CN105227948A - A kind of method and device searching distorted region in image - Google Patents

Abstract

The embodiment of the present invention discloses a method for searching a distorted area in an image, comprising: acquiring a target image collected by a camera, acquiring a foreground target area in the target image; acquiring depth information of a foreground target corresponding to the foreground target area; Calculate the distortion radius corresponding to the foreground target area according to a preset linear function with the depth information of the foreground target as an argument; find the pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius points, and determine the area formed by the searched pixels as the distorted area. The invention also correspondingly proposes a device for searching the distorted area in the image. By adopting the present invention, the calculation amount in the process of processing the lens distortion phenomenon in the photographing process is reduced, the processing efficiency is improved, and the user experience is improved.

Description

A method and device for finding a distorted region in an image

technical field

The invention relates to the field of computer technology, in particular to a method and a device for searching a distorted area in an image.

Background technique

In the prior art, general optical lenses will have a certain degree of lens distortion when imaging, and it is difficult to achieve the effect of ideal lens imaging, and the lens distortion is an inherent characteristic of optical lenses (convex lens converges light, concave lens diverges light). Therefore, although this distortion is very detrimental to the imaging quality of the photo, it cannot be completely eliminated.

Generally speaking, when users use portable devices such as smart phones to take pictures, their purpose is mostly to reproduce the scene at the time of taking pictures, especially to reproduce the imaging area of objects, people or buildings, that is, whether the target image area is real or not. , or whether there is distortion, but a certain degree of image distortion in the non-target image area can be ignored. Aiming at problems such as image distortion and distortion, there is a method of correcting image distortion in the prior art, that is, obtaining the distortion coefficient of the lens in advance, and correcting the coordinates of the imaging point after imaging, thereby improving the accuracy of the image point coordinates. Accuracy, thereby correcting distortions that appear in the image to a certain extent. However, the above distortion correction method requires a series of calculations after imaging, which will increase the amount of calculations in the image processing process after imaging.

Therefore, in the prior art, there is a problem of large amount of calculation in the way of processing the lens distortion that occurs during the photographing process.

Contents of the invention

Based on this, in order to solve the technical problem of excessive calculation in the above-mentioned traditional technology for processing the lens distortion that occurs during the photographing process, a method for finding the distorted area in the image is specially provided.

A method of finding distorted regions in an image, comprising:

Obtain the target image collected by the camera, and obtain the foreground target area in the target image;

Obtaining depth information of a foreground object corresponding to the foreground object area;

calculating a distortion radius corresponding to the foreground object area according to a preset linear function using the depth information of the foreground object as an independent variable;

Find the pixel points in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixel points as the distortion area.

Optionally, the step of acquiring the depth information of the foreground object corresponding to the foreground object area further includes: acquiring the depth information of the foreground object corresponding to the foreground object area through dual cameras.

Optionally, the step of obtaining the depth information of the foreground object corresponding to the foreground object area further includes: selecting a preset number of reference pixels in the foreground object area, and obtaining the depth information corresponding to the reference pixels , and calculate the average value of the depth information of all reference pixel points, and use the average value of the depth information of all reference pixel points as the depth information of the foreground object corresponding to the foreground object area.

Optionally, the step of acquiring the foreground target area in the target image further includes: acquiring at least two foreground target areas in the target image;

The step of obtaining the depth information of the foreground object corresponding to the foreground object area further includes: respectively obtaining the depth information of at least two foreground objects corresponding to the at least two foreground object areas;

The step of calculating the distortion radius corresponding to the foreground object area according to the preset linear function using the depth information of the foreground object as an argument further includes: using the depth information of the foreground object according to the preset linear function is an independent variable, respectively calculating the distortion radius corresponding to the at least two foreground target areas;

The step of searching for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determining the area formed by the found pixels as a distortion area further includes: separately searching for the at least two For pixels in the foreground target areas whose distance from the center point of the target image is greater than the distortion radius, the areas formed by the found pixels are respectively determined as the distortion areas corresponding to the at least two foreground target areas.

