lower edge clipping scale threshold.

In an embodiment of the present invention, the image processing apparatus further includes: a threshold judgment unit configured to:

after determining the jitter ratio of the current image to the right or left in the horizontal direction with respect to the reference image, before determining the left or right edge clipping region of the current image, determining whether the jitter ratio of the current image to the right or left in the horizontal direction with respect to the reference image is smaller than the image horizontal edge clipping ratio threshold, and if so, determining the left or right edge clipping region of the current image by the left or right clipping region determining module 121;

and/or the number of the groups of groups,

after determining the jitter ratio of the current image to the reference image jittering upward or downward in the up-down direction, before determining the upper or lower edge clipping region of the current image, determining whether the jitter ratio of the current image to the reference image jittering upward or downward in the up-down direction is smaller than the image upper and lower edge clipping ratio threshold, if so, determining the upper or lower edge clipping region of the current image by the upper and lower clipping region determining module 122.

Similarly, the dithering ratio of the current image to the upper side or the lower side of the reference image in the up-down direction is smaller than the upper and lower edge clipping ratio threshold value of the image, which indicates that the image dithering is within an acceptable range; if the jitter proportion of the current image to the upper side or the lower side of the reference image in the up-down direction is larger than the cutting proportion threshold value of the upper edge and the lower edge of the image, the image jitter is too large, the current image can be discarded, cutting is not performed on the current image, the current image is not used for subsequent image recognition, and therefore the accuracy of subsequent image recognition can be further improved.

Referring to fig. 7, the embodiment of the invention also provides a forest fire prevention system, which comprises a camera 21, an image processing device 22 and a fire recognition device 23; wherein, the camera 21 is installed on the shooting of the forest scene and is used for collecting the image of the forest scene; the image processing device 22 is used for processing the image acquired by the camera; the fire recognition device 23 is configured to recognize the image processed by the image processing device to determine whether a fire exists in the forest scene; the image processing device is any one of the image processing devices described in the foregoing embodiments.

The system of the present embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and are not described here again.

Fig. 8 is a schematic structural diagram of an embodiment of an electronic device according to the present invention, where the flow of the embodiment shown in fig. 1, fig. 2, and fig. 4 may be implemented, and as shown in fig. 8, the electronic device may include: the device comprises a shell 41, a processor 42, a memory 43, a circuit board 44 and a power circuit 45, wherein the circuit board 44 is arranged in a space surrounded by the shell 41, and the processor 42 and the memory 43 are arranged on the circuit board 44; a power supply circuit 45 for supplying power to the respective circuits or devices of the above-described electronic apparatus; the memory 43 is for storing executable program code; the processor 42 executes a program corresponding to the executable program code by reading the executable program code stored in the memory 43 for executing the image processing method described in any of the foregoing embodiments.

The specific implementation of the above steps by the processor 42 and the further implementation of the steps by the processor 42 through the execution of the executable program code may be referred to in the embodiments of fig. 1, 2 and 3 of the present invention, and will not be described herein.

The electronic device exists in a variety of forms including, but not limited to:

(1) Personal computer device: such devices are in the category of personal computers, having computing and processing functions, and generally also having mobile internet access characteristics.

(2) And (3) a server: the configuration of the server includes a processor, a hard disk, a memory, a system bus, and the like, and the server is similar to a general computer architecture, but is required to provide highly reliable services, and thus has high requirements in terms of processing capacity, stability, reliability, security, scalability, manageability, and the like.

(3) Other electronic devices with data interaction functions.

Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs executable by one or more processors to implement the image processing method according to any of the foregoing embodiments.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or device. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or device comprising the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

In particular, for the device embodiments, since they are substantially similar to the device embodiments, the description is relatively simple, and reference is made to the description of the device embodiments in part.

For convenience of description, the above apparatus is described as being functionally divided into various units/modules, respectively. Of course, the functions of the various elements/modules may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.

Those skilled in the art will appreciate that implementing all or part of the above-described embodiments of the apparatus may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of embodiments of the apparatus as described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. An image processing method, comprising:

Acquiring the jitter amplitude and jitter direction of a lens of a camera relative to the jitter amplitude and jitter direction of a shooting reference image when shooting a current image; the camera is used for shooting images of the target monitoring area; the target area comprises one of a forest fire prevention monitoring area and a road traffic monitoring area; the images shot by the camera comprise a plurality of continuous images, and the images shot at a certain moment in the plurality of continuous images are the reference images;

determining an edge clipping region of the current image shot by the lens according to the jitter amplitude, the jitter direction and a preset edge clipping threshold; the edge cutting area of the current image is an area of the current image after cutting according to the edge cutting area of the current image;

the obtaining of the jitter amplitude and jitter direction of the lens of the camera relative to the current image when the reference image is shot comprises:

acquiring a shake angle or shake displacement amount of a lens of a camera in a horizontal direction relative to a reference image when a current image is shot, and a shake direction to the right or left in the horizontal direction; and/or the number of the groups of groups,

