CN113678163A - Image correction method, device, electronic device and storage medium - Google Patents

Abstract

The present disclosure relates to the technical field of image processing, and in particular, to an image correction method, an apparatus, an electronic device and a storage medium. The method includes: acquiring a target image including four positioning marks collected by a camera, wherein the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals in sequence; The mark position in the target image; according to the mark position, the target image is corrected. The technical solution of the present disclosure automatically corrects the target image according to the four positioning marks in the target image, improves the accuracy and efficiency of framing, and ensures the consistency of framing results.

Description

Image correction method, device, electronic device and storage medium

technical field

Embodiments of the present disclosure relate to an image correction method, apparatus, electronic device, and storage medium.

Background technique

Framing is a necessary prerequisite for taking photos and videos, and framing is essentially to determine the relative position of the camera and the target object on the six axes of space, and framing directly affects the quality of photos and videos.

The existing viewfinder mainly relies on the human eye to observe the content of the photo in real time on the viewfinder or preview display screen to fine-tune the position of the camera, and sometimes relies on equipment such as laser ranging to simply judge the distance of the target object. However, the existing framing has problems such as large errors, low efficiency and poor repeatability.

SUMMARY OF THE INVENTION

(1) Technical problems to be solved

In the prior art, there are problems such as large errors, low efficiency and poor repeatability when taking pictures and framing.

(2) Technical solutions

According to various embodiments of the present disclosure, an image correction method, apparatus, electronic device, and storage medium are provided.

An image correction method, the method comprising:

Acquiring a target image including four positioning marks collected by the camera, wherein the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals and surrounding them in turn;

determining the identification positions of the four positioning marks in the target image;

The target image is corrected according to the marked position.

An image correction device, comprising:

an image acquisition module, configured to acquire a target image including four positioning marks collected by the camera, wherein the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals in turn and in a surrounding arrangement;

an identification position determination module, configured to determine the identification positions of the four positioning marks in the target image;

The image correction module is configured to correct the target image according to the identified position.

An electronic device includes a memory and one or more processors, the memory stores computer-readable instructions, and when one or more processors execute the computer-readable instructions, an image correction method provided by any embodiment of the present disclosure is implemented. step.

One or more non-volatile computer-readable instructions storing computer-readable instructions having computer-readable instructions stored thereon that, when executed by one or more processors, implement any of the embodiments of the present disclosure. The steps of an image correction method.

Other features and advantages of the present disclosure will be set forth in the description that follows, and in part will become apparent from the description. The objectives and other advantages of the disclosure will be realized and attained by the structure particularly pointed out in the description, claims and drawings. In order to make the above-mentioned objects, features and advantages of the present disclosure more obvious and easy to understand, optional embodiments are exemplified below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the accompanying drawings that are required to be used in the description of the embodiments or the prior art will be briefly introduced below. In other words, on the premise of no creative labor, other drawings can also be obtained from these drawings.

FIG. 1 is a schematic diagram of a positioning marker in one or more embodiments;

FIG. 2 is a schematic diagram of an identification plane in one or more embodiments;

3 is a schematic diagram of an application scenario in one or more embodiments;

4 is a schematic diagram of a deviation image and a standard image in one or more embodiments;

5 is a schematic flowchart of an image correction method in one or more embodiments;

6 is a schematic flowchart of an image correction method in one or more embodiments;

7 is a schematic diagram of the positional relationship between an image plane and an identification plane in one or more embodiments;

8 is a schematic diagram of a projection angle measurement in one or more embodiments;

9 is a structural block diagram of an image correction apparatus in one or more embodiments;

10 is a diagram of the internal structure of an electronic device in one or more embodiments.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure, but not to limit the present disclosure.

At present, framing mainly relies on the human eye to observe the content of the photo in real time on the viewfinder or preview display screen to fine-tune the position of the camera. However, due to the influence of human eye observation or the size of the viewfinder/preview display screen, it will inevitably bring about a large error in the position of the scene in the image; moreover, when precise positioning is required, the operator needs to observe and adjust the camera repeatedly, which is time-consuming and labor-intensive. The efficiency is low; in addition, the consistency of the results of multiple framing is an important prerequisite for ensuring image quality evaluation, but the positioning relying on human eye observation has the disadvantage of poor repeatability.

In view of the above technical problems, the embodiment of the present disclosure can improve the accuracy and efficiency of framing by acquiring a target image containing four positioning marks collected by a camera, and marking the position in the target image according to the four positioning marks to correct the target image. Consistency of framing results.

The positioning mark involved in the embodiment of the present disclosure may be a graphic with high contrast and spatial symmetry, and can have high anti-interference in image recognition, and the positioning mark may be a graphic as shown in FIG. 1 , such as positioning mark 110 , the positioning mark 120 , the positioning mark 130 and the positioning mark 140 , and the specific graphic structure of the positioning mark is not limited.

In the embodiment of the present disclosure, four positioning marks may be placed at fixed spatial positions relative to the shooting target to obtain a marking plane. For example, for the schematic diagram of a marking plane shown in FIG. 2 , the positioning mark 120 in FIG. The four positioning marks 120 are sequentially placed in the object space at equal intervals to obtain a mark plane, and the distance between any two adjacent positioning marks 120 is the same. In addition, the graphics of the four positioning marks in the identification plane may be the same or different.

The image correction method provided by the embodiment of the present disclosure may be executed by a terminal or a server. The terminal or server can correct the target image through the positions of the four positioning marks in the target image.

For example, in an application scenario, as shown in FIG. 3 , the server 32 calculates the deviation of the target image through the positions of the four positioning marks in the target image, and sends the deviation of the target image to the terminal 31, and the terminal 31 according to The received deviation is directly corrected for the target image, where the target image may be captured by the terminal 31 and sent to the server 32 . Alternatively, the target image is acquired by the terminal 31 from other devices. Alternatively, the target image is an image obtained after the terminal 31 performs image processing on the preset image, and the preset image may be obtained by the terminal 31 by shooting, or the preset image may be obtained by the terminal 31 from other devices. Here, other devices are not specifically limited.

In another application scenario, the terminal 31 acquires the target image, and sends the target image to the server 32, and the server 32 corrects the target image according to the positions of the four positioning marks in the target image.

In another application scenario, the terminal 31 captures and obtains the target image, and further, the terminal 31 corrects the target image according to the positions of the four positioning marks in the target image.