Optionally, after the step of determining the area formed by the found pixels as a distorted area, it further includes: highlighting the distorted area in the target image, the way of highlighting includes highlighting, Add at least one of the borders.

In addition, in order to solve the above-mentioned technical problem of excessive calculation in the processing method of the lens distortion occurring in the photographing process in the above-mentioned traditional technology, the present invention also provides a device for searching the distorted area in the image.

A device for finding a distorted area in an image, comprising: a foreground target area acquisition module, configured to acquire a target image collected by a camera, and acquire a foreground target area in the target image;

a depth information acquisition module, configured to acquire the depth information of the foreground object corresponding to the foreground object area;

A distortion radius calculation module, configured to calculate a distortion radius corresponding to the foreground target area according to a preset linear function with the depth information of the foreground target as an independent variable;

The distortion area determination module is configured to search for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels as the distortion area.

Optionally, the depth information acquisition module is further configured to: acquire the depth information of the foreground object corresponding to the foreground object area through dual cameras.

Optionally, the depth information acquisition module is further configured to: select a preset number of reference pixels in the foreground target area, acquire depth information corresponding to the reference pixels, and calculate depth information of all reference pixels The average value of the depth information of all reference pixels is the depth information of the foreground object corresponding to the foreground object area.

Optionally, the foreground target area acquisition module is further configured to: acquire at least two foreground target areas in the target image; the depth information acquisition module is also configured to: respectively acquire the at least two foreground target areas corresponding Depth information of at least two foreground targets in ;

The distortion radius calculation module is further configured to: respectively calculate the distortion radii corresponding to the at least two foreground object areas according to a preset linear function with the depth information of the foreground object as an independent variable;

The distortion area determination module is further configured to: respectively search for pixels in the at least two foreground target areas whose distance from the center point of the target image is greater than the distortion radius, and respectively divide the areas formed by the found pixels into It is determined as a distorted area corresponding to the at least two foreground target areas.

Optionally, the device further includes a highlight display module, configured to highlight the distorted region in the target image, and the highlight display manner includes at least one of highlighting and bordering.

Implementing the embodiment of the present invention will have the following beneficial effects:

After adopting the above-mentioned method and device for finding the distorted region in the image, in the process of taking pictures, aiming at the lens distortion phenomenon caused by the inherent optical characteristics of the lens, the distance between the foreground target or the position of the subject that the user cares about and the distance from the lens is calculated, In order to determine the area where distortion will occur at this distance position, if the area where the foreground object is located coincides with the area where distortion will occur, the area will be identified as the distortion area, that is, the foreground object or subject that the user cares about Distortion occurs and needs to be adjusted. Compared with the traditional technology, the above-mentioned method and device for finding the distortion region in the image avoids a series of distortion correction calculations after imaging in the process of processing lens distortion, reduces the amount of calculation in the imaging process, and improves imaging. processing efficiency.

At the same time, the user can also know the distortion that may occur during the photographing process, and make further adjustments, so that the distortion can be actively avoided on the object that the user cares about, and the user experience is improved.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

in:

Fig. 1 is a schematic flow chart of a method for finding a distorted region in an image in an embodiment;

Fig. 2 is a schematic diagram of a foreground target area of a target image in an embodiment;

Fig. 3 is a schematic diagram of a foreground target area of a target image in an embodiment;

Fig. 4 is a schematic diagram of region division in a target image in an embodiment;

Fig. 5 is a spatial schematic diagram of the area where the latitude unit corresponding to the lens is located in an embodiment;

Fig. 6 is a spatial schematic diagram of the area where the latitude unit corresponding to the lens is located in an embodiment in another embodiment;

Fig. 7 is a schematic diagram of region division in a target image in an embodiment in an embodiment;

Fig. 8 is a schematic structural diagram of an apparatus for finding a distorted region in an image in an embodiment.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

In order to solve the technical problem of excessive calculation in the traditional technology mentioned above in the processing of the lens distortion that occurs during the photographing process, a method for finding the distorted area in the image is provided, which can be implemented by a computer program, the computer program may be a camera application program in a smart phone, or an image processing program running on a camera terminal. The computer program can run on a computer system based on the Von Neumann architecture. The computer system may be a terminal device such as a smart phone, a tablet computer, a handheld computer, or a camera installed with a camera application or an image processing application.