Acquiring a shake angle or shake displacement amount of a lens of a camera in an up-down direction and a shake direction in an up-down direction or a down direction relative to a reference image when shooting a current image;

the determining the edge clipping area of the current image shot by the lens according to the jitter amplitude, the jitter direction and the preset edge clipping threshold value comprises the following steps:

determining the edge cutting proportion or cutting size of the left edge and the right edge of the current image shot by the camera according to the shake angle or shake displacement amount of the camera lens in the horizontal direction relative to the shake direction of the camera lens in the shooting reference image when the current image is shot, and presetting an edge cutting threshold value in the horizontal direction; and/or the number of the groups of groups,

and determining the edge cutting proportion or cutting size of the upper side edge and the lower side edge of the current image shot by the camera according to the dithering angle or dithering displacement amount of the camera in the up-down direction relative to the dithering direction in the up-down direction when shooting the reference image and the preset edge cutting threshold value.

2. The image processing method according to claim 1, wherein,

The obtaining of the shake angle of the lens of the camera in the horizontal direction relative to the shooting of the reference image when shooting the current image comprises the following steps:

The obtaining the shake angle of the lens of the camera in the up-down direction relative to the shooting reference image when shooting the current image comprises the following steps:

3. The image processing method according to claim 1, wherein,

the obtaining of the shake displacement amount of the lens of the camera in the horizontal direction relative to the shooting of the reference image when shooting the current image comprises the following steps: acquiring a reference image and a current image shot by a lens of a camera; comparing the reference point in the image, the horizontal coordinate value in the reference image and the horizontal coordinate value in the current image to obtain the shake displacement of the lens of the camera in the horizontal direction relative to the time of shooting the reference image when shooting the current image;

4. The image processing method according to claim 1, wherein the determining the edge clipping ratio of the left side edge and the right side edge of the current image captured by the lens includes:

The determining the edge clipping proportion of the upper side edge and the lower side edge of the current image shot by the lens comprises the following steps:

The determining the edge clipping size of the left side edge and the right side edge of the current image shot by the lens comprises the following steps:

The determining the edge clipping size of the upper side edge and the lower side edge of the current image shot by the lens comprises the following steps:

5. The image processing method according to claim 4, wherein the shake ratio F1 of the current image to the right or left in the horizontal direction with respect to the reference image is determined according to the following formula:

F1＝|P2-P1|/PV；

wherein P1 is the shooting horizontal angle of the lens of the camera at the reference position, and P2 is the shooting horizontal angle of the lens of the camera at the current position; or, P1 is the horizontal angle of the cradle head at the reference position, and P2 is the horizontal angle of the cradle head at the current position; PV is the horizontal visual angle of the camera, P2 is smaller than P1 and represents right shake, and P2 is larger than P1 and represents left shake;

and/or the number of the groups of groups,

the shake ratio F2 of the current image to the reference image in the up-down direction to the up-down or down direction is determined according to the following formula:

F2＝|T2-T1|/TV；

wherein T1 is a shooting pitch angle of a lens of the camera at a reference position, and T2 is a shooting pitch angle of the lens of the camera at a current position; or, T1 is the pitch angle of the cradle head at the reference position, and T2 is the pitch angle of the cradle head at the current position; TV is the vertical view angle of the camera, T2 is smaller than T1 indicating downward shake, and T2 is larger than T1 indicating upward shake.

6. The image processing method according to claim 4, wherein after determining a shake ratio at which the current image is shake to the right or left in the horizontal direction with respect to the reference image, before determining the left or right edge clipping region of the current image, the method further comprises:

Determining whether the jitter proportion of the current image to the right side or the left side of the reference image in the horizontal direction is smaller than the image horizontal edge clipping proportion threshold value, and if so, executing the step of determining the left side or the right side edge clipping area of the current image;

and/or the number of the groups of groups,

after determining the dither proportion of the current image to the reference image in the up-down direction to the up-down or down side, before determining the upper or lower side edge clipping region of the current image, the method further includes:

determining whether a jitter ratio of the current image to the reference image in the up-down direction to the up-down or down direction is smaller than an image up-down edge clipping ratio threshold, and if so, executing the step of determining an up-down edge clipping area of the current image.