During the actual viewing process, due to the deviation of the relative positions of the camera and the target object, the target image collected by the camera is deviated from the standard image. In the embodiment of the present disclosure, the deviation of the target image relative to the standard image may include any one or a combination of the following: front-to-back deviation (refer to image (a) in FIG. 4 ); horizontal deviation (refer to image (b) in FIG. 4 ) ; Vertical deviation (refer to image (c) in Figure 4); Rotational deviation (refer to image (d) in Figure 4); Left and right flip deviation (refer to Figure 4 (e)); Up and down flip deviation (refer to Figure 4 Image in 4 (f)). In addition, the image (o) in FIG. 4 is a standard image. In the embodiment of the present disclosure, when the target image collected by the camera has at least one deviation among front and rear deviation, horizontal deviation, vertical deviation and rotation deviation, the image plane of the camera is still parallel to the marking plane, and when the target image collected by the camera appears When there is a flip deviation such as left-right flip deviation or up-down flip deviation, the image plane of the camera intersects with the marking plane. The technical solution of the present disclosure can calculate any of the above deviations or a combination of deviations, so as to correct the target image and obtain a standard image.

In one embodiment, as shown in FIG. 5 , an image correction method is provided. The image correction method is suitable for the precise positioning of the relative position of the camera and the target object, and can be applied to automatic optical detection and machine vision shooting. Scenes. This embodiment is exemplified by applying the method to a terminal, and the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The image correction method includes the following steps as shown in Figure 5:

S510: Acquire a target image including four positioning marks collected by the camera.

Optionally, the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals in sequence and in a surrounding arrangement.

Understandably, relative to the shooting target (target object), four positioning marks are placed at fixed spatial positions in the object space (actual space), referring to the positions of the four positioning marks in the mark plane shown in FIG. When there is a certain distance (object distance) from the shooting target, a target image is generated by collecting information including four positioning marks and the shooting target through the camera. The embodiments of the present disclosure are not limited to acquiring the target image by taking a photo, and the target image may also be acquired by means of previewing screenshots and video recordings.

S520: Determine the marker positions of the four positioning markers in the target image.

Understandably, on the basis of the above S510, the image processing algorithm can be used to calculate the identification positions of the four positioning marks in the target image, wherein the identification positions include the specific position information of the four positioning marks in the target image, such as four positioning marks. The coordinates of a positioning marker in the Cartesian coordinate system of the target image.

S530: Correct the target image according to the marked position.

In the embodiment of the present disclosure, the four positioning marks are used to locate the relative positions of the camera and the target object captured by the camera, so that the relative positions of the camera and the target object can be determined according to the mark positions of the four positioning marks, and then the relative positions of the camera and the target object can be determined by correcting the mark positions, namely The relative position of the camera and the target object can be corrected, and the target image can be corrected to obtain a standard image corresponding to the target image.

In the above-mentioned embodiment, the target image containing four positioning marks collected by the camera is acquired, wherein the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals in sequence; The mark position in the mark; according to the mark position, the target image is corrected. According to the technical solution of the present disclosure, four positioning marks are preset on the target object, and a camera is used to obtain a target image corresponding to the target object containing the above four positioning marks, and the photographed image can be determined according to the mark positions of the four positioning marks in the target image. The deviation of the target object can be quickly corrected according to the marked position, which improves the accuracy and efficiency of the framing and ensures the consistency of the framing results.

In one embodiment, as shown in Figure 6, an image correction method is provided. In this embodiment, according to the identification position, the target image is corrected, including the following steps as shown in Figure 6:

S610: Determine the mark deviation according to the mark position.

The identification deviation is used to represent the deviation between the target image and the standard image, and the standard image is a pre-shot image that meets the framing requirements and is used as a reference image for correcting the target image. Optionally, the identification deviation includes at least one of front and rear deviation, vertical deviation, horizontal deviation, rotation deviation and flip deviation, that is, the identification deviation may be front and rear deviation, vertical deviation, horizontal deviation, rotation deviation or flip deviation, or it may be A combination of two or more of front-to-back bias, vertical bias, horizontal bias, rotational bias, and flip bias. In the embodiment of the present disclosure, the front-to-back deviation means that the target image is enlarged or reduced relative to the standard image, but the imaging plane is parallel to the marking plane. For the target object, and the camera is too close or too far from the target object when moving along its main optical axis; vertical deviation refers to the vertical deviation of the target image relative to the standard image, but the imaging surface is parallel to the marking plane, which is reflected in the actual shooting. When the main optical axis of the camera is perpendicular to the marking plane, the camera is not facing the target object, and it translates up or down relative to the target object; horizontal deviation refers to the left and right deviation of the target image relative to the standard image, but the imaging plane is different from the standard image. The marking plane is parallel. In actual shooting, when the main optical axis of the camera is perpendicular to the marking plane, the camera is not facing the target object, and it translates to the left or right relative to the target object; the rotation deviation refers to the target image relative to the standard The image rotates counterclockwise or clockwise, but the imaging surface is parallel to the marking plane. In actual shooting, the camera is facing the target object when the main optical axis of the camera is perpendicular to the marking plane, and the camera is clockwise around its main optical axis. Or rotate counterclockwise; Flip deviation means that the target image is flipped relative to the standard image, and the imaging plane intersects the marking plane. In actual shooting, the camera shoots the target object when the main optical axis of the camera is not perpendicular to the marking plane. , that is, the camera shoots the target object at a certain tilt angle.

Optionally, determine the mark deviation according to the mark position, including S611 and S612:

S611: Determine the positional relationship between the image plane of the camera and the identification plane according to the identification position.

The positional relationship includes the image plane being parallel to or intersecting with the marking plane. The image plane refers to the plane where the target image captured by the camera is located. Understandably, the positional relationship is the positional relationship between the image plane and the identification plane when the camera captures the target image.

In an implementation of this embodiment, when the lengths of the first set of opposite sides determined by the marking positions are equal, and the lengths of the second set of opposite sides determined by the marking positions are equal, the image plane is parallel to the marking plane; When the lengths of any one of the first group of opposite sides and the second group of opposite sides are not equal, the image plane intersects with the identification plane.

Specifically, the four positioning marks sequentially include a first positioning mark, a second positioning mark, a third positioning mark and a fourth positioning mark in the arrangement direction. According to the location of the marker, the distance algorithm between the two points can be used to determine the first imaging distance between the first location marker and the second location marker, the second imaging distance between the second location marker and the third location marker, and the third location marker. The third imaging distance between the fourth positioning mark and the fourth positioning mark and the fourth imaging distance between the fourth positioning mark and the first positioning mark. The sides corresponding to the first imaging distance and the third imaging distance are the first group of opposite sides, and the sides corresponding to the second imaging distance and the fourth imaging distance are the second group of opposite sides. Thus, when the first imaging distance is equal to the third imaging distance, and the second imaging distance is equal to the fourth imaging distance, the image plane is parallel to the marking plane; when the first imaging distance and the third imaging distance are not equal, or When the second imaging distance is not equal to the fourth imaging distance, the image plane intersects the marking plane.