Specifically, the method for finding a distorted region in an image is shown in Figure 1, and the method includes the following steps:

Step S102: Obtain a target image captured by a camera, and acquire a foreground target area in the target image.

The target image is the image obtained through the camera set on the terminal, and the target image can be displayed on the display screen set on the terminal for the user to preview or confirm the scene captured by the camera, and can be based on Further operations are performed on the target image, for example, manual focus, that is, the user manually selects a target to be focused on. It should be noted that the determination of the focal length in the focusing process in the acquisition process of the above target image, or the selection of the subject to be focused can be done by the terminal itself, that is, automatic focusing, or it can be done by the user according to his own needs. Manually select to complete the focusing process.

The target image includes background and foreground targets. After the target image is acquired, the foreground target region corresponding to the foreground target in the target image can be extracted according to the segmentation algorithm of the foreground target. It should be noted that, in this embodiment, the acquisition process of the foreground target area can be that the terminal automatically extracts the area where the foreground target in the target image is located according to the acquired target image; The main body determines the foreground target that the user cares about, so as to determine the foreground target area that needs to be acquired in this method.

The shape of the foreground target area can be changeable, for example, it can be a circle centered on the corresponding point of the center of the foreground target in the target image and the preset length is the radius, or it can be the center of the foreground target in the target image Any preset shape centered on the corresponding point in , can also be an area composed of pixels corresponding to the foreground object extracted according to the actual situation, and this area is the foreground object area.

As shown in Figure 2, Figure 2 shows a shot image of a person in the application scene, the image is the target image acquired by the camera, and the areas marked 1, 2, 3, 4 are the target images foreground target area.

As shown in Figure 3, Figure 3 shows a schematic diagram of shooting in a camera application scenario. The area C shown in the schematic diagram is the area where the target image obtained by the camera is located, and the point marked A is the user's own selection. The reference point of the shooting subject, the circular area B with the reference point as the center and the preset radius length R as the radius is the foreground target area in the target image.

Step S104: Obtain the depth information of the foreground object corresponding to the foreground object area.

The depth information of the foreground object is the distance information between the foreground object and the lens. In this embodiment, there may be multiple ways of acquiring the distance between the foreground object and the lens.

For example, in one embodiment, the distance information between the foreground object and the lens is obtained by a distance sensor. Specifically, the distance sensor emits electromagnetic signals such as laser light or infrared light to the object under test and detects echoes to determine the Measure the distance between the object and the lens.

For another example, in another embodiment, the distance information between the foreground object and the lens is acquired through dual cameras. Specifically, two cameras are used to image images separately. Because there is a certain distance between the two cameras, the images formed by the same object will have certain differences in pixel coordinates and other information. That is to say, the difference between the two cameras Imaging, there will be a certain amount of parallax. The parallax of the above-mentioned dual-camera imaging can be used to estimate and calculate the physical distance between the object and the lens, that is, the depth information, and can further obtain the depth information of each pixel to form a depth image.

It should be noted that, in the acquisition of the depth information of the above-mentioned foreground object, the obtained depth information is used to represent the depth information of all pixels in the entire foreground object area. In this embodiment, which point or which area's depth is used The information is used to represent the depth information of the foreground target corresponding to the foreground target area, which can be selected, for example, it can be set for the user, it can also be preset by the system, or it can be randomly selected by the system a method.