7. An image processing apparatus, comprising:

a shake acquiring unit for acquiring a shake amplitude and a shake direction of a lens of the camera relative to a reference image when the current image is shot; the camera is used for shooting images of the target monitoring area; the target area comprises one of a forest fire prevention monitoring area and a road traffic monitoring area; the images shot by the camera comprise a plurality of continuous images, and the images shot at a certain moment in the plurality of continuous images are the reference images;

A clipping region determining unit, configured to determine an edge clipping region of the current image shot by the lens according to the jitter amplitude and the jitter direction and a preset edge clipping threshold; the edge cutting area of the current image is an area of the current image after cutting according to the edge cutting area of the current image;

the shake acquisition unit includes:

the horizontal shake acquisition module is used for acquiring a shake angle or shake displacement amount of a lens of the camera in a horizontal direction relative to a reference image when the lens of the camera shoots a current image and a shake direction to the right or left in the horizontal direction; and/or the number of the groups of groups,

the up-down jitter acquisition module is used for acquiring a jitter angle or jitter displacement amount of a lens of the camera in an up-down direction and a jitter direction in an up-down direction or a down direction relative to a reference image when the lens of the camera shoots a current image;

the clipping region determining unit includes: a left-right clipping region determining module and/or an up-down clipping region determining module; wherein,,

the left and right clipping region determining module is used for determining the edge clipping proportion or clipping size of the left side edge and the right side edge of the current image shot by the camera according to the shake angle or shake displacement amount of the camera lens in the horizontal direction relative to the shake direction of the camera lens in the horizontal direction when the reference image is shot, and the edge clipping threshold value in advance;

The upper and lower clipping region determining module is used for determining the edge clipping proportion or clipping size of the upper side edge and the lower side edge of the current image shot by the camera according to the upper and lower jitter angle or jitter displacement amount of the camera lens relative to the upper and lower jitter direction when the reference image is shot and the preset edge clipping threshold value.

8. The image processing apparatus according to claim 7, wherein the horizontal shake acquisition module includes: a horizontal shake angle acquisition sub-module and/or an up-down shake angle acquisition sub-module; wherein,,

the horizontal shake angle acquisition sub-module is used for:

the up-down shaking angle obtaining sub-module is used for:

9. The image processing apparatus according to claim 7, wherein the horizontal shake acquisition module includes: a horizontal shake displacement amount acquisition sub-module and an up-down shake displacement amount acquisition sub-module; wherein,,

10. The image processing apparatus according to claim 7, wherein the left and right clipping region determination module includes: a left-right clipping proportion determining sub-module, a left-right clipping size determining sub-module, an up-down clipping proportion determining sub-module and an up-down clipping size determining sub-module; wherein,,

the left-right clipping proportion determination submodule is used for:

the up-down clipping proportion determining submodule is used for:

the left-right clipping size determining submodule is used for:

the up-down clipping size determining submodule is used for:

11. The image processing apparatus according to claim 10, wherein the left-right clipping ratio determining submodule determines the shake ratio F1 of the current image to shake to the right or left in the horizontal direction with respect to the reference image according to the following formula:

F1＝|P2-P1|/PV；

And/or the number of the groups of groups,

the up-down clipping proportion determining submodule determines a jitter proportion F2 of the current image to be dithered to the upper side or the lower side in the up-down direction relative to the reference image according to the following formula:

F2＝|T2-T1|/TV；

12. The image processing apparatus according to claim 10, further comprising: a threshold judgment unit configured to:

after determining the jitter proportion of the current image to the right or left in the horizontal direction relative to the reference image, before determining the left or right edge clipping region of the current image, determining whether the jitter proportion of the current image to the right or left in the horizontal direction relative to the reference image is smaller than the image horizontal edge clipping proportion threshold value, and if so, determining the left or right edge clipping region of the current image by a left or right clipping region determining module;

And/or the number of the groups of groups,

13. The forest fire prevention system is characterized by comprising a camera, an image processing device and a fire recognition device; wherein,,

the camera is arranged on shooting of a forest scene and used for collecting images of the forest scene;

the image processing device is used for processing the image acquired by the camera;

the fire identification device is used for identifying the image processed by the image processing device so as to determine whether fire exists in the forest scene;

wherein the image processing apparatus is an image processing apparatus according to any one of the preceding claims 7 to 12.

14. An electronic device, the electronic device comprising: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space surrounded by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, for executing the image processing method according to any one of the preceding claims.

15. A computer readable storage medium storing one or more programs executable by one or more processors to implement the image processing method of any preceding claim.