Exemplarily, referring to FIG. 7 , 710 shows that the image plane 712 is parallel to the marking plane 711 , that is, the camera 713 is placed directly in front of the marking plane 711 , and the camera 713 is located in the marking plane 711 on the diagonal connection of the four positioning marks. Right in front of the intersection, that is, the dotted line in the figure is perpendicular to the marking plane 711, the camera 713 generates a target image on the image plane 712, and the image plane 712 includes the target image. At this time, the imaging distances determined between the four positioning marks are equal, and the The generated target image is regarded as a reduced image of the identification plane. 720 represents the intersection of the image plane 721 and the identification plane 711, the lens of the camera 713 and the identification plane 711 have an inclination angle, that is, the main optical axis of the camera 713 is not perpendicular to the identification plane 711, and four of the image planes 721 corresponding to the camera 713 The positions of the positioning marks are also inclined with respect to the mark plane 711. At this time, the positions of the four positioning marks in the target image are inclined compared with the positions of the four positioning marks in the mark plane. The four positioning marks in the target image in FIG. 7 are respectively a first positioning mark P ₁ ′, a second positioning mark P ₂ ′, a third positioning mark P ₃ ′ and a fourth positioning mark P ₄ ′. At this time, the first imaging distance can be calculated according to the positions of P ₁ ' and P ₂ ', the second imaging distance can be calculated according to the positions of P ₂ ' and P ₃ ', and the second imaging distance can be calculated according to the positions of P ₃ ' and P ₄ '. The third imaging distance is calculated, and the fourth imaging distance can be calculated according to the positions of P ₄ ′ and P ₁ ′.

S612: Determine the mark deviation according to the positional relationship and the mark position.

In this embodiment, the positional relationship is first determined according to the position of the mark, and when the positional relationship is determined, the mark deviation is determined according to the mark position, which can improve the efficiency and accuracy of the identification deviation determination. For example, when the identification deviation is directly determined according to the identification position, if the distance between the two positioning marks determined by the identification position is not equal to the standard distance, the identification deviation may be a front-to-back deviation or a flip deviation, and further determination of the identification deviation is required. In the case where the positional relationship is determined, for example, the positional relationship is that the image plane is parallel to the marking plane, then the marking deviation in the above situation can only be the front-to-back deviation, and the positional relationship is that the image plane and the marking plane intersect, then the marking deviation in the above situation can only be is the inversion deviation.

Specifically, a rectangular coordinate system is established with the target image point in the image plane as the origin, the x-axis of the rectangular coordinate system is parallel to the first side determined by the preset standard position, and the y-axis of the rectangular coordinate system is determined parallel to the preset standard position On the second side of , the preset standard position is the position of the four positioning marks in the standard image; in the Cartesian coordinate system, the identification coordinates of the four positioning marks in the target image and the standard coordinates in the standard image are determined. The target image point can be located at the lower left corner of the image plane of the camera, so that all other image points are located in the first quadrant of the rectangular coordinate system, that is, the abscissa and the ordinate are both positive values, which is convenient for calculation. Referring to FIG. 4 , the four positioning marks P ₁ ”, P ₂ ”, P ₃ ” and P ₄ ” in the standard image (o), the edge P ₁ ” and P ₂ ” formed by the connection of P ₁ ” and P ₂ ” are pre- Let the first side determined by the standard position and the side P ₂ ”P ₃ ” formed by connecting P ₂ ” and P ₃ ” be the second side determined by the preset standard position.

Correspondingly, the identification deviation is determined according to the positional relationship and the identification position, including at least one of the following:

When the image plane is parallel to the marking plane, and the distance between the two points determined by the marking coordinates is not equal to the distance between the corresponding two points determined by the standard coordinates, the marking deviation is determined as the front and rear deviation;

When the image plane is parallel to the marking plane, and the average value of the ordinate determined by the marking coordinates is not equal to the average value of the ordinate determined by the standard coordinates, the marking deviation is determined to be the vertical deviation;

When the image plane is parallel to the marking plane, and the average abscissa determined by the marking coordinates is not equal to the average abscissa determined by the standard coordinates, the marking deviation is determined as a horizontal deviation;

When the image plane is parallel to the marking plane, and a line passing through the midpoints of the first set of opposite sides determined by the marking coordinates intersects the y-axis, or a straight line passing through the midpoints of the second set of opposite sides determined by the marking coordinates, and When the x-axis intersects, the identification deviation is determined as the rotation deviation;

When the image plane and the mark plane intersect, and the first group of opposite sides determined by the mark coordinates are not equal, or the second group of opposite sides determined by the mark coordinates are not equal, the mark deviation is determined as a flip deviation.

Exemplarily, referring to FIG. 4, in the target image (a), the distance P ₁ 'P ₂ ' between P ₁ ' and P ₂ ' is determined by the coordinates of P ₁ ' and P ₂ ', in the standard image (o) , the distance P ₁ ”P ₂ ” between P ₁ ” and P 2 ” is determined by the coordinates of the corresponding P ₁ ” and P ₂ ”, when P ₁ 'P ₂ ' is not equal to P ₁ ”P ₂ ”, determine the distance P 1 ”P ₂ ” The deviation is identified as the front-to-back deviation. Specifically, the front-to-back deviation may include forward translation deviation or backward translation deviation. When P ₁ 'P ₂ ' is greater than P ₁ 'P ₂ ', it is forward translation deviation, that is, the camera is too close to the target object; when P ₁ When 'P ₂ ' is smaller than P ₁ ”P ₂ ””, it is the backward translation deviation, that is, the camera is too far from the target object.

Referring to FIG. 4 , the average value of the ordinate determined by the coordinates of P ₁ ′, P ₂ ′, P ₃ ′ and P ₄ ′ in the target image (c) is not equal to that of P ₁ ″, P ₂ in the standard image (o) ”, P ₃ ” and P ₄ ” are determined as the average value of the ordinates, and the identification deviation is determined as the vertical deviation. Specifically, the vertical deviation includes an upward translation deviation or a downward translation deviation. When the average value of the ordinate determined by the coordinates of P ₁ ', P ₂ ', P ₃ ' and P ₄ ' is greater than that of P ₁ ', P ₂ '', P 4 ' When the average value of the ordinates determined by the coordinates of ₃ ” and P ₄ ” is the upward translation deviation, that is, the camera is shifted downward relative to the target object; when the coordinates of P ₁ ', P ₂ ', P ₃ ' and P ₄ ' When the determined average value of the ordinate is smaller than the average value of the ordinate determined by the coordinates of P ₁ ”, P ₂ ”, P ₃ ” and P ₄ ”, it is the downward translation deviation, that is, the camera is shifted upward relative to the target object.