Specifically, the depth information of any point in the foreground target area can be taken, and the depth information of this point can be used to represent the depth information of the entire foreground target area. It is also possible to take the corresponding depth information of a specific point in the foreground target area that meets the preset conditions to replace the depth information of the entire foreground target area, for example, take the depth information of the pixel point with the largest value corresponding to the depth information, for example Get the depth information corresponding to the center point of the foreground target area. In another embodiment, the depth information of the foreground target area can also be obtained by obtaining the distance corresponding to each pixel in the foreground target area, and calculating the average value of the distances corresponding to all points, and using the average value to represent Depth information of foreground objects.

In another embodiment, the acquisition of the depth information of the foreground object can also be the following calculation method: randomly select a certain number of pixels in the foreground object area, use these pixels as reference pixels, and obtain the depth information corresponding to the above reference pixels. distance information or depth information, and then calculate the average value of the depth information or distance information of all reference pixel points, and use the average value as the depth information of the foreground object corresponding to the foreground object area.

Step S106: Calculate a distortion radius corresponding to the foreground object area according to a preset linear function with depth information of the foreground object as an argument.

Distortion and distortion of the lens are caused by the characteristics of the lens itself, and the farther the lens is from the subject, the smaller the area formed by the pixels occupied by the subject in the imaging image. The smaller the size change. Since the distortion occurs in the peripheral area of the imaging image, that is to say, generally no distortion or distortion occurs near the center point of the imaging image. In this embodiment, the area where distortion may occur is called the area where the distortion range is located, and the area where distortion does not occur is called the area where the tolerance range is located. Generally speaking, the closer you are to the lens, the greater the distortion, the larger the distortion range, and the smaller the acceptable tolerance range; correspondingly, the farther you are from the lens, the smaller the distortion, the smaller the distortion range, and the acceptable tolerance range. The range is larger. Therefore, if the latitude range is determined, the distortion range in the imaging image can be obtained directly.

As shown in FIG. 4 , the scene shown in the figure is a schematic diagram of area division where the distortion range and tolerance range in the target image are located. In the figure, S2 indicates the area where the acceptable latitude range is located, and S1 indicates the area where the distortion range where distortion or distortion phenomenon occurs in the target image is located.

In this embodiment, the latitude range of the object at a certain position outside the lens, when the lens is regarded as a point, that is, the influence of the size of the lens is ignored, and the latitude range can be regarded as the range of the lens. A cone whose center gradually diverges outwards, the cone takes the center of the lens as the apex, and the distance between the object and the lens is high (that is, the depth information of the foreground target obtained in step S104 is the height of the cone) , the bottom radius is the default value.

As shown in Figure 5, D shown in the figure is the distance between the object and the lens, that is, the depth information obtained in step S104, and the range shown by the cone in the figure is the latitude range, that is, there is no The extent of the distortion. Depending on the lens, the angle θ between the generatrix and the height of the cone will also be different, that is to say, the setting of the angle θ is determined by the hardware setting or hardware structure of the lens. After the camera is formed, the angle θ angle can be determined.

In order to calculate the radius of the circular area of the section where the object to be photographed is located, the following formula can be obtained according to the geometric structure of the cone:

r = tan θ·D.

According to the above formula, the radius of the circular area where the latitude range is located can be determined, so that the range of the distortion area can be determined, and the distortion area is all areas in the target image except the area where the latitude range is located.

In another embodiment, considering the influence of the size of the lens, the latitude range of the object at a certain position outside the lens can be regarded as the plane where the lens is located as the plane where the upper base is located, and the center point of the lens as is the center of the upper base, the height is the distance between the object and the lens (that is, the depth information of the foreground object acquired in step S104 is the height of the cone), and the radius of the lower base is the preset value of the frustum of a cone.

As shown in Figure 6, θ is the angle between the busbar and the height, r is the radius of the lens, the radius of the bottom surface under R is the distortion radius, and D is the distance between the object and the lens, according to the following formula Compute the radius of the lower base, the distortion radius:

R=r+tanθ·D.

Step S108: Search for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels as the distortion area.

