Method and apparatus for determining overlapping region of images, electronic device and storage medium

Abstract

Embodiments of the present disclosure disclose a method and device for determining an overlapping area of images, electronic equipment and a storage medium, wherein the method comprises: obtaining a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system; determining a first boundary pixel set in the first cylindrical image coordinate system based on the first cylindrical image; determining a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image; converting each pixel in the first boundary pixel set to the second cylindrical image coordinate system to obtain a target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system; and determining an overlapping area of the first cylindrical image and the second cylindrical image based on the target pixel set and the target image boundary. The embodiments of the present disclosure realize the determination of the overlapping area of the cylindrical image, can effectively retain the image information of a larger field of view angle area, and solve the problem of missing information in a large field of view angle area.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer vision, and particularly relates to a method and apparatus for determining an overlapping region of images, an electronic device and a storage medium. BACKGROUND

[0002] In an autonomous driving scenario, fisheye cameras are widely used due to their large field of view (FOV). For example, four fisheye cameras are used to form a four-way surround view system to perceive the surrounding environment information of a vehicle. In order to better perceive the surrounding environment, the images of the cameras are usually fused and stitched to form a complete surrounding environment image. In the fusion process, since the adjacent cameras usually have an overlapping view coverage region (referred to as an overlapping region), the overlapping region between images of different views needs to be determined to facilitate subsequent multi-view fusion. In the related art, the overlapping region is usually determined based on a pinhole camera model. However, the pinhole camera model cannot retain the pixel information of the fisheye camera beyond a certain angle (such as 180 degrees), resulting in a lack of information. SUMMARY

[0003] To solve the technical problems such as the information loss caused by the pinhole camera model, the present disclosure is proposed. Embodiments of the present disclosure provide a method and apparatus for determining an overlapping region of images, an electronic device and a storage medium.

[0004] According to an aspect of an embodiment of the present disclosure, a method for determining an overlapping region of images is provided, including: obtaining a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system; determining a first set of boundary pixel points in the first cylindrical image coordinate system based on the first cylindrical image; determining a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image, the target image boundary including at least one boundary of the second cylindrical image; converting each pixel point in the first set of boundary pixel points to the second cylindrical image coordinate system to obtain a target set of pixel points corresponding to the first set of boundary pixel points in the second cylindrical image coordinate system; and determining an overlapping region of the first cylindrical image and the second cylindrical image based on the target set of pixel points and the target image boundary.

[0005] According to another aspect of the embodiments of the present disclosure, a device for determining an overlapping area of images is provided, comprising: a first obtaining module configured to obtain a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system; a first processing module configured to determine a first boundary pixel set in the first cylindrical image coordinate system based on the first cylindrical image; a second processing module configured to determine a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image, the target image boundary comprising at least one boundary of the second cylindrical image; a third processing module configured to convert each pixel in the first boundary pixel set to the second cylindrical image coordinate system to obtain a target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system; and a fourth processing module configured to determine an overlapping area of the first cylindrical image and the second cylindrical image based on the target pixel set and the target image boundary.

[0006] According to still another aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, the storage medium storing a computer program, the computer program being configured to execute the method for determining an overlapping area of images according to any one of the embodiments of the present disclosure.

[0007] According to yet another aspect of the embodiments of the present disclosure, an electronic device is provided, comprising: a processor; a memory configured to store executable instructions for the processor; and the processor configured to read the executable instructions from the memory and execute the instructions to implement the method for determining an overlapping area of images according to any one of the embodiments of the present disclosure.

[0008] Based on the method, device, electronic device and storage medium for determining an overlapping area of images provided by the embodiments of the present disclosure, the first boundary pixel set in the first cylindrical image coordinate system and the image boundary in the second cylindrical image coordinate system are determined, and each pixel in the first boundary pixel set is converted to the second cylindrical image coordinate system, so as to determine the overlapping area of the first cylindrical image and the second cylindrical image, which realizes the determination of the overlapping area of the cylindrical images. Since the field of view angle of the cylindrical image is large, the image information in the large field of view angle region of the fisheye camera can be effectively reserved, and the problems such as information loss in the large field of view angle region caused by the prior art are solved.