Referring to Fig. 4, the average value of the abscissa determined by the coordinates of P ₁ ', P ₂ ', P ₃ ' and P ₄ ' in the target image (b) is not equal to that of P ₁ ″, P ₂ in the standard image (o) When the average value of the abscissa determined by the coordinates of ”, P ₃ ” and P ₄ ” is determined, the identification deviation is determined as the horizontal deviation. Specifically, the horizontal deviation includes leftward translation deviation or rightward translation deviation. When the average value of the abscissa determined by the coordinates of P ₁ ', P ₂ ', P ₃ ' and P ₄ ' is greater than that of P ₁ ', P ₂ '', When the average value of the abscissa determined by the coordinates of P ₃ ” and P ₄ ” is the right translation deviation, that is, the camera is shifted to the left relative to the target object; when P ₁ ', P ₂ ', P ₃ ' and P ₄ ' When the average value of the abscissa determined by the coordinates of P ₁ ”, P ₂ ”, P ₃ ” and P ₄ ” is smaller than the average value of the abscissa determined by the coordinates of P 1 ”, P 2 ”, P 3 ” and P 4 ”, it is the translation deviation to the left, that is, the camera is offset to the right relative to the target object. shift.

Referring to FIG. 4 , in the target image (d), the side P ₁ 'P ₂ ' determined by the coordinates of P ₁ ' and P ₂ ' and the side P ₃ 'P ₄ determined by the coordinates of P ₃ ' and P ₄ '' is the first set of opposite sides, the side P ₂ 'P ₃ ' determined by the coordinates of P ₂ ' and P ₃ ' and the side P ₄ 'P ₁ ' determined by the coordinates of P ₄ ' and P ₁ ' are the second The line passing through the midpoint of P ₁ 'P ₂ ' and the mid point of P ₃ 'P ₄ ' is the line passing through the mid point of the first set of opposite sides, passing through the mid point of P ₂ 'P ₃ ' and The straight line at the midpoint of P ₄ 'P ₁ ' is the straight line passing through the midpoint of the second set of opposite sides; when the straight line passing through the midpoint of the first set of opposite sides intersects the y-axis, or the line passing through the midpoint of the second set of opposite sides When the line of the point intersects the x-axis, the identification deviation is determined as the rotation deviation. Specifically, the rotation deviation includes a counterclockwise rotation deviation or a clockwise rotation deviation. Exemplarily, the description will be given by taking the line passing through the midpoint of the first pair of opposite sides intersecting the y-axis as an example. Assuming that the counterclockwise direction is the positive direction, when the angle between the straight line passing through the midpoint of the first group of opposite sides and the y-axis is greater than 0, it is a counterclockwise rotation deviation, that is, the camera rotates clockwise relative to the target object; When the angle between the midpoint of the opposite side of the group and the y-axis is less than 0, it is a clockwise rotation deviation, that is, the camera rotates counterclockwise relative to the target object.

In addition, the rollover deviation includes a left-right rollover deviation and/or an up-down rollover deviation. Referring to FIG. 4 , in the target image (e), the side P ₂ 'P ₃ ' determined by the coordinates of P ₂ ' and P ₃ ' and the side P ₄ 'P ₁ determined by the coordinates of P ₄ ' and P ₁ '' is the second group of opposite sides, when P ₂ 'P ₃ ' and P ₄ 'P ₁ ' are not equal, it is the left-right flip deviation. Specifically, the left-right flip deviation includes the left flip deviation or the right flip deviation. When P ₂ 'P ₃ ' is greater than P ₄ 'P ₁ ', it is the left flip deviation, that is, the camera flips to the left relative to the target object; When P ₂ 'P ₃ ' is less than P ₄ 'P ₁ ', it is a right flip deviation, that is, the camera flips to the right relative to the target object. In the target image (f), the edge P ₁ 'P ₂ ' determined by the coordinates of P ₁ ' and P ₂ ' and the edge P ₃ 'P ₄ ' determined by the coordinates of P ₃ ' and P ₄ ' are the first On the opposite side of the group, when P ₁ 'P ₂ ' and P ₃ 'P ₄ ' are not equal, it is the upside-down deviation. Specifically, the up-down flip deviation includes flip-up deviation or flip-down deviation. When P ₁ 'P ₂ ' is greater than P ₃ 'P ₄ ', it is flip-down deviation, that is, the camera flips down relative to the target object; when P 1 'P 2 ' is greater than P 3 'P 4 ' When ₁ 'P ₂ ' is smaller than P ₃ 'P ₄ ', it is the upward flip deviation, that is, the camera flips upward relative to the target object.

S620: Correct the target image according to the mark deviation.

In the embodiment of the present disclosure, the correction of the target image is realized by adjusting the pose of the camera and/or the pose of the target object. That is, according to the mark deviation, the pose of the camera and/or the target object is adjusted until the mark deviation meets the preset deviation condition, wherein four marks are located on the target object, so that the target image can be corrected according to the mark deviation. The preset deviation condition is that the identification deviation meets the framing requirements, and the preset deviation condition can be adapted to be set according to different application scenarios. Preferably, the preset deviation condition is that the identification deviation does not exist.

In this embodiment, the target image can be corrected step by step, or the target image can be corrected at one time by calculating a specific deviation.

In an implementation of this embodiment, the pose of the camera and/or the pose of the target object is adjusted according to the identification deviation until the identification deviation satisfies the preset deviation condition, including S621 and S622:

S621: Determine the first compensation parameter of the camera and/or the target object according to the identification deviation.

The first compensation parameter includes a first compensation type and a first compensation direction, and the first compensation type includes an angle and/or a length. It is understandable that the present disclosure can adjust the pose of the camera or the target object independently to correct the target image, and can also adjust the pose of the camera and the target object simultaneously to correct the target image. Since the camera and the target image are set relative to each other, the first compensation directions of the camera and the target object are opposite. In addition, both the first compensation type and the first compensation direction can be determined according to the identification deviation. For example, take adjusting the pose of the camera as an example for description. When the identification deviation is forward translation deviation, the first compensation type is length, and the first compensation direction is backward translation; when the identification deviation is leftward translation deviation, the first compensation type is length, and the first compensation direction is leftward Translation; when the identification deviation is a counterclockwise rotation deviation, the first compensation type is angle, and the first compensation direction is counterclockwise rotation; when the identification deviation is an upward flip deviation, the first compensation type is angle, and the first compensation direction is direction. Flip down. For other cases in which the first compensation parameter is determined according to the identification deviation, reference may be made to the above determination method, which will not be repeated here.

S622: According to the first compensation parameter, stepwise adjust the pose of the camera and/or the pose of the target object until the identification deviation satisfies the preset deviation condition.

Specifically, including S6221 to S6226:

S6221: Along the first compensation direction, adjust the camera and/or the target object once according to the preset compensation amount corresponding to the first compensation type.

Illustratively, adjusting the pose of the camera is taken as an example for description. In this embodiment of the present disclosure, a stepper motor can be used to realize stepwise adjustment of the camera pose. The preset compensation amount is the amount of one step preset by the stepper motor, which can be determined as the step length or the step length according to the first compensation type. angle. For example, when the identification deviation is forward translation deviation, the stepper motor controls the camera to translate backward by a first preset length L1; when the identification deviation is leftward translation deviation, the stepper motor controls the camera to translate leftward by a second preset length L2; when the identification deviation is a counterclockwise rotation deviation, the stepping motor controls the camera to rotate the first preset angle A1 counterclockwise; when the identification deviation is an upward flip deviation, the stepping motor controls the camera to flip down a second preset angle A2 .

S6222: Collect a current image including four positioning marks through a camera, and use the current image as a target image.

S6223: Determine the marker positions of the four positioning markers in the target image.

S6224: Determine the mark deviation according to the mark position.

S6225: Determine the first compensation parameter of the camera and/or the target object according to the identification deviation.

S6226: Return to the direction of the first compensation, and adjust the camera and/or the target object again according to the preset compensation amount corresponding to the first compensation type, until the identification deviation satisfies the preset deviation condition.

In this embodiment, since it is not necessary to determine the precise deviation amount, it can be determined whether the identification deviation satisfies the preset deviation condition during the process of determining the identification deviation. Exemplarily, when the identification deviation is a forward translation deviation, it can be determined whether the difference between the distance between the two points determined by the identification coordinates and the distance between the corresponding two points determined by the standard coordinates is less than the preset distance difference, when the When the difference between the distance between the two points determined by the identification coordinates and the distance between the corresponding two points determined by the standard coordinates is less than the preset distance difference, the identification deviation satisfies the preset deviation condition.

In another implementation of this embodiment, the target image can be corrected at one time by calculating a specific deviation amount.

Specifically, the above method further includes: determining a deviation amount corresponding to the deviation of the identification according to the position of the identification. Correspondingly, according to the identification deviation, adjust the pose of the camera and/or the pose of the target object until the identification deviation satisfies the preset deviation conditions, including S623 and S624:

S623: Determine the second compensation parameter of the camera and/or the target object according to the identification deviation.

Wherein, the second compensation parameter includes a second compensation type and a second compensation direction, and the second compensation type includes an angle and/or a length. The second compensation parameter is similar to the above-mentioned first compensation parameter, and will not be repeated here.

S624: Adjust the pose of the camera and/or the pose of the target object according to the second compensation parameter and the deviation amount corresponding to the identification deviation.

In this embodiment, along the second compensation direction, the camera and/or the target object are adjusted according to the deviation amount corresponding to the second compensation type. Therefore, the camera and/or the target object can be adjusted to the standard pose at one time, and the target image can be corrected by one compensation, which further improves the efficiency of framing.

In the above solution, the deviation amount corresponding to the identification deviation is determined according to the identification position, including at least one of the following:

When the mark deviation is a flip deviation, the first projection angle and the second projection angle are determined according to the mark position, and the first projection angle and the second projection angle are used as the deviation amount corresponding to the mark deviation, wherein the mark plane surrounds the first predetermined angle. Suppose the line is rotated by the second projection angle, and after the first projection angle is rotated around the second preset line, it is parallel to the image plane. The first preset line passes through the first diagonal corner of the four positioning marks in the object space, and the second preset line is The straight line passes through the second diagonal corner of the four positioning marks in the object space;

When the marking deviation is the front and rear deviation, the current object distance is determined according to the marking position, and the difference between the current object distance and the preset standard object distance is used as the deviation corresponding to the marking deviation;

When the mark deviation is a vertical deviation, the preset distance from the center of the four positioning marks in the object space to the preset point is determined according to the mark position, and the product of the preset distance and the sine of the preset angle is used as the deviation corresponding to the mark deviation The preset point is the intersection of the main optical axis of the camera lens and the marking plane, and the preset angle is the angle between the horizontal line and the line passing through the center of the four positioning marks in the object space and the preset point;

When the marker deviation is a horizontal deviation, the preset distances from the centers of the four positioning markers in the object space to the preset point are determined according to the marker positions, and the product of the preset distance and the cosine value of the preset angle is used as the deviation corresponding to the marker deviation. quantity;

When the identification deviation is a rotation deviation, the rotation angle of the target image around the main optical axis of the camera lens is determined according to the identification position, and the rotation angle is used as the deviation amount corresponding to the identification deviation.

Optionally, determining the first projection angle and the second projection angle according to the identification position, including:

Use the following formula to determine the first projection angle:

Use the following formula to determine the second projection angle:

Among them, α represents the first projection angle, β represents the second projection angle, A' ₁ represents the distance from the first positioning mark to the mark imaging center in the target image, A' ₂ indicates the second positioning mark in the target image to the mark imaging The distance from the center, A' ₃ represents the distance from the third positioning mark to the marking imaging center in the target image, A' ₄ represents the distance from the fourth positioning mark to the marking imaging center in the target image, f represents the focal length of the camera, and the marking imaging The center is the intersection of the diagonal lines connecting the four positioning markers in the target image.

Specifically, the first projection angle and the second projection angle are calculated by the following formulas (1)-(12), which are described with the symbols marked in FIG. 8 .

Combining Figure 8 and the imaging formula, formula (1) and formula (2) can be obtained.

Wherein, point O is the intersection point of the straight line LP ₂ connecting the camera L and the second positioning mark P ₂ and the straight line passing through the center line point C and perpendicular to the straight line CL, and P is the extension line of the straight line connecting the camera head and the fourth positioning mark P ₄ The intersection point of LP ₄ and the straight line passing through the center line point C and perpendicular to the straight line CL, D is the distance between the center point C and the camera center L, and C' is the connection line between P ₁ ' and P ₃ ' in the target image and P ₂ ' and _The intersection of the lines of P4', A'2 is the distance between C' and P2', and _f is the focal length of the camera.

Among them, A' ₄ is the distance between C' and P ₄ '.

Formulas (3) to (8) can be obtained in combination with FIG. 8 and the triangular geometric relationship.

P ₂ C=A Formula (3)

Wherein, A is the distance between the _second positioning marker P2 and the center point C in the marker plane.

P ₄ C=A Formula (4)

Wherein, the distance from any positioning mark to the center point C in the mark plane is equal to A.

P ₂ M=A×cosα Formula (5)

Wherein, P ₂ M is perpendicular to MC, and the included angle between P ₂ M and P ₂ C is the first projection angle α.

P ₄ N=A×cosα Formula (6)

Wherein, P ₄ N is perpendicular to CL, and the included angle between P ₄ N and P ₄ C is the first projection angle α.

MC=A×sinα Formula (7)

NC=A×sinα Formula (8)

According to the similarity of the triangle composed of P ₂ ML to the triangle composed of OCL, formula (9) can be obtained.

Combining the above formula (1), formula (5), formula (7) and formula (9), the following formula (10) is obtained.

Equation (11) can be obtained from the similarity of the triangle formed by P ₄ NL to the triangle formed by PCL.