In step S106, in the process of considering the latitude range, the latitude range is regarded as a circular area with the center point of the target image and the distortion radius as the radius, so every point in the latitude range to the distance of the target image The distance between the center points must be less than or equal to the above-mentioned distortion radius. Conversely speaking, if the distance from a certain point to the center point is greater than the distortion radius, the point is no longer within the above-mentioned tolerance range.

Specifically, traverse all the pixel points included in the foreground target area, and calculate the distance between the pixel point and the pixel point corresponding to the center point of the target image according to the coordinate position of the pixel point.

For example, if the target image is an image of 1400*900 (that is, there are 1440 pixel columns in the horizontal direction and 900 pixel rows in the vertical direction), the coordinates of the center point of the target image are (x ₀ , y ₀ )=(700,450); further Generally, the space occupied by each pixel is a×a (that is, the horizontal width is a unit, and the vertical width is a unit). Then the distance between the pixel point with coordinates (x ₁ , y ₁ ) and the pixel point corresponding to the center point is:

$\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; \&CenterDot;</span>\sqrt{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; ,</span>$

Then judge the size relationship between d and the distortion radius R.

If d>R, it means that the pixel with the coordinates (x ₁ , y ₁ ) is not in the set of pixels included in the area where the tolerance range is located, that is, the set of pixels included in the area where the distortion range is located middle; if d>R, it means that the pixel with the coordinates (x ₁ , y ₁ ) is included in the set of pixels contained in the region where the tolerance range is located.

Traversing all the pixels contained in the foreground target area, when the distance between the pixel and the center point of the target image is greater than the distortion radius, add the pixel to the pixel set in the distortion area, and add the pixels in the set The area formed by all pixels is determined as a distorted area, that is, the area is marked as a distorted area.

If the set of pixel points in the above-mentioned distorted area is not an empty set, it means that distortion occurs in the foreground target area in the target image. If there is a phenomenon of distortion, it is necessary to display the relevant prompt information to the user. The prompt information should include the specific areas where distortion will occur, so as to perform corresponding operations according to the prompt information, so as to avoid the subject or foreground target in the target image. Distortion occurs.

As shown in Figure 7, Figure 7 shows a schematic diagram of the area division of a target image, the area numbered S1 is the area where the tolerance range is located, the area numbered S2 is the area where the distortion phenomenon is located, and the area numbered S3 is the foreground The target area, the area numbered S4 is the intersection of S2 and S3, that is, the area where the pixel point in the foreground target area found in step S108 is located with a distance greater than the distortion radius from the center point of the target image, that is, the distortion area.

Further, in this embodiment, in step S108: search for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels to be distorted After the region, the method further includes the step of: highlighting and displaying the distorted region in the target image, the way of highlighting and displaying includes at least one of highlighting and adding a frame.

Specifically, the previewed image is displayed on the display screen of the terminal, and the target image is previewed in real time. In the image, the distorted area is prominently displayed on the display screen of the terminal.

For example, as shown in Figure 7, what Figure 7 shows is the image displayed on the display screen of the terminal. When S4 is not empty, add a border to the area where the distortion area S4 is located on the displayed on the display page of the display.

Optionally, in the preview image shown to the user on the display screen of the terminal, the area where the corresponding latitude range is located, the area where the distortion range is located, and the foreground target area can also be displayed on the display screen, so as to For user reference.

It should be noted that, in other embodiments, the number of foreground target areas contained in the target image may be more than one, that is, in step S102, after the step of acquiring the target image collected by the camera, at least one of the target images is acquired Foreground target area.

For example, in the application scenario shown in FIG. 2 , the target image includes four foreground target areas labeled 1, 2, 3, and 4.

Correspondingly, in step S104: acquiring the depth information of the foreground object corresponding to the foreground object area, the depth information of the foreground object corresponding to the at least one foreground object area is acquired, that is, each of the foreground objects acquired in step S102 is acquired. Depth information of a foreground object corresponding to a foreground object area. In step S106: in calculating the distortion radius corresponding to the foreground object area according to the preset linear function and using the depth information of the foreground object as an argument, the number of calculated distortion radii is also corresponding to the above-mentioned foreground object area .