[0009] The technical solutions of the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. The drawings provided below are for illustrative purposes and are included to further convey the principles of the present disclosure and are not intended to limit the scope of the present disclosure. The drawings provided are intended to explain the principles of the present disclosure and are not intended to limit the scope of the present disclosure. In the drawings, like reference numerals refer to like elements or steps throughout.

[0011] Figure 1 is one exemplary application scenario of the method for determining the overlapping region of images provided by the present disclosure;

[0012] Figure 2 is a flowchart of the method for determining the overlapping region of images provided by an exemplary embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of the method for determining the overlapping region of images provided by another exemplary embodiment of the present disclosure;

[0014] Figure 4 is a schematic diagram of the principle of determining the preset sequence provided by an exemplary embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of the target pixel set provided by an exemplary embodiment of the present disclosure;

[0016] Figure 6 is a flowchart of step 2042 provided by an exemplary embodiment of the present disclosure;

[0017] Figure 7 is a schematic diagram of the first cylindrical camera coordinate system provided by an exemplary embodiment of the present disclosure;

[0018] Figure 8 is a schematic diagram of the conversion principle from the second coordinate point to the third coordinate point provided by an exemplary embodiment of the present disclosure;

[0019] Figure 9 is a flowchart of step 2053 provided by an exemplary embodiment of the present disclosure;

[0020] Figure 10 is a structural schematic diagram of the device for determining the overlapping region of images provided by an exemplary embodiment of the present disclosure;

[0021] Figure 11 is a structural schematic diagram of the device for determining the overlapping region of images provided by another exemplary embodiment of the present disclosure;

[0022] Figure 12 is a structural schematic diagram of an application embodiment of the electronic device of the present disclosure. DETAILED DESCRIPTION

[0023] Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of embodiments of the present disclosure, and the present disclosure should not be limited to the described embodiments.

[0024] It should be noted that the relative arrangement, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0025] Those skilled in the art can understand that the terms "first", "second", and the like in the embodiments of the present disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they represent a logical order between them.

[0026] It should also be understood that in the embodiments of the present disclosure, "a plurality of" can mean two or more, and "at least one" can mean one, two, or more.

[0027] It should also be understood that for any component, data, or structure mentioned in the embodiments of the present disclosure, it can be understood as one or more in general, without explicit limitation or in the context of the preceding and following text giving the opposite indication.

[0028] In addition, the term "and / or" in the present disclosure is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the front and rear associated objects.

[0029] It should also be understood that the description of the embodiments of the present disclosure focuses on the differences between the embodiments, and the same or similar parts can be referred to each other, and for the sake of brevity, they will not be repeated.

[0030] At the same time, it should be understood that, for the sake of brevity, the size of each part shown in the drawings is not drawn in accordance with the actual proportional relationship.

[0031] The following description of at least one example embodiment is merely illustrative in nature and does not in any way limit the disclosure and its application or uses.

[0032] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification where appropriate.

[0033] It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0034] Embodiments of the present disclosure can be applied to terminal devices, computer systems, servers and other electronic devices, which can operate with many other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with terminal devices, computer systems, servers and other electronic devices include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments that include any of the above systems, and the like.

[0035] Terminal devices, computer systems, servers and other electronic devices can be described in the general context of computer system executable instructions, such as program modules, executed by the computer system. Generally, program modules can include routines, programs, objects, components, logic, data structures, and the like, which perform particular tasks or implement particular abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, in which tasks are performed by remote processing devices that are linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computer system storage media including storage devices.