Combining the above formula (2), formula (6), formula (8) and formula (10), the following formula (12) is obtained.

According to formula (10) and formula (12), the first projection angle α can be obtained.

In addition, the calculation method of the second projection angle β is the same as the principle of the first projection angle α, which is not repeated here.

Optionally, determine the current object distance, including:

According to the position of the mark, the imaging distance between any two positioning marks in the target image is determined; according to the imaging distance and combined with the imaging principle, the current object distance is determined.

Optionally, according to the identification position, determine the rotation angle of the target image around the main optical axis of the lens of the camera, including:

Referring to the target image (d) in Figure 4, the rotation angle θ is determined by the following formula:

或者，

or,

Among them, the coordinates of P ₁ ' are (x ₁ ', y ₁ '), the coordinates of P ₂ ' are (x ₂ ', y ₂ '), and the coordinates of P ₃ ' are (x ₃ ', y ₃ '), The coordinates _{of P3} ' are ( _x3 ', y3').

In one embodiment, as shown in FIG. 9, an image correction device 900 is provided, and the image correction device 900 includes an image acquisition module 910, an identification position determination module 920 and an image correction module 930; wherein, the image acquisition module 910, It is configured to acquire a target image collected by the camera and contains four positioning marks, wherein the four positioning marks are located on the mark plane in the object space, and are arranged at equal intervals in turn and arranged in a circle; the mark position determination module 920 is configured to determine four positioning marks The mark position in the target image; the image correction module 930 is configured to correct the target image according to the mark position.

For specific limitations on the image correction device, reference may be made to the above limitations on the image correction method, which will not be repeated here. Each module in the above-mentioned image correction device may be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of one or more processors in the electronic device in the form of hardware, and can also be stored in the memory in the electronic device in the form of software, so that one or more processors can call and execute the above modules. The corresponding operation of the module.

Optionally, the image correction module 930 includes: a deviation determination unit, configured to determine the mark deviation according to the mark position; and an image correction unit, configured to correct the target image according to the mark deviation.

Optionally, the deviation determination unit includes: a positional relationship determination subunit configured to determine the positional relationship between the image plane of the camera and the identification plane according to the identification position, wherein the positional relationship includes the image plane and the identification plane being parallel or intersecting; the deviation determination subunit. The unit is configured to determine the marker deviation based on the positional relationship and the marker position.

Optionally, the positional relationship determination subunit is specifically configured to: when the lengths of the first group of opposite sides determined by the mark position are equal, and the length of the second group of opposite sides determined by the mark position are equal, the image plane is parallel to the mark plane; When any one of the lengths of the opposite sides of the first group of opposite sides determined by the mark position and the length of the second group of opposite sides are not equal, the image plane intersects the mark plane.

Optionally, the identification deviation includes at least one of a front-to-back deviation, a vertical deviation, a horizontal deviation, a rotation deviation, and a flip deviation.

Optionally, the image correction device further includes: a coordinate system establishment module, configured to take the target image point in the image plane as the origin, to establish a rectangular coordinate system, and the x-axis of the rectangular coordinate system is parallel to the first side determined by the preset standard position. , the y-axis of the rectangular coordinate system is parallel to the second side determined by the preset standard position, and the preset standard position is the position of the four positioning marks in the standard image; the identification coordinate determination module is configured to determine the four positioning marks in the rectangular coordinate system. The identification coordinates of each positioning mark in the target image and the standard coordinates in the standard image.

Optionally, the deviation determination subunit is specifically configured to: when the image plane is parallel to the marking plane, and the distance between the two points determined by the marking coordinates is not equal to the distance between the corresponding two points determined by the standard coordinates, determine the marking deviation. It is the deviation before and after; when the image plane is parallel to the marking plane, and the average value of the ordinate determined by the marking coordinates is not equal to the average value of the ordinate determined by the standard coordinates, the marking deviation is determined as the vertical deviation; when the image plane is parallel to the marking plane , and the average value of the abscissa determined by the identification coordinates is not equal to the average value of the abscissa determined by the standard coordinates, the identification deviation is determined as the horizontal deviation; when the image plane is parallel to the identification plane, and passes through the first group determined by the identification coordinates When the straight line at the midpoint of the opposite side intersects with the y-axis, or the straight line passing through the midpoint of the second group of opposite sides determined by the identification coordinates intersects with the x-axis, the identification deviation is determined as the rotation deviation; when the image plane and the identification When the planes intersect and the first group of opposite sides determined by the identification coordinates are not equal, or the second group of opposite sides determined by the identification coordinates are not equal, the identification deviation is determined as a flip deviation.

Optionally, the forward and backward deviations include forward translation deviation or backward translation deviation, the vertical deviation includes upward translation deviation or downward translation deviation, the horizontal deviation includes leftward translation deviation or right translation deviation, and the rotation deviation includes counterclockwise rotation deviation or Clockwise rotation bias, flip bias includes one or both of up flip bias, down flip bias, left flip bias, and right flip bias.

Optionally, the image correction unit includes: a pose adjustment subunit configured to adjust the pose of the camera and/or the pose of the target object according to the marker deviation, until the marker deviation satisfies a preset deviation condition, and the four markers are located on the target object. superior.

Optionally, the pose adjustment subunit is specifically configured to: determine the first compensation parameter of the camera and/or the target object according to the identification deviation, the first compensation parameter includes a first compensation type and a first compensation direction, and the first compensation type includes Angle and/or length; according to the first compensation parameter, stepwise adjust the pose of the camera and/or the pose of the target object until the marker deviation satisfies the preset deviation condition.

Optionally, the pose adjustment subunit is configured to stepwise adjust the pose of the camera and/or the pose of the target object according to the first compensation parameter until the marker deviation satisfies the preset deviation condition, and is specifically configured to: Compensation direction, adjust the camera and/or the target object once according to the preset compensation amount corresponding to the first compensation type; collect the current image containing four positioning marks through the camera, and use the current image as the target image; determine that the four positioning marks are on the target Mark position in the image; according to the mark position, determine the mark deviation; according to the mark deviation, determine the first compensation parameter of the camera and/or the target object; return to the preset compensation amount corresponding to the first compensation type along the first compensation direction Adjust the camera and/or the target object again until the marker deviation meets the preset deviation condition.

Optionally, the device further includes: a deviation amount determination module, configured to determine the deviation amount corresponding to the identification deviation according to the identification position. The pose adjustment subunit is specifically configured to: determine the second compensation parameter of the camera and/or the target object according to the identification deviation, the second compensation parameter includes a second compensation type and a second compensation direction, and the second compensation type includes an angle and/or length; adjust the pose of the camera and/or the pose of the target object according to the second compensation parameter and the deviation amount corresponding to the identification deviation.

Optionally, the deviation determination module is specifically configured to: when the identification deviation is a flip deviation, according to the identification position, determine the first projection angle and the second projection angle, and take the first projection angle and the second projection angle as the identification deviation corresponding. , where the marking plane rotates around the first preset line by the second projection angle, and after rotating the first projection angle around the second preset line, it is parallel to the image plane, and the first preset line passes through four The first diagonal corner of the positioning mark, and the second preset straight line passes through the second diagonal corner of the four positioning marks in the object space; when the mark deviation is the front and rear deviation, the current object distance is determined according to the mark position, and the current object distance and the preset distance are determined. Set the difference of the standard object distance as the deviation corresponding to the mark deviation; when the mark deviation is a vertical deviation, according to the mark position, determine the preset distance from the center of the four positioning marks in the object space to the preset point, and set the preset distance The product of the sine value of the preset angle is used as the deviation corresponding to the identification deviation, wherein the preset point is the intersection of the main optical axis of the camera lens and the identification plane, and the preset angle is the center and the center of the four positioning marks in the object space. The angle between the straight line of the preset point and the horizontal line; when the mark deviation is the horizontal deviation, according to the mark position, determine the preset distance from the center of the four positioning marks in the object space to the preset point, and compare the preset distance with the preset angle The product of the cosine values of , is used as the deviation corresponding to the logo deviation; when the logo deviation is a rotation deviation, the rotation angle of the target image around the main optical axis of the camera lens is determined according to the logo position, and the rotation angle is used as the deviation corresponding to the logo deviation. .

Optionally, when determining the first projection angle and the second projection angle according to the identification position, the deviation determination module is specifically configured to: determine the first projection angle by using the following formula:

Use the following formula to determine the second projection angle:

Among them, α represents the first projection angle, β represents the second projection angle, A' ₁ represents the distance from the first positioning mark to the mark imaging center in the target image, A' ₂ indicates the second positioning mark in the target image to the mark imaging The distance from the center, A' ₃ represents the distance from the third positioning mark to the marking imaging center in the target image, A' ₄ represents the distance from the fourth positioning mark to the marking imaging center in the target image, f represents the focal length of the camera, and the marking imaging The center is the intersection of the diagonal lines connecting the four positioning markers in the target image.

Optionally, when determining the current object distance according to the position of the mark, the deviation determination module is specifically configured to: according to the position of the mark, determine the imaging distance between any two positioning marks in the target image; according to the imaging distance and in combination with the imaging principle, Determines the current object distance.

In one embodiment, an electronic device is provided, the electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. 10 . The electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the execution of the operating system and computer-readable instructions in the non-volatile storage medium. The communication interface of the electronic device is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, near field communication (NFC) or other technologies. The computer readable instructions, when executed by one or more processors, implement a method. The display screen of the electronic device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the electronic device , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 10 is only a block diagram of a partial structure related to the solution of the present disclosure, and does not constitute a limitation on the electronic device to which the solution of the present disclosure is applied. The specific electronic device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, the image correction apparatus provided by the present disclosure may be implemented in the form of computer-readable instructions, and the computer-readable instructions may be executed on the electronic device as shown in FIG. 10 . Various program modules constituting the image correction apparatus may be stored in the memory of the electronic device, for example, the image acquisition module 910 , the identification position determination module 920 and the image correction module 930 shown in FIG. 9 . The computer-readable instructions constituted by each program module cause one or more processors to execute the steps in the image correction method of the various embodiments of the present disclosure described in this specification.

For example, the electronic device shown in FIG. 10 may perform step S510 through the image acquisition module 910 in the apparatus shown in FIG. 9 . The electronic device may perform step S520 by identifying the location determination module 920 . The electronic device may perform step S530 through the image correction module 930 .

In one embodiment, an electronic device is provided, which includes a memory and one or more processors, where the memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, implements the functions described in any of the foregoing embodiments. Provides the steps of the image rectification method. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile computer-readable In the storage medium, the computer-readable instructions, when executed, may include the processes of the foregoing method embodiments. Wherein, any reference to memory, database or other media used in the various embodiments provided by the present disclosure may include at least one of non-volatile and volatile memory. The non-volatile memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM).

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present disclosure, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be noted that, for those skilled in the art, without departing from the concept of the present disclosure, several modifications and improvements can be made, which all belong to the protection scope of the present disclosure. Accordingly, the scope of protection of the present disclosure should be determined by the appended claims.

Industrial Applicability

The image correction method provided by the present disclosure makes it possible to determine the photographed image by acquiring the target image corresponding to the target object pre-set with four positioning marks when taking a photo for framing, and according to the mark positions of the four positioning marks in the target image. The deviation of the target object can be quickly corrected according to the marked position, which improves the accuracy and efficiency of the framing, ensures the consistency of the framing results, and has strong industrial practicability.

Claims (20)

1. An image rectification method, comprising:

acquiring a target image which is acquired by a camera and contains four positioning marks, wherein the four positioning marks are positioned on a mark plane in an object space, are sequentially arranged at equal intervals and are arranged in a surrounding manner;

determining the identification positions of the four positioning identifications in the target image;

and correcting the target image according to the identification position.

2. The method of claim 1, wherein rectifying the target image based on the identified location comprises:

determining an identification deviation according to the identification position;

and correcting the target image according to the identification deviation.

3. The method of claim 2, wherein determining an identification bias from the identification location comprises:

determining the position relation between the image plane of the camera and the identification plane according to the identification position, wherein the position relation comprises that the image plane is parallel to or intersected with the identification plane;

and determining the identification deviation according to the position relation and the identification position.

4. The method of claim 3, wherein determining the position relationship between the image plane of the camera and the identification plane according to the identification position comprises:

when the lengths of a first group of opposite sides determined by the identification position are equal and the lengths of a second group of opposite sides determined by the identification position are equal, the image plane is parallel to the identification plane;

when any one pair of side lengths in the first group of opposite side lengths and the second group of opposite side lengths determined by the identification position is not equal to the side length, the image plane intersects with the identification plane.

5. The method of claim 3, wherein the identification bias comprises at least one of a front-to-back bias, a vertical bias, a horizontal bias, a rotational bias, and a roll-over bias.

6. The method of claim 5, further comprising:

establishing a rectangular coordinate system by taking a target image point in an image plane as an origin, wherein an x axis of the rectangular coordinate system is parallel to a first edge determined by a preset standard position, a y axis of the rectangular coordinate system is parallel to a second edge determined by the preset standard position, and the preset standard position is the position of the four positioning marks in a standard image;

and under the rectangular coordinate system, determining the identification coordinates of the four positioning identifications in the target image and the standard coordinates in the standard image.

7. The method of claim 6, wherein determining the tag bias based on the positional relationship and the tag location comprises at least one of:

when the image plane is parallel to the identification plane and the distance between two points determined by the identification coordinates is not equal to the distance between corresponding two points determined by the standard coordinates, determining the identification deviation as the front-back deviation;

when the image plane is parallel to the identification plane and the mean value of the ordinate determined by the identification coordinate is not equal to the mean value of the ordinate determined by the standard coordinate, determining the identification deviation as the vertical deviation;

when the image plane is parallel to the identification plane and the abscissa average value determined by the identification coordinates is not equal to the abscissa average value determined by the standard coordinates, determining the identification deviation as the horizontal deviation;

when the image plane is parallel to the identification plane and a straight line passing through the middle points of a first group of opposite sides determined by the identification coordinates intersects both the y-axis and the x-axis, or a straight line passing through the middle points of a second group of opposite sides determined by the identification coordinates intersects the x-axis, determining the identification deviation as the rotation deviation;

and when the image plane is intersected with the identification plane, and a first group of opposite sides determined by the identification coordinates are not equal, or a second group of opposite sides determined by the identification coordinates are not equal, determining the identification deviation as the overturning deviation.

8. The method of claim 7, wherein the front-to-back bias comprises a forward translation bias or a backward translation bias, the vertical bias comprises an upward translation bias or a downward translation bias, the horizontal bias comprises a leftward translation bias or a rightward translation bias, the rotational bias comprises a counterclockwise rotation bias or a clockwise rotation bias, and the flip bias comprises one or both of an upward flip bias, a downward flip bias, a leftward flip bias, and a rightward flip bias.

9. The method of claim 2, wherein rectifying the target image based on the identified deviation comprises:

and adjusting the pose of the camera and/or the pose of the target object according to the identification deviation until the identification deviation meets a preset deviation condition, wherein the four identifications are positioned on the target object.

10. The method of claim 9, wherein adjusting the pose of the camera and/or the pose of the target object according to the identification deviation until the identification deviation satisfies a preset deviation condition comprises:

determining a first compensation parameter of the camera and/or the target object according to the identification deviation, wherein the first compensation parameter comprises a first compensation type and a first compensation direction, and the first compensation type comprises an angle and/or a length;

and adjusting the pose of the camera and/or the pose of the target object step by step according to the first compensation parameter until the identification deviation meets a preset deviation condition.

11. The method of claim 10, wherein adjusting the pose of the camera and/or the pose of the target object in steps according to the first compensation parameter until the identification deviation satisfies a preset deviation condition comprises:

adjusting the camera and/or the target object once along the first compensation direction according to a preset compensation amount corresponding to the first compensation type;

acquiring a current image containing the four positioning identifications through the camera, and taking the current image as the target image;

determining the identification positions of the four positioning identifications in the target image;

determining an identification deviation according to the identification position;

determining a first compensation parameter of the camera and/or the target object according to the identification deviation;

and returning to the direction along the first compensation direction, and adjusting the camera and/or the target object again according to the preset compensation amount corresponding to the first compensation type until the identification deviation meets the preset deviation condition.

12. The method of claim 9, further comprising:

and determining a deviation amount corresponding to the identification deviation according to the identification position.

13. The method of claim 12, wherein adjusting the pose of the camera and/or the pose of the target object according to the identification deviation until the identification deviation satisfies a preset deviation condition comprises:

determining a second compensation parameter of the camera and/or the target object according to the identification deviation, wherein the second compensation parameter comprises a second compensation type and a second compensation direction, and the second compensation type comprises an angle and/or a length;

and adjusting the pose of the camera and/or the pose of the target object according to the second compensation parameter and the deviation amount corresponding to the identification deviation.

14. The method of claim 12, wherein determining the deviation amount corresponding to the identification deviation according to the identification position comprises at least one of:

when the identification deviation is a turning deviation, determining a first projection angle and a second projection angle according to the identification position, and taking the first projection angle and the second projection angle as deviation amounts corresponding to the identification deviation, wherein the identification plane rotates around a first preset straight line by the second projection angle, and after rotating around a second preset straight line by the first projection angle, the identification plane is parallel to an image plane, the first preset straight line passes through first diagonal angles of the four positioning identifications in the object space, and the second preset straight line passes through second diagonal angles of the four positioning identifications in the object space;

when the identification deviation is front and back deviation, determining the current object distance according to the identification position, and taking the difference value of the current object distance and a preset standard object distance as the deviation amount corresponding to the identification deviation;

when the identification deviation is vertical deviation, determining a preset distance from the center of the four positioning identifications to a preset point in an object space according to the identification position, and taking the product of the preset distance and the sine value of a preset angle as a deviation amount corresponding to the identification deviation, wherein the preset point is an intersection point of a main optical axis of a lens of the camera and the identification plane, and the preset angle is an included angle between a straight line passing through the centers of the four positioning identifications and the preset point in the object space and a horizontal line;

when the identification deviation is horizontal deviation, determining preset distances from the centers of the four positioning identifications to a preset point in an object space according to the identification positions, and taking the product of the preset distances and cosine values of preset angles as deviation amount corresponding to the identification deviation;

and when the identification deviation is rotation deviation, determining a rotation angle of the target image around a main optical axis of a lens of the camera according to the identification position, and taking the rotation angle as a deviation amount corresponding to the identification deviation.

15. The method of claim 14, wherein determining a first projection angle and a second projection angle from the identified location comprises:

determining the first projection angle using the following equation:

determining the second projection angle using the following equation:

wherein α represents the first projection angle, β represents the second projection angle, A'₁Representing a distance, A ', from a first location marker to a marker imaging center in the target image'₂Representing a distance, A ', of a second location marker to a marker imaging center in the target image'₃Representing a distance, A ', of a third location marker to a marker imaging center in the target image'₄And f represents the focal length of the camera, wherein the identification imaging center is the intersection point of the diagonal lines of the four positioning identifications in the target image.

16. The method of claim 14, wherein determining a current object distance from the identified location comprises:

determining the imaging distance between any two positioning marks in the target image according to the mark positions;

and determining the current object distance according to the imaging distance and combining the imaging principle.

17. An image rectification apparatus, characterized by comprising:

the image acquisition module is configured to acquire a target image which is acquired by a camera and contains four positioning marks, wherein the four positioning marks are positioned on a mark plane in an object space, are sequentially arranged at equal intervals and are arranged in a surrounding manner;

an identification position determination module configured to determine identification positions of the four positioning identifications in the target image;

and the image rectification module is configured to rectify the target image according to the identification position.

18. The apparatus of claim 17, wherein the image rectification module comprises:

a deviation determination unit configured to determine an identification deviation based on the identification position;

and the image correction unit is configured to correct the target image according to the identification deviation.

19. An electronic device comprising a memory and one or more processors, the memory storing computer-readable instructions, wherein the one or more processors, when executing the computer-readable instructions, perform the steps of the method of any one of claims 1 to 16.

20. One or more non-transitory computer-readable instructions having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by one or more processors, implement the steps of the method of any one of claims 1 to 16.

Images