Image distortion correction method and device and electronic equipment

Through the binocular camera's binocular camera's image fusion technology, the problem of distortion correction accuracy and efficiency caused by the out-of-synchronization of the conveyor belt speed and the camera line frequency is solved, and efficient image distortion correction and plate detection are achieved.

CN118941474APending Publication Date: 2024-11-12北京远舢智能科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410611440.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the distortion processing of the plate image is not synchronized with the camera line frequency due to the conveyor belt speed and the distortion correction accuracy and efficiency are not high. All real distortions cannot be eliminated by the camera distortion coefficient alone.

Method used

The binocular camera is used to obtain the circular images of the left and right calibration plates, and the target calibration plate images are determined through lateral distortion correction, and combined with the overlapping field of view areas to generate a complete circular image after distortion correction.

Benefits of technology

It greatly improves the accuracy and efficiency of image distortion correction, and improves the accuracy and efficiency of detecting plate indicators.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941474A_ABST
    Figure CN118941474A_ABST
Patent Text Reader

Abstract

The invention provides an image distortion correction method and device and electronic equipment, and relates to the technical field of image processing, and the method comprises the steps: carrying out the transverse distortion correction of a left calibration plate circular image and a right calibration plate circular image obtained by a left camera and a right camera of a binocular camera, determining a left side target calibration plate circular image and a right side target calibration plate circular image; under the condition that the preset circular calibration plate is located at the preset positions of the left camera and the right camera, based on the left semicircular image and the right semicircular image acquired by the left camera and the right camera and the circular image of the left calibration plate and the circular image of the right calibration plate, determining an overlapped view area of the left camera and the right camera; and performing fusion based on the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapped view area, and determining a complete circular image after distortion correction. According to the invention, the precision and efficiency of image distortion correction are greatly improved, and the accuracy and efficiency of plate index detection can also be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image distortion correction method, device and electronic equipment. Background Art

[0002] During the production process of the plate assembly line, the produced plates will be sent to the testing equipment through the conveyor belt for relevant index testing, such as testing whether the plates have defects and / or whether the size of the plates meets the standards, etc.; to determine whether each plate is qualified, and when plates of various sizes pass through the conveyor belt respectively, the camera first captures the complete plate image, and then identifies and analyzes the captured plate image. However, when the plate reaches the shooting range of the left and right cameras via the conveyor belt, the first plate image of a calibration plate captured by the left and right cameras is first obtained, and the second calibration plate image obtained by shooting another calibration plate from different angles using the left and right cameras is used to determine the camera distortion coefficient, and then the camera distortion coefficient is used to perform distortion correction on the first plate image, and then the image obtained after the distortion correction is tested for relevant indicators.

[0003] However, due to the fact that the existing plate image distortion processing is caused by the speed of the conveyor belt and the camera line frequency being out of sync, the captured image is compressed longitudinally, resulting in the inability to eliminate all the actual distortions using only the camera distortion coefficient, resulting in low accuracy and efficiency of distortion correction. Summary of the invention

[0004] The present invention provides an image distortion correction method, device and electronic equipment, which are used to solve the defects of low accuracy and efficiency of distortion correction caused by eliminating distortion only through the distortion coefficient of the camera, thereby greatly improving the accuracy and efficiency of image distortion correction, and also improving the accuracy and efficiency of detecting plate indicators.

[0005] The present invention provides an image distortion correction method, comprising:

[0006] Performing lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate;

[0007] When the preset circular calibration plate is located at the preset position of the left and right cameras, based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate, determining the overlapping field of view area of ​​the left and right cameras;

[0008] A complete circular image after distortion correction is determined based on the fusion of the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area.

[0009] According to an image distortion correction method provided by the present invention, the circular image of the left calibration plate and the circular image of the right calibration plate acquired by the left and right cameras of the binocular camera are respectively subjected to lateral distortion correction to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate, including:

[0010] In a case where the left camera photographs the preset circular calibration plate to obtain a plurality of circular images of the left calibration plate, and the right camera photographs the preset circular calibration plate to obtain a plurality of circular images of the right calibration plate, determining left distortion coefficients corresponding to the plurality of circular images of the left calibration plate and right distortion coefficients corresponding to the plurality of circular images of the right calibration plate;

[0011] Based on the left distortion coefficient, longitudinally stretch the plurality of circular images of the left calibration plate respectively to determine the circular images of the left target calibration plate;

[0012] Based on the right distortion coefficient, multiple right calibration plate circular images are respectively longitudinally stretched to determine each right target calibration plate circular image.

[0013] According to an image distortion correction method provided by the present invention, the determining of the left distortion coefficients corresponding to the plurality of circular images of the left calibration plate and the right distortion coefficients corresponding to the plurality of circular images of the right calibration plate comprises:

[0014] Respectively determining the left lateral diameter and the left longitudinal diameter of each circular image of the left calibration plate, and determining the right lateral diameter and the right longitudinal diameter of each circular image of the right calibration plate;

[0015] Respectively determine the left target transverse diameter corresponding to each of the left transverse diameters and the left target longitudinal diameter corresponding to each of the left longitudinal diameters, and determine the right target transverse diameter corresponding to each of the right transverse diameters and the right target transverse diameter corresponding to each of the right longitudinal diameters;

[0016] The ratio of the left target transverse diameter to the left target longitudinal diameter is determined as the left distortion coefficient, and the ratio of the right target transverse diameter to the right target transverse diameter is determined as the right distortion coefficient.

[0017] According to an image distortion correction method provided by the present invention, the determining of the left horizontal diameter and the left vertical diameter of each circular image of the left calibration plate includes:

[0018] For each circular image of the left calibration plate, perform the following steps respectively:

[0019] Determine the outer contour to be processed of the circular image of the left calibration plate, and sequentially perform grayscale processing, binarization processing and interference point removal processing on the initial inner contour circular image within the outer contour to be processed, and determine the target inner contour circular image based on the processing results;

[0020] Determine the target column pixel and the target row pixel whose accumulated pixel value in the circular image within the target contour is the smallest;

[0021] determining a target column boundary point based on the target column pixels, and determining a target row boundary point based on the target row pixels;

[0022] The left side transverse diameter is determined based on the transverse straight line corresponding to the target column boundary point, and the left side longitudinal diameter is determined based on the longitudinal straight line corresponding to the target row boundary point.

[0023] According to an image distortion correction method provided by the present invention, the step of determining the outer contour to be processed of the circular image of the left calibration plate includes:

[0024] In the case where the preset circular calibration plate is a calibration plate containing a plurality of concentric circles of different diameters, performing color inversion processing on the circular image of the left calibration plate;

[0025] A target circular ring region is determined from a plurality of circular ring regions contained in the calibration plate image obtained after the color inversion process, and an outer contour of the target circular ring region is determined as the outer contour to be processed.

[0026] According to an image distortion correction method provided by the present invention, the method comprises: fusing the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area to determine a complete circular image after distortion correction, including:

[0027] Determine a difference area between a preset pixel value sub-area of ​​the circular image of the left target calibration plate and the overlapping field of view area;

[0028] The difference area and the circular image of the right target calibration plate are spliced, and the complete circular image is determined based on the splicing result.

[0029] According to an image distortion correction method provided by the present invention, the method determines the overlapping field of view area of ​​the left and right cameras based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the left calibration plate circular image and the right calibration plate circular image, including:

[0030] When there are multiple left semicircular images, multiple right semicircular images, multiple circular images of the left calibration plate, and multiple circular images of the right calibration plate, determining first target axial distances corresponding to the multiple left semicircular images and second target axial distances corresponding to the multiple right semicircular images;

[0031] Determine a mean value of the target transverse diameter based on the left target transverse diameter corresponding to each of the circular images of the left target calibration plate and the left target transverse diameter corresponding to each of the circular images of the right target calibration plate;

[0032] The overlapping field of view area is determined based on the first target axial distance, the second target axial distance and the average of the target transverse diameter.

[0033] According to a method for image distortion correction provided by the present invention, the method further includes:

[0034] Based on the number of diameter pixels of the complete circular image and the diameter length of the preset circular calibration plate, a mapping coefficient characterizing the mapping relationship between the number of pixels and the diameter length in millimeters is determined.

[0035] The present invention also provides an image distortion correction device, comprising:

[0036] A lateral distortion correction unit is used to perform lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate;

[0037] an overlapping area determination unit, configured to determine the overlapping field of view area of ​​the left and right cameras based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate when the preset circular calibration plate is located at the preset position of the left and right cameras;

[0038] The image distortion correction unit is used to determine a complete circular image after distortion correction based on the fusion of the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area.

[0039] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the image distortion correction method described above is implemented.

[0040] The image distortion correction method, device and electronic device provided by the present invention, wherein the image distortion correction method firstly performs lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; and when the preset circular calibration plate is located at the preset position of the left and right cameras, based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate, determine the overlapping field of view of the left and right cameras; so that the complete circular image after distortion correction can be determined after fusion based on the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area. In this way, by shooting a customized circular calibration plate with a binocular camera and only adjusting the position of the customized circular calibration plate, and performing lateral distortion correction on both the left and right cameras, and then combining the image after lateral distortion correction and the overlapping field of view area of ​​the left and right cameras for splicing, the accuracy and efficiency of image distortion correction are greatly improved, and the accuracy and efficiency of plate index detection can also be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a flow chart of the image distortion correction method provided by the present invention;

[0043] Figure 2 is a schematic diagram of the concentric circle calibration plate provided by the present invention;

[0044] Figure 3 is a schematic diagram of a circular image of a left calibration plate provided by the present invention;

[0045] Figure 4 is a schematic diagram of a calibration plate image obtained after color inversion processing provided by the present invention;

[0046] Figure 5 It is a structural schematic diagram of the image distortion correction device provided by the present invention;

[0047] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the embodiments of the present invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In the textual description of the present invention, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship. In addition, it should be noted that the serial numbers themselves, such as "first", "second", etc., used to distinguish the objects described in the present invention are only used to distinguish the objects described, and do not have any order or technical meaning.

[0050] During the production process of the plate assembly line, the finished plates are sent to the inspection equipment through the conveyor belt for relevant index inspection, such as whether the plates have defects and / or whether the plate size meets the standard, etc., to determine whether each plate is qualified. In addition, when plates of various sizes pass through the conveyor belt, the camera first captures the complete plate image, and then identifies and analyzes the captured plate image. Therefore, it is particularly important to set up the camera and capture the complete plate image.

[0051] In the related art, in order to take into account plates of different sizes and considering the limited field of view of a camera, two cameras are usually set up at a limited height position in the plate production workshop where the conveyor belt is located. At this point, when the plate arrives within the shooting range of the left and right cameras via the conveyor belt, the left and right cameras first obtain a first plate image of a calibration plate, and use the left and right cameras to take another calibration plate from different angles to obtain a second calibration plate image to determine the camera distortion coefficient, and then use the camera distortion coefficient to perform distortion correction on the first plate image, and then perform relevant index detection on the image obtained after the distortion correction.

[0052] However, the existing plate image distortion processing not only requires two special calibration plates, but also the two cameras cannot be "coincidentally" connected and the fields of view overlap; in addition, the speed of the conveyor belt is not synchronized with the camera line frequency, which will cause the captured image to be compressed longitudinally. Therefore, the camera distortion coefficient alone cannot eliminate all the real distortions, resulting in low accuracy and efficiency of distortion correction.

[0053] In order to solve the above technical problems, the present invention provides an image distortion correction method, device and electronic equipment, which are used to solve the defects of low accuracy and efficiency of existing image distortion correction, and realize a method of shooting a customized circular calibration plate through a binocular camera and only adjusting the position of the customized circular calibration plate, as well as performing lateral distortion correction on both left and right cameras, and then combining the image after lateral distortion correction and the overlapping field of view area of ​​the left and right cameras for splicing, which can greatly improve the accuracy and efficiency of image distortion correction, and also can improve the accuracy and efficiency of detecting plate indicators.

[0054] Combine the following Figure 1-Figure 6 The image distortion correction method, device and electronic device of the present invention are described, wherein the execution subject of the image distortion correction method is an electronic device or a server, and the electronic device or the server can communicate with the binocular camera that takes the image of the plate in the assembly line production workshop of the plate, and the electronic device can be set inside the assembly line production workshop or outside the assembly line production workshop; the electronic device can be a personal computer (Personal Computer, PC), a portable device, a laptop computer, a smart phone, a tablet computer and other devices such as a portable wearable device; the server can refer to a server, or it can be a server cluster composed of multiple servers, a cloud computing center, etc. The present invention does not limit the specific form of the electronic device or server. Furthermore, the image distortion correction method can also be applied to an image distortion correction device set in an electronic device or a server, and the image distortion correction device can be implemented by software, hardware or a combination of the two. The following takes the execution subject of the image distortion correction method as an electronic device as an example to describe the image distortion correction method.

[0055] In order to facilitate understanding of the image distortion correction method provided by the embodiment of the present invention, the image distortion correction method provided by the present invention will be described in detail below through the following exemplary embodiments. It can be understood that the following exemplary embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0056] Reference Figure 1 , is a flow chart of the image distortion correction method provided by the present invention, such as Figure 1 As shown, the image distortion correction method includes the following steps 110 to 130.

[0057] Step 110 , perform lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate acquired by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate.

[0058] Among them, the number of circular images of the left calibration plate and the number of circular images of the right calibration plate can be at least 2, each circular image of the left calibration plate is a circular image obtained by the left camera in the binocular camera after shooting the preset circular calibration plate, and each circular image of the right calibration plate is a circular image obtained by the right camera in the binocular camera after shooting the preset circular calibration plate.

[0059] The number of circular images on the left target calibration plate is the same as the number of circular images on the left calibration plate and corresponds one to one, and the number of circular images on the right target calibration plate is the same as the number of circular images on the right calibration plate and corresponds one to one.

[0060] The number of preset circular calibration plates may be one or more. When the number of preset circular calibration plates is more than one, the diameters of each adjacent two preset circular calibration plates are different. When the number of preset circular calibration plates is one, the specific diameter of the preset circular calibration plate is Figure 2 The concentric circular calibration plate shown in FIG. 1 contains multiple concentric circles of different diameters, such as Figure 2 There are 4 concentric circles with different diameters, namely 200mm, 300mm, 350mm and 400mm.

[0061] Specifically, when the preset circular calibration plate arrives within the shooting range of the binocular camera via the conveyor belt, the left camera will shoot the preset circular calibration plate and obtain a set of circular images of the left calibration plate, and then further send the captured set of circular images of the left calibration plate to the electronic device; at the same time, the right camera will also shoot the preset circular calibration plate and obtain a set of circular images of the right calibration plate, and then further send the captured set of circular images of the right calibration plate to the electronic device; at this point, the electronic device can obtain the circular images of the left calibration plate and the circular images of the right calibration plate obtained by the left and right cameras.

[0062] Considering that even if the preset circular calibration plate is rotated through the conveyor belt and enters the camera range of the left and right cameras, the left and right cameras have no longitudinal distortion and both have lateral distortion, so only the lateral distortion of the left and right cameras needs to be corrected. Based on this, the electronic device uses a preset lateral distortion correction algorithm to determine the left correction coefficient and the right correction coefficient corresponding to the left and right cameras, and performs lateral distortion correction on the circular image of the left calibration plate by the left correction coefficient, and performs lateral distortion correction on the circular image of the right calibration plate by the right correction coefficient, so as to obtain the circular image of the left target calibration plate and the circular image of the right target calibration plate after lateral distortion correction.

[0063] Step 120: When the preset circular calibration plate is located at the preset position of the left and right cameras, the overlapping field of view area of ​​the left and right cameras is determined based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate.

[0064] The number of the left semicircular images and the number of the right semicircular images may be at least 2.

[0065] Exemplarily, the preset position may be specifically the middle position between the left and right cameras.

[0066] Specifically, when the preset circular calibration plate is placed in the middle position of the left and right cameras, incomplete semicircular calibration plates will appear in the respective camera ranges of the left camera and the right camera. At this time, the left camera will shoot the corresponding semicircular calibration plate and obtain a set of left semicircular images, and then further send the captured set of left semicircular images to the electronic device; at the same time, the right camera will also shoot the corresponding semicircular calibration plate and obtain a set of right semicircular images, and then further send the captured set of right semicircular images to the electronic device; at this point, the electronic device can obtain the left semicircular images and right semicircular images taken by the left and right cameras.

[0067] It can be understood that when the preset circular calibration plate is placed in the middle position of the left and right cameras for shooting, the shooting fields of the left and right cameras will inevitably overlap and respectively shoot the corresponding semicircular calibration plates. Therefore, the electronic device can combine the left semicircular image and the right semicircular image taken when there is overlap between the left and right cameras, and the left calibration plate circular image and the right calibration plate circular image taken when there is no overlap to calibrate the overlapping area, thereby obtaining the overlapping field of view area of ​​the left and right cameras.

[0068] Exemplarily, the electronic device can first determine the mean lateral diameters corresponding to multiple left semicircular images and multiple right semicircular images, then calculate the average of each lateral diameter average, and then calibrate the overlapping area based on the average calculation result, the incomplete lateral diameter averages corresponding to multiple left semicircular images, and the incomplete lateral diameter averages corresponding to multiple right semicircular images, to obtain the overlapping field of view area of ​​the left and right cameras.

[0069] Step 130 : Fusing the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area to determine a complete circular image after distortion correction.

[0070] Specifically, the electronic device can first select a pure color sub-region that does not contain a preset circular calibration plate from the circular image of the target calibration plate on the left, and subtract the pure color sub-region of the circular image of the target calibration plate on the left from the overlapping field of view area, and then splice the subtracted regional image with the circular image of the target calibration plate on the right to obtain a complete circular image after distortion correction.

[0071] The image distortion correction method provided by the present invention is that the electronic device first performs lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; and when the preset circular calibration plate is located at the preset position of the left and right cameras, based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate, the overlapping field of view area of ​​the left and right cameras is determined; so that the complete circular image after distortion correction can be determined after fusion based on the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area. In this way, by shooting a customized circular calibration plate with a binocular camera and only adjusting the position of the customized circular calibration plate, and performing lateral distortion correction on both the left and right cameras, and then combining the image after lateral distortion correction and the overlapping field of view area of ​​the left and right cameras for splicing, the accuracy and efficiency of image distortion correction are greatly improved, and the accuracy and efficiency of plate index detection can also be improved.

[0072] Based on the above Figure 1 In the image distortion correction method shown in FIG. 1 , in an exemplary embodiment, the specific implementation process of step 110 may include:

[0073] First, when the left camera shoots a preset circular calibration plate to obtain multiple circular images of the left calibration plate and the right camera shoots a preset circular calibration plate to obtain multiple circular images of the right calibration plate, the left distortion coefficients corresponding to the multiple circular images of the left calibration plate and the right distortion coefficients corresponding to the multiple circular images of the right calibration plate are determined; then, based on the left distortion coefficient, the multiple circular images of the left calibration plate are longitudinally stretched respectively to determine each circular image of the left target calibration plate; at the same time, based on the right distortion coefficient, the multiple circular images of the right calibration plate are longitudinally stretched respectively to determine each circular image of the right target calibration plate.

[0074] It should be noted that since both the left and right cameras have only lateral distortion, when the left camera shoots the preset circular calibration plate to obtain a set of circular images of the left calibration plate, and the right camera shoots the preset circular calibration plate to obtain a set of circular images of the right calibration plate, the electronic device can calculate the left lateral parameter value of each circular image of the left calibration plate, and then average the left lateral parameter values ​​to obtain the left lateral parameter average value, and calculate the left longitudinal parameter value of each circular image of the left calibration plate, and then average the left longitudinal parameter values ​​to obtain the left longitudinal parameter average value, and determine the ratio of the left lateral parameter average value to the left longitudinal parameter average value as the left distortion coefficient, for example, the left distortion coefficient is denoted as a1.

[0075] Similarly, the electronic device can also calculate the right side horizontal parameter value of each circular image of the right side calibration plate, and then take the average of each right side horizontal parameter value to obtain the right side horizontal parameter average value, and calculate the right side longitudinal parameter value of each circular image of the right side calibration plate, and then take the average of each right side longitudinal parameter value to obtain the right side longitudinal parameter average value, and determine the ratio of the right side horizontal parameter average value to the right side longitudinal parameter average value as the right side distortion coefficient, for example, the right side distortion coefficient is recorded as a2.

[0076] At this time, the electronic device can determine the left target calibration plate circular image corresponding to each left calibration plate circular image by longitudinally stretching each left calibration plate circular image by a1 times; similarly, it can also determine the right target calibration plate circular image corresponding to each right calibration plate circular image by longitudinally stretching each right calibration plate circular image by a2 times. In this way, the purpose of performing lateral distortion correction on the left calibration plate circular image and the right calibration plate circular image can be achieved, providing reliable guarantee for the subsequent image fusion effect.

[0077] Based on the above Figure 1 In the image distortion correction method shown in the figure, in an exemplary embodiment, the electronic device determines the left distortion coefficients corresponding to multiple circular images of the left calibration plate and the right distortion coefficients corresponding to multiple circular images of the right calibration plate, and the specific implementation process includes:

[0078] Determine the left lateral diameter and the left longitudinal diameter of each circular image of the left calibration plate, and determine the right lateral diameter and the right longitudinal diameter of each circular image of the right calibration plate; determine the left target lateral diameter corresponding to each left lateral diameter and the left target longitudinal diameter corresponding to each left longitudinal diameter, and determine the right target lateral diameter corresponding to each right lateral diameter and the right target lateral diameter corresponding to each right longitudinal diameter; determine the ratio of the left target lateral diameter to the left target longitudinal diameter as the left distortion coefficient, and determine the ratio of the right target lateral diameter to the right target lateral diameter as the right distortion coefficient.