[0036] SUMMARY

[0037] In the process of implementing the present disclosure, the inventors found that in the automatic driving scene, fisheye cameras are widely used due to their large field of view (FOV), such as four fisheye cameras forming a four-way surround view system for perceiving the surrounding environment information of the vehicle. In order to better perceive the surrounding environment, it is usually necessary to fuse and stitch the images of each camera to form a complete surrounding environment image. In the fusion process, since adjacent cameras usually have overlapping angle coverage areas (referred to as overlapping areas), it is necessary to determine the overlapping areas between images of different angles to facilitate subsequent multi-view fusion. In the related art, the overlapping areas are usually determined based on a pinhole camera model, but the pinhole camera model cannot preserve the pixel information of the fisheye camera beyond a certain angle (such as 180 degrees), resulting in the loss of information.

[0038] EXEMPLARY SUMMARY

[0039] Figure 1 is an exemplary application scenario of the method for determining the overlapping area of the image provided by the present disclosure.

[0040] In autonomous driving scenarios, cameras (such as fisheye cameras) based on the four perspectives (including left-view, front-view, right-view, and rear-view) of the vehicle's four-way surround-view system acquire images of the vehicle's surrounding environment. The overlapping region determination method of the image disclosed herein is executed using the image overlapping region determination device of this disclosure. The overlapping regions between the left-view and front-view (referred to as the left front overlapping region), the overlapping regions between the front-view and right-view (referred to as the front right overlapping region), the overlapping regions between the right-view and rear-view (referred to as the right rear overlapping region), and the overlapping regions between the left-view and rear-view (referred to as the left rear overlapping region) can be determined for subsequent multi-view fusion and stitching. Specifically, for any two adjacent viewpoints, such as a left-view viewpoint and a front-view viewpoint, the images of the two adjacent viewpoints can be transformed into their respective cylindrical image coordinate systems to obtain a first cylindrical image corresponding to one viewpoint (e.g., the left-view viewpoint) and a second cylindrical image corresponding to the other viewpoint (e.g., the front-view viewpoint). Based on the first cylindrical image, a first boundary pixel set in the first cylindrical image coordinate system can be determined. Based on the second cylindrical image, a target image boundary in the second cylindrical image coordinate system can be determined. The target image boundary includes at least one boundary of the second cylindrical image. Then, each pixel in the first boundary pixel set is transformed into the second cylindrical image coordinate system to obtain the target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system. Based on the target pixel set and the target image boundary, the overlapping area of ​​the first cylindrical image and the second cylindrical image is determined. This overlapping area can be used as the overlapping area between the two adjacent viewpoints, or the overlapping area can be transformed into another coordinate system (e.g., the vehicle coordinate system), and the overlapping area in this other coordinate system can be used as the overlapping area between the two adjacent viewpoints. The specific settings can be configured according to actual needs. This embodiment of the present disclosure realizes the determination of the overlapping area of ​​cylindrical images. Since the cylindrical image has a large field of view, it can effectively retain the image information of the large field of view area of ​​the fisheye camera, and solve the problem of information loss in the large field of view area caused by the prior art.

[0041] The method for determining the overlapping region of images provided in this disclosure is not limited to autonomous driving scenarios, but can also be applied to any other scenario that requires multi-view fusion, such as map building scenarios, parking scenarios, etc., according to actual needs, without any specific limitation.

[0042] EXEMPLARY METHOD

[0043] Figure 2 This is a flowchart illustrating a method for determining overlapping regions of an image according to an exemplary embodiment of this disclosure. This embodiment can be applied to electronic devices, specifically, for example, in-vehicle computing platforms. Figure 2 As shown, it includes the following steps:

[0044] Step 201, obtaining a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system.

[0045] The first cylindrical image coordinate system is a cylindrical image coordinate system corresponding to a first view angle, and the second cylindrical image coordinate system is a cylindrical image coordinate system corresponding to a second view angle. The first view angle and the second view angle are adjacent view angles with an overlapping area. The first cylindrical image can be obtained by converting a first image captured by a camera at the first view angle from an image pixel coordinate system to the first cylindrical image coordinate system, and the second cylindrical image can be obtained by converting a second image captured by a camera at the second view angle from the image pixel coordinate system to the second cylindrical image coordinate system.