That is to say, when there are multiple foreground object areas, it is necessary to obtain the depth information of the corresponding foreground object for each foreground object area, and then calculate the distortion radius corresponding to each depth information.

Correspondingly, in step S108, the pixel points in each foreground target area whose distance from the center point of the target image is greater than the distortion radius are also searched for, and for each foreground target area, it is judged whether its corresponding distortion area exists, And in the subsequent process of displaying to the user, multiple distorted regions are displayed on the display interface.

In order to solve the above-mentioned technical problem of excessive calculation of lens distortion in the process of taking pictures in the above-mentioned traditional technology, the present invention also provides a device for searching the distorted area in the image, the device includes the foreground object The area acquisition module 102, the depth information acquisition module 104, the distortion radius calculation module 106 and the distortion area determination module 108, wherein:

The foreground target area acquisition module 102 is used to acquire the target image collected by the camera, and acquire the foreground target area in the target image;

The depth information obtaining module 104 is used for obtaining the depth information of the foreground object corresponding to the foreground object area;

The distortion radius calculation module 106 is used to calculate the distortion radius corresponding to the foreground object area according to a preset linear function with the depth information of the foreground object as an independent variable;

The distorted area determination module 108 is used to search for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels as the distorted area.

Optionally, the depth information acquiring module 104 is further configured to acquire the depth information of the foreground object corresponding to the foreground object area through dual cameras.

Optionally, the depth information acquisition module 104 is further configured to: select a preset number of reference pixels in the foreground target area, acquire depth information corresponding to the reference pixels, and calculate the sum of the depth information of all reference pixels. An average value, using the average value of the depth information of all reference pixel points as the depth information of the foreground object corresponding to the foreground object area.

Optionally, the foreground target area acquiring module 102 is further configured to: acquire at least two foreground target areas in the target image;

The depth information obtaining module 104 is further configured to: respectively obtain the depth information of at least two foreground objects corresponding to the at least two foreground object areas;

The distortion radius calculation module 106 is further configured to: respectively calculate the distortion radii corresponding to the at least two foreground object areas according to a preset linear function with the depth information of the foreground object as an independent variable;

The distortion area determination module 108 is further configured to: respectively search for pixels in the at least two foreground target areas whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels is the distorted area corresponding to the at least two foreground object areas.

Optionally, as shown in Figure 8, the device for finding a distorted region in an image further includes a highlight display module 110, configured to highlight and display the distorted region in the target image, the way of highlighting and displaying includes highlighting, adding a frame at least one of .

Implementing the embodiment of the present invention will have the following beneficial effects:

After adopting the above-mentioned method and device for finding the distorted region in the image, in the process of taking pictures, aiming at the lens distortion phenomenon caused by the inherent optical characteristics of the lens, the distance between the foreground target or the position of the subject that the user cares about and the distance from the lens is calculated, In order to determine the area where distortion will occur at this distance position, if the area where the foreground object is located coincides with the area where distortion will occur, the area will be identified as the distortion area, that is, the foreground object or subject that the user cares about Distortion occurs and needs to be adjusted. Compared with the traditional technology, the above-mentioned method and device for finding the distortion region in the image avoids a series of distortion correction calculations after imaging in the process of processing lens distortion, reduces the amount of calculation in the imaging process, and improves imaging. processing efficiency.

At the same time, the user can also know the distortion that may occur during the photographing process, and make further adjustments, so that the distortion can be actively avoided on the object that the user cares about, and the user experience is improved.

The above disclosures are only preferred embodiments of the present invention, and certainly cannot limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims (10)

1. A method for finding a distorted region in an image, comprising: Obtain the target image collected by the camera, and obtain the foreground target area in the target image; Obtaining depth information of a foreground object corresponding to the foreground object area; calculating a distortion radius corresponding to the foreground object area according to a preset linear function using the depth information of the foreground object as an independent variable; Find the pixel points in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixel points as the distortion area. 2. The method for searching for a distorted area in an image according to claim 1, wherein the step of obtaining the depth information of the foreground object corresponding to the foreground object area further comprises: The depth information of the foreground object corresponding to the foreground object area is acquired through dual cameras. 3. The method for searching for a distorted region in an image according to claim 1, wherein the step of obtaining the depth information of the foreground object corresponding to the foreground object region further comprises: Select a preset number of reference pixels in the foreground target area, obtain depth information corresponding to the reference pixels, and calculate the average value of the depth information of all reference pixels, and use the depth information of all reference pixels The average value of is the depth information of the foreground object corresponding to the foreground object area. 4. the method for the distorted region in the search image according to claim 1, is characterized in that, the step of described obtaining the foreground target region in the target image also comprises: acquiring at least two foreground object regions in the object image; The step of obtaining the depth information of the foreground object corresponding to the foreground object area further includes: respectively obtaining the depth information of at least two foreground objects corresponding to the at least two foreground object areas; The step of calculating the distortion radius corresponding to the foreground object area according to the preset linear function using the depth information of the foreground object as an argument further includes: using the depth information of the foreground object according to the preset linear function is an independent variable, respectively calculating the distortion radius corresponding to the at least two foreground target areas; The step of searching for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determining the area formed by the found pixels as a distortion area further includes: Respectively search for pixels in the at least two foreground target areas whose distance from the central point of the target image is greater than the distortion radius, and determine the area formed by the found pixel points as being the same as the at least two foreground targets The region corresponds to the distortion region. 5. The method for searching for a distorted region in an image according to claim 1, wherein the step of determining the region formed by the found pixels as a distorted region further includes: and highlighting the distorted region in the target image, the way of highlighting includes at least one of highlighting and adding a frame. 6. A device for finding a distorted region in an image, comprising: The foreground target area acquisition module is used to acquire the target image collected by the camera, and acquire the foreground target area in the target image; A depth information acquisition module, configured to acquire the depth information of the foreground object corresponding to the foreground object area; A distortion radius calculation module, configured to calculate a distortion radius corresponding to the foreground target area according to a preset linear function with the depth information of the foreground target as an independent variable; The distortion area determination module is configured to search for pixels in the foreground target area whose distance from the center point of the target image is greater than the distortion radius, and determine the area formed by the found pixels as the distortion area. 7 . The device for searching for a distorted area in an image according to claim 6 , wherein the depth information acquisition module is further configured to: acquire depth information of a foreground object corresponding to the foreground object area through dual cameras. 8. The device for searching for a distorted region in an image according to claim 6, wherein the depth information acquisition module is also used for: Select a preset number of reference pixels in the foreground target area, obtain depth information corresponding to the reference pixels, and calculate the average value of the depth information of all reference pixels, and use the depth information of all reference pixels The average value of is the depth information of the foreground object corresponding to the foreground object area. 9. The device for searching for a distorted region in an image according to claim 6, wherein the foreground target region acquisition module is further used to: acquire at least two foreground target regions in the target image; The depth information acquisition module is further configured to: respectively acquire the depth information of at least two foreground objects corresponding to the at least two foreground object areas; The distortion radius calculation module is further configured to: respectively calculate the distortion radii corresponding to the at least two foreground object areas according to a preset linear function with the depth information of the foreground object as an independent variable; The distortion area determination module is further configured to: respectively search for pixels in the at least two foreground target areas whose distance from the center point of the target image is greater than the distortion radius, and respectively divide the areas formed by the found pixels into It is determined as a distorted area corresponding to the at least two foreground target areas. 10. The device for finding a distorted region in an image according to claim 6, wherein the device further comprises a highlight display module for highlighting the distorted region in the target image, and the highlighted display The manner includes at least one of highlighting and bordering.