[0079] Among them, the left target transverse diameter can specifically be the average value of the left transverse diameters, the left target longitudinal diameter can specifically be the average value of the left longitudinal diameters, the right target transverse diameter can specifically be the average value of the right transverse diameters, and the right target transverse diameter can specifically be the average value of the right transverse diameters.

[0080] Exemplarily, when the left camera shoots a preset circular calibration plate to obtain at least two circular images of the left calibration plate, and the right camera shoots a preset circular calibration plate to obtain at least two circular images of the right calibration plate, the electronic device can calculate the left lateral diameter of each circular image of the left calibration plate, and then take the average of the left lateral diameters to obtain the left lateral diameter average value (D_H1), and calculate the left longitudinal diameter of each circular image of the left calibration plate, and then take the average of the left longitudinal diameters to obtain the left longitudinal diameter average value (D_Z1), and determine the ratio of the left lateral diameter average value to the left longitudinal diameter average value as the left distortion coefficient a1, a1=D_H1 / D_Z1.

[0081] Similarly, the electronic device can also calculate the right side lateral diameter of each circular image of the right side calibration plate, and then take the average of the right side lateral diameters to obtain the right side lateral diameter average value (D_H2), and calculate the right side longitudinal diameter of each circular image of the right side calibration plate, and then take the average of the right side longitudinal diameters to obtain the right side longitudinal diameter average value (D_Z2), and determine the ratio of the right side lateral diameter average value to the right side longitudinal diameter average value as the right side distortion coefficient a2, a2=D_H2 / D_Z2.

[0082] Based on the above Figure 1 In the image distortion correction method shown in the figure, in an exemplary embodiment, the electronic device determines the left lateral diameter and the left longitudinal diameter of each circular image of the left calibration plate, including:

[0083] For each circular image of the left calibration plate, perform the following steps respectively:

[0084] Determine the outer contour to be processed of the circular image of the calibration plate on the left, and perform grayscale processing, binarization processing and interference point removal processing on the initial inner contour circular image within the outer contour to be processed in turn, and determine the target inner contour circular image based on the processing results; determine the target column pixels and target row pixels with the smallest cumulative result of pixel values ​​in the target inner contour circular image; determine the target column boundary points based on the target column pixels, and determine the target row boundary points based on the target row pixels; determine the left side horizontal diameter based on the horizontal straight line corresponding to the target column boundary points, and determine the left side longitudinal diameter based on the longitudinal straight line corresponding to the target row boundary points.

[0085] Specifically, for any one of the circular images of the left calibration plate, firstly, a circular contour is selected from at least one circular contour contained in the circular image of the left calibration plate as the outer contour to be processed. For example, when there are three concentric circular contours, the largest circular contour can be used as the outer contour to be processed, or the smallest circular contour can be used as the outer contour to be processed, or the middle circular contour can be used as the outer contour to be processed; then, the initial inner contour circular image within the outer contour to be processed is first grayscaled and then binarized. At this time, the white pixel value in the binarized circular image is 1 and the black pixel value is 0. The purpose of this operation is to accurately extract the white area; then, the binary image is subjected to interference point removal processing through image processing methods such as morphology, such as removing black points in the white area and white points in the black area, so as to obtain the circular image within the target contour.

[0086] Furthermore, the pixel values ​​of the circular image within the target outline are added column by column and row by row, and the target column pixel and target row pixel with the smallest pixel value accumulation result are determined according to the accumulation results of the pixel values ​​of each row and each column.

[0087] At this time, the column boundary points in the target column pixels are determined according to the number of white pixels contained in the target column pixels, and the target row boundary points are determined according to the number of white pixels contained in the target row pixels. For example, if the target column pixels contain one white pixel, the white pixel can be used as the target column boundary point; if the target column pixels contain at least two white pixels, the white pixel in the middle position can be used as the target column boundary point. In this way, the left horizontal diameter of the circular image of the left calibration plate is determined by drawing a horizontal straight line along the target column boundary points, and the left vertical diameter of the circular image of the left calibration plate is determined by drawing a vertical straight line along the target row boundary points.

[0088] It should be noted that the determination process of the right lateral diameter and the right longitudinal diameter of each right calibration plate circular image can refer to the specific determination process of the left lateral diameter and the left longitudinal diameter of each left calibration plate circular image, which will not be described in detail here.

[0089] Based on the above Figure 1 In the image distortion correction method shown in the figure, in an exemplary embodiment, in order to ensure that the selection of the outer contour to be processed is more accurate, the circular image of the left calibration plate containing multiple concentric circular contours can be first inverted and then the outer contour to be processed can be selected. Based on this, the electronic device determines the outer contour to be processed of the circular image of the left calibration plate, and the specific implementation process thereof may include:

[0090] Firstly, when the preset circular calibration plate is a calibration plate containing multiple concentric circles of different diameters, the circular image of the calibration plate on the left is inverted; further, the target circular area is determined from the multiple circular areas contained in the calibration plate image obtained after the inversion processing, and the outer contour of the target circular area is determined as the outer contour to be processed.

[0091] For example, when the preset circular calibration plate is as follows Figure 2 When the concentric circle calibration plate shown in FIG. 3 is used, the circular image of the left calibration plate can be obtained by shooting the preset circular calibration plate with the left camera. Figure 3 The circular image of the calibration plate on the left is inverted, that is, the pixel value of each pixel on the circular image of the calibration plate on the left is subtracted from 255, such as 255-the pixel value of each pixel, and the following can be obtained: Figure 4 The calibration plate image obtained after the inversion processing is shown; further, the smallest circular ring area, the largest circular ring area, or any circular ring area between the smallest circular ring area and the largest circular ring area are selected from the multiple circular ring areas contained in the calibration plate image obtained after the inversion processing as the target circular ring area, so as to determine the outer contour of the target circular ring area as the outer contour to be processed. In this way, the subsequent binarization effect can be better and the effect of preventing interference can be better.

[0092] It should be noted that the reason why the preset circular calibration plate is set to contain multiple concentric circles of different diameters is to obtain multiple circular images of the calibration plate of different sizes at the same time when one shooting is completed. In this way, the accuracy of image distortion correction is ensured by calculating the horizontal diameter and vertical diameter of each circular image of the calibration plate and taking the average value.

[0093] Based on the above Figure 1 In the image distortion correction method shown in FIG. 1 , in an exemplary embodiment, the specific implementation process of step 130 may include:

[0094] First, the difference area between the preset pixel value sub-area of ​​the circular image of the target calibration plate on the left and the overlapping field of view area is determined; then, the difference area and the circular image of the target calibration plate on the right are spliced, and the complete circular image is determined based on the splicing result.

[0095] Exemplarily, the preset pixel value sub-region may be a partial region in which the pixel values ​​of the circular image of the left target calibration plate are all 0.

[0096] Specifically, the electronic device can obtain a left target calibration plate circular image after lateral distortion correction for the left calibration plate circular image taken by the left camera, and obtain a right target calibration plate circular image after lateral distortion correction for the right calibration plate circular image taken by the right camera, by subtracting the right half of the pure black area of ​​the left target calibration plate circular image from the overlapping field of view area, so as to remove the overlapping field of view area; and then splicing the subtraction result image with the right target calibration plate circular image to obtain a complete circular image.

[0097] Based on the above Figure 1 In the image distortion correction method shown in FIG. 1 , in an exemplary embodiment, in step 120, based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the left calibration plate circular image and the right calibration plate circular image, the overlapping field of view area of ​​the left and right cameras is determined, and the specific implementation process may include:

[0098] Firstly, when there are multiple left-side semicircular images, multiple right-side semicircular images, multiple left-side calibration plate circular images and multiple right-side calibration plate circular images respectively, determine the first target axial distances corresponding to the multiple left-side semicircular images and the second target axial distances corresponding to the multiple right-side semicircular images; further, based on the left-side target lateral diameters corresponding to each left-side target calibration plate circular image and the left-side target lateral diameters corresponding to each right-side target calibration plate circular image, determine the average of the target lateral diameters; based on the first target axial distance, the second target axial distance and the average of the target lateral diameters, determine the overlapping field of view area.

[0099] Specifically, a preset circular calibration plate is placed in the middle position of the left and right cameras for shooting. An incomplete semicircle will appear under the lens of the left camera and the right camera, and a group of left semicircle images and a group of right semicircle images are obtained. At this time, the left incomplete lateral diameter of each left semicircle image and the right incomplete lateral diameter of each right semicircle image are calculated, and the left incomplete lateral diameters are averaged and the obtained average is used as the first target axial distance (D_B1) corresponding to the multiple left semicircle images; similarly, the right incomplete lateral diameters are averaged and the obtained average is used as the second target axial distance (D_B2) corresponding to the multiple right semicircle images.

[0100] At this time, the left side transverse diameter average value (D_H1) and the right side transverse diameter average value (D_H2) calculated above are called, and the left side transverse diameter average value (D_H1) and the right side transverse diameter average value (D_H2) are averaged and the obtained average value is determined as the target transverse diameter average value (D); so as to prevent errors. In this way, the overlapping field of view area (Gap_D) can be obtained, Gap_D = D_B1 + D_B2 - D.

[0101] Based on the above Figure 1In the image distortion correction method shown, in an exemplary embodiment, considering that the purpose of the actual project is measurement, it is necessary to know the relationship between the pixel world and the physical world, that is, how many pixels correspond to a shooting distance of 1 mm, so that an image with a required number of pixels can be captured according to the error requirement. Based on this, after step 130, the image distortion correction method provided by the present invention may also include:

[0102] Based on the number of diameter pixels of the complete circular image and the diameter length of the preset circular calibration plate, a mapping coefficient characterizing the mapping relationship between the number of pixels and the diameter length in millimeters is determined.

[0103] Specifically, the electronic device determines the mapping coefficient b by calculating the ratio between the number of diameter pixels (P) of the complete circular image and the diameter length (L) of the preset circular calibration plate, where b=P / L.

[0104] It should be noted that when the preset circular calibration plate is a calibration plate containing multiple concentric circles with different diameters, for example Figure 2 The four concentric circles of different diameters shown in the figure can be selected based on the outer contour to be processed selected when calculating the left horizontal diameter and the left longitudinal diameter of each circular image of the left calibration plate as mentioned above, and the diameter length (L) used to calculate the mapping coefficient can be selected from multiple different diameters; for example, the diameter of the outer contour to be processed corresponding to the preset circular calibration plate is taken as L.

[0105] For example, when the diameter of a complete circular image contains 200 pixels and the diameter of the preset circular calibration plate is 200 mm, the mapping coefficient can be 0.1, that is, 1 mm corresponds to 10 pixels. In this way, the number of pixels required to be accurate during shooting can be known according to the actual error requirements.

[0106] The image distortion correction device provided by the present invention is described below. The image distortion correction device described below and the image distortion correction method described above can be referred to each other.

[0107] Reference Figure 5 , is a schematic diagram of the structure of the image distortion correction device provided by the present invention, such as Figure 5 As shown, the image distortion correction device 500 includes: a lateral distortion correction unit 510, an overlapping area determination unit 520 and an image distortion correction unit 530.

[0108] The lateral distortion correction unit 510 is used to perform lateral distortion correction on the left calibration plate circular image and the right calibration plate circular image obtained by the left and right cameras of the binocular camera, respectively, to determine the left target calibration plate circular image and the right target calibration plate circular image.

[0109] The overlapping area determination unit 520 is used to determine the overlapping field of view area of ​​the left and right cameras based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the left calibration plate circular image and the right calibration plate circular image when the preset circular calibration plate is located at the preset position of the left and right cameras.

[0110] The image distortion correction unit 530 is used to fuse the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area to determine a complete circular image after distortion correction.

[0111] Optionally, the lateral distortion correction unit 510 is specifically used to determine the left-side distortion coefficients corresponding to the multiple left-side calibration plate circular images and the right-side distortion coefficients corresponding to the multiple right-side calibration plate circular images when the left-side camera shoots a preset circular calibration plate to obtain multiple left-side calibration plate circular images and the right-side camera shoots a preset circular calibration plate to obtain multiple right-side calibration plate circular images; longitudinally stretch the multiple left-side calibration plate circular images based on the left-side distortion coefficients to determine each left-side target calibration plate circular image; and longitudinally stretch the multiple right-side calibration plate circular images based on the right-side distortion coefficients to determine each right-side target calibration plate circular image.

[0112] Optionally, the lateral distortion correction unit 510 is specifically used to respectively determine the left lateral diameter and the left longitudinal diameter of each left calibration plate circular image, and determine the right lateral diameter and the right longitudinal diameter of each right calibration plate circular image; respectively determine the left target lateral diameter corresponding to each left lateral diameter and the left target longitudinal diameter corresponding to each left longitudinal diameter, and determine the right target lateral diameter corresponding to each right lateral diameter and the right target lateral diameter corresponding to each right longitudinal diameter; determine the ratio of the left target lateral diameter to the left target longitudinal diameter as the left distortion coefficient, and determine the ratio of the right target lateral diameter to the right target lateral diameter as the right distortion coefficient.

[0113] Optionally, the lateral distortion correction unit 510 is specifically used to execute the following steps for each circular image of the left calibration plate: determine the outer contour to be processed of the circular image of the left calibration plate, and perform grayscale processing, binarization processing and interference point removal processing on the initial inner contour circular image within the outer contour to be processed in sequence, and determine the target inner contour circular image based on the processing results; determine the target column pixels and target row pixels with the smallest cumulative result of pixel values ​​in the target inner contour circular image; determine the target column boundary points based on the target column pixels, and determine the target row boundary points based on the target row pixels; determine the left lateral diameter based on the horizontal straight line corresponding to the target column boundary points, and determine the left longitudinal diameter based on the vertical straight line corresponding to the target row boundary points.

[0114] Optionally, the lateral distortion correction unit 510 is specifically used to perform color inversion processing on the circular image of the left calibration plate when the preset circular calibration plate is a calibration plate containing multiple concentric circles of different diameters; determine the target circular ring area from the multiple circular ring areas contained in the calibration plate image obtained after the inversion processing, and determine the outer contour of the target circular ring area as the outer contour to be processed.

[0115] Optionally, the overlapping area determination unit 520 is specifically used to determine the difference area between the preset pixel value sub-area of ​​the circular image of the left target calibration plate and the overlapping field of view area; splice the difference area and the circular image of the right target calibration plate, and determine the complete circular image based on the splicing result.

[0116] Optionally, the image distortion correction unit 530 is specifically used to determine the first target axial distance corresponding to the multiple left semicircular images and the second target axial distance corresponding to the multiple right semicircular images when there are multiple left semicircular images, multiple right semicircular images, multiple left calibration plate circular images and multiple right calibration plate circular images; determine the average target lateral diameter based on the left target lateral diameter corresponding to each left target calibration plate circular image and the left target lateral diameter corresponding to each right target calibration plate circular image; determine the overlapping field of view area based on the first target axial distance, the second target axial distance and the average target lateral diameter.

[0117] Optionally, the image distortion correction device provided by the present invention may also include a mapping coefficient determination unit, which is used to determine a mapping coefficient characterizing the mapping relationship between the number of pixels and the diameter length in millimeters based on the number of diameter pixels of the complete circular image and the diameter length of a preset circular calibration plate.

[0118] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the image distortion correction method, which includes:

[0119] The circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera are respectively corrected for lateral distortion to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; when the preset circular calibration plate is located at the preset position of the left and right cameras, the overlapping field of view area of ​​the left and right cameras is determined based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate; the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view are fused to determine the complete circular image after distortion correction.

[0120] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0121] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the image distortion correction method provided by the above methods, the method comprising:

[0122] The circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera are respectively corrected for lateral distortion to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; when the preset circular calibration plate is located at the preset position of the left and right cameras, the overlapping field of view area of ​​the left and right cameras is determined based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate; the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view are fused to determine the complete circular image after distortion correction.

[0123] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the image distortion correction method provided by the above methods is implemented, and the method includes:

[0124] The circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera are respectively corrected for lateral distortion to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; when the preset circular calibration plate is located at the preset position of the left and right cameras, the overlapping field of view area of ​​the left and right cameras is determined based on the left semicircular image and the right semicircular image obtained by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate; the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view are fused to determine the complete circular image after distortion correction.

[0125] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0126] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for correcting image distortion, characterized in that: include: Performing lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; When the preset circular calibration plate is located at the preset position of the left and right cameras, based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate, determining the overlapping field of view area of ​​the left and right cameras; A complete circular image after distortion correction is determined based on the fusion of the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area.

2. The image distortion correction method according to claim 1, characterized in that: The method of performing lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate includes: In a case where the left camera photographs the preset circular calibration plate to obtain a plurality of circular images of the left calibration plate, and the right camera photographs the preset circular calibration plate to obtain a plurality of circular images of the right calibration plate, determining left distortion coefficients corresponding to the plurality of circular images of the left calibration plate and right distortion coefficients corresponding to the plurality of circular images of the right calibration plate; Based on the left distortion coefficient, longitudinally stretch the plurality of circular images of the left calibration plate respectively to determine the circular images of the left target calibration plate; Based on the right distortion coefficient, multiple right calibration plate circular images are respectively longitudinally stretched to determine each right target calibration plate circular image.

3. The image distortion correction method according to claim 2, characterized in that: The determining of the left distortion coefficients corresponding to the plurality of circular images of the left calibration plate and the right distortion coefficients corresponding to the plurality of circular images of the right calibration plate includes: Respectively determining the left lateral diameter and the left longitudinal diameter of each circular image of the left calibration plate, and determining the right lateral diameter and the right longitudinal diameter of each circular image of the right calibration plate; Respectively determine the left target transverse diameter corresponding to each of the left transverse diameters and the left target longitudinal diameter corresponding to each of the left longitudinal diameters, and determine the right target transverse diameter corresponding to each of the right transverse diameters and the right target transverse diameter corresponding to each of the right longitudinal diameters; The ratio of the left target transverse diameter to the left target longitudinal diameter is determined as the left distortion coefficient, and the ratio of the right target transverse diameter to the right target transverse diameter is determined as the right distortion coefficient.

4. The image distortion correction method according to claim 3, characterized in that: The determining of the left side transverse diameter and the left side longitudinal diameter of each circular image of the left calibration plate comprises: For each circular image of the left calibration plate, perform the following steps respectively: Determine the outer contour to be processed of the circular image of the left calibration plate, and sequentially perform grayscale processing, binarization processing and interference point removal processing on the initial inner contour circular image within the outer contour to be processed, and determine the target inner contour circular image based on the processing results; Determine the target column pixel and the target row pixel whose accumulated pixel value in the circular image within the target contour is the smallest; determining a target column boundary point based on the target column pixels, and determining a target row boundary point based on the target row pixels; The left side transverse diameter is determined based on the transverse straight line corresponding to the target column boundary point, and the left side longitudinal diameter is determined based on the longitudinal straight line corresponding to the target row boundary point.

5. The image distortion correction method according to claim 4, characterized in that: The step of determining the outer contour to be processed of the circular image of the left calibration plate includes: In the case where the preset circular calibration plate is a calibration plate containing a plurality of concentric circles of different diameters, performing color inversion processing on the circular image of the left calibration plate; A target circular ring region is determined from a plurality of circular ring regions contained in the calibration plate image obtained after the color inversion process, and an outer contour of the target circular ring region is determined as the outer contour to be processed.

6. The image distortion correction method according to any one of claims 1 to 5, characterized in that: The step of fusing the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area to determine a complete circular image after distortion correction includes: Determine a difference area between a preset pixel value sub-area of ​​the circular image of the left target calibration plate and the overlapping field of view area; The difference area and the circular image of the right target calibration plate are spliced, and the complete circular image is determined based on the splicing result.

7. The image distortion correction method according to any one of claims 1 to 5, characterized in that: The determining the overlapping field of view area of ​​the left and right cameras based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the left calibration plate circular image and the right calibration plate circular image, comprises: When there are multiple left semicircular images, multiple right semicircular images, multiple circular images of the left calibration plate, and multiple circular images of the right calibration plate, determining first target axial distances corresponding to the multiple left semicircular images and second target axial distances corresponding to the multiple right semicircular images; Determine a mean value of the target transverse diameter based on the left target transverse diameter corresponding to each of the circular images of the left target calibration plate and the left target transverse diameter corresponding to each of the circular images of the right target calibration plate; The overlapping field of view area is determined based on the first target axial distance, the second target axial distance and the average of the target transverse diameter.

8. The image distortion correction method according to any one of claims 1 to 5, characterized in that: The method further comprises: Based on the number of diameter pixels of the complete circular image and the diameter length of the preset circular calibration plate, a mapping coefficient characterizing the mapping relationship between the number of pixels and the diameter length in millimeters is determined.

9. An image distortion correction device, characterized in that: include: A lateral distortion correction unit is used to perform lateral distortion correction on the circular image of the left calibration plate and the circular image of the right calibration plate obtained by the left and right cameras of the binocular camera, respectively, to determine the circular image of the left target calibration plate and the circular image of the right target calibration plate; an overlapping area determination unit, configured to determine the overlapping field of view area of ​​the left and right cameras based on the left semicircular image and the right semicircular image acquired by the left and right cameras, and the circular image of the left calibration plate and the circular image of the right calibration plate when the preset circular calibration plate is located at the preset position of the left and right cameras; The image distortion correction unit is used to determine a complete circular image after distortion correction based on the fusion of the circular image of the left target calibration plate, the circular image of the right target calibration plate and the overlapping field of view area.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the image distortion correction method as described in any one of claims 1 to 8 is implemented.