[0046] In an optional example, for the conversion from the first image to the first cylindrical image, the conversion can be realized by converting from the image pixel coordinate system to a camera coordinate system, from the camera coordinate system to a cylindrical camera coordinate system, and from the cylindrical camera coordinate system to the cylindrical image coordinate system. The same applies to the second cylindrical image, which will not be described here.

[0047] In an optional example, when converting the first image to the first cylindrical image, any pixel point A on the first cylindrical image coordinate system can be converted to a corresponding pixel point B in the first image pixel coordinate system corresponding to the first image, and the pixel value (such as the RGB value) of the corresponding pixel point B can be taken as the RGB value of the pixel point A. For the case that the pixel point B is not a known pixel point in the first image pixel coordinate system, such as the pixel point B being (1.5, 2.5), the pixel value of the pixel point B can be obtained by interpolation of adjacent known pixel points. In this way, the pixel value of each pixel point on the first cylindrical image coordinate system can be obtained, thereby avoiding the occurrence of a hole in the first cylindrical image.

[0048] Step 202, determining a first boundary pixel point set in the first cylindrical image coordinate system based on the first cylindrical image.

[0049] The first boundary pixel point set can be determined according to a preset rule. The preset rule can be determined based on the possible overlapping part between two adjacent view angles and the conversion requirement of the cylindrical image coordinate system of the subsequent adjacent view angle. For example, only the points on the ground can be converted between two view angles because the Z-axis coordinate in the known vehicle coordinate system is known. Therefore, the first boundary pixel point set can be a boundary pixel point set belonging to the ground part in the first cylindrical image.

[0050] In an optional example, the part belonging to the ground in the first cylindrical image can be determined by a vanishing line of the first cylindrical image, the vanishing line representing a vanishing position of the ground plane, and the part below the vanishing line belongs to the ground. In order to facilitate the determination of the vanishing line, the cylindrical camera can be a virtual camera whose pitch angle has been corrected to 0, so that the vanishing line of the cylindrical image is a line in the middle of the cylindrical image and parallel to the horizontal plane. Based on this, the first boundary pixel set can be determined as a point set formed by the boundary pixels of the part below the vanishing line of the first cylindrical image.

[0051] In step 203, the target image boundary in the second cylindrical image coordinate system is determined based on the second cylindrical image, and the target image boundary includes at least one boundary of the second cylindrical image.

[0052] The target image boundary can be determined based on the adjacent relationship between the second cylindrical image and the first cylindrical image. For example, when the first camera corresponding to the first cylindrical image is on the left of the second camera corresponding to the second cylindrical image, the left boundary and the lower boundary of the second cylindrical image can have overlapping parts with the first cylindrical image, and the target image boundary is the left boundary and the lower boundary. Similarly, if the first camera is on the right of the second camera, the target image boundary is the right boundary and the lower boundary. The specific setting can be made according to actual needs.

[0053] In step 204, each pixel point in the first boundary pixel set is converted to the second cylindrical image coordinate system to obtain a target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system.

[0054] The conversion of the pixel points in the first boundary pixel set to the second cylindrical image coordinate system can be realized by first converting the pixel points to the first cylindrical camera coordinate system corresponding to the first cylindrical image, then converting from the first cylindrical camera coordinate system to the vehicle coordinate system, and then converting from the vehicle coordinate system to the second cylindrical camera coordinate system corresponding to the second cylindrical image.

[0055] In step 205, the overlapping area of the first cylindrical image and the second cylindrical image is determined based on the target pixel set and the target image boundary.

[0056] Since the target pixel set represents the boundary of the first cylindrical image in the second cylindrical image coordinate, and the target image boundary represents the boundary of the second cylindrical image, the two cylindrical images are unified in the same coordinate system. If the two perspectives have an overlapping area, the cylindrical image boundaries in the same coordinate system of the two perspectives will enclose a certain area, which can represent the overlapping area of the two perspectives in the second cylindrical image coordinate system.

[0057] The method for determining the overlapping region of images provided by the embodiment determines the first boundary pixel set in the first cylindrical image coordinate system and the image boundary in the second cylindrical image coordinate system, converts the first boundary pixel set to the second cylindrical image coordinate system, and determines the overlapping region of the first cylindrical image and the second cylindrical image, thereby achieving the determination of the overlapping region of the cylindrical image. Since the field of view angle of the cylindrical image is large, the image information in the large field of view angle region of the fisheye camera can be effectively retained, and the problem of information loss in the large field of view angle region caused by the prior art is solved.

[0058] Figure 3 FIG. 1 is a flowchart of the method for determining the overlapping region of images provided by another exemplary embodiment of the present disclosure.

[0059] In an optional embodiment, step 204 can specifically include the following steps.

[0060] Step 2041, determining the current pixel point based on the first boundary pixel set and the preset sequence.

[0061] The preset sequence can be determined based on the adjacent relationship between the first camera and the second camera (the first camera is located on the first side (such as the left side) or the second side (such as the right side) of the second camera). Each pixel point in the first boundary pixel set is sequentially taken as the current pixel point in the preset sequence.

[0062] For example, Figure 4 FIG. 2 is a schematic diagram of the determination principle of the preset sequence provided by an exemplary embodiment of the present disclosure. When the first camera is located on the left side of the second camera, for example, the camera with the left view angle is the first camera, and the camera with the front view angle is the second camera. The boundary pixel points on the right side of the first boundary pixel set are most likely to be the boundary points of the overlapping region. Therefore, in order to reduce the calculation amount, the preset sequence is the sequence from the topmost point on the right side of the first boundary pixel set in the clockwise direction (as indicated by the arrow).

[0063] Step 2042, converting the current pixel point to the second cylindrical image coordinate system to obtain the target pixel point corresponding to the current pixel point.

[0064] The conversion principle of the first cylindrical image coordinate system to the second cylindrical image coordinate system is described above and will not be repeated here.

[0065] Step 2043, determining the first distance between the target pixel point and each boundary in the target image boundary.

[0066] The distance between the target pixel point and each boundary can be determined based on the distance principle from a point to a straight line. The first distance represents the pixel distance from the target pixel point to each boundary. For example, the first distance between the target pixel point and a certain boundary is 5 pixels.

[0067] In response to the first distance corresponding to any of the boundaries being less than the preset distance threshold, step 2044 takes the set of target image points corresponding to the current pixel point and the previous pixel point as a target image point set, and the previous pixel point includes each pixel point determined based on the first boundary pixel point set and the preset order before the current pixel point.

[0068] The preset distance threshold can be set according to actual needs, for example, it can be set to 1 pixel. If the first distance between the target image point corresponding to the current pixel point and a certain boundary is less than the preset distance threshold, it indicates that the boundary where the target image point is located intersects with the target image boundary, and it indicates that the pixel points that have been traversed and the target image boundary enclose a certain area. The previous pixel point is a pixel point processed according to the processing procedure of the current pixel point before the current pixel point, for example, Figure 5 is a schematic diagram of a target image point set provided by an example embodiment of the present disclosure. The target image point corresponding to the current pixel point is the black pixel point at the lower left corner of the second cylindrical image, and the other gray pixel points are target image points corresponding to the previous pixel points.

[0069] By setting the traversal order of the pixel points in the first boundary pixel point set, the embodiment can control the boundary pixel points most likely to belong to the overlapping area to be traversed first, and the traversal can be ended when the pixel point traversed is less than the preset distance threshold from the boundary of the second cylindrical image in the second cylindrical image coordinate system, without the need to traverse the remaining pixel points in the first boundary pixel point set, which can effectively reduce the number of pixel points traversed, thereby improving the processing efficiency and quickly determining the overlapping area.

[0070] In an optional embodiment, the first boundary pixel point set includes the pixel points of the first side boundary below the vanishing line of the first cylindrical image, the pixel points of the first lower boundary, and the pixel points of the second side boundary below the vanishing line; and the determination of the current pixel point based on the first boundary pixel point set and the preset order in step 2041 includes:

[0071] In response to the first camera corresponding to the first cylindrical image being on the first side of the second camera corresponding to the second cylindrical image, the pixel point close to the vanishing line of the second side boundary of the first boundary pixel point set is taken as a starting pixel point, and the current pixel point is determined in a clockwise order; in response to the first camera being on the second side of the second camera, the pixel point close to the vanishing line of the first side boundary is taken as a starting pixel point, and the current pixel point is determined in a counterclockwise order.

[0072] The determination principle of the vanishing line is described above and will not be repeated here. The first side can be the left side described above, and the second side can be the right side described above. The case where the first camera is on the first side of the second camera can be described above Figure 5The case is not described here again. The principle of the second side of the second camera is similar to the first side, which is not described here again.

[0073] The embodiment can ensure that the two-view cameras in any position relationship can effectively traverse the pixel points of the first boundary pixel point set, effectively reduce the traversal of invalid pixel points, and further improve the universality, for example, the cylindrical image of the left-view perspective can be taken as the first cylindrical image, and the cylindrical image of the front-view perspective can be taken as the second cylindrical image, or the cylindrical image of the front-view perspective can be taken as the first cylindrical image, and the cylindrical image of the left-view perspective can be taken as the second cylindrical image.

[0074] Figure 6 FIG. 2 is a flowchart of step 2042 according to an example embodiment of the present disclosure.

[0075] In an optional embodiment, step 2042 converts the current pixel point into the second cylindrical image coordinate system to obtain a target pixel point corresponding to the current pixel point, including:

[0076] Step 20421 converts the current pixel point into the first cylindrical camera coordinate system corresponding to the first cylindrical image to obtain a first coordinate point in the first cylindrical camera coordinate system.

[0077] The first cylindrical camera coordinate system is a virtual cylindrical camera coordinate system pre-established for the first camera, which is a coordinate system in which the pitch angle has been corrected to 0.

[0078] An example is as follows: Figure 7 FIG. 2 is a schematic diagram of the first cylindrical camera coordinate system according to an example embodiment of the present disclosure. The first cylindrical camera coordinate system can be a coordinate system with the origin of the first camera as the origin, the X-axis (cylindrical radius) direction (i.e., the camera optical axis direction) with a pitch angle of 0 (parallel to the ground), the cylindrical height direction as the Z-axis, and the Y-axis direction representing a direction with an arc of 90 degrees, for example, the first coordinate point P in the first cylindrical camera coordinate system is represented as (r, θ, h), θ represents the arc between the connecting line OP' of the projection point P' of P in the XOY plane and the X-axis and the origin O, h represents the height of P relative to the XOY plane, and r represents the radius of the cylindrical surface on which P is located. The conversion of the first cylindrical image coordinate system to the first cylindrical camera coordinate system can be realized based on the pre-obtained intrinsic parameters of the first cylindrical camera.

[0079] Step 20422 converts the first coordinate point into the first Euclidean coordinate system corresponding to the first cylindrical image to obtain a second coordinate point in the first Euclidean coordinate system.

[0080] Wherein, since the first cylindrical camera coordinate system is projected onto the XOY plane as a polar coordinate including a radius and an arc, in order to facilitate subsequent conversion, the first coordinate point is converted from the first cylindrical camera coordinate system to the first Euclidean coordinate system. The coordinate components of the first Euclidean coordinate system represent the coordinates in the direction of each coordinate axis, for example, the first coordinate point P is converted from (r, θ, h) to a second coordinate point P1 in the first Euclidean coordinate system (for example, represented as an x-y-z-o coordinate system, the x-axis direction is the same as the X-axis direction of the first cylindrical camera coordinate system, the y-axis direction is the same as the Y-axis direction of the first cylindrical camera coordinate system, the z-axis direction is the same as the Z-axis direction of the first cylindrical camera coordinate system, and the coordinate origin o is the same as the coordinate origin O of the first cylindrical camera coordinate system), represented as (x1, y1, z1). The absolute value of each component of P1 can represent the distance, for example, if x1 is positive, it represents the distance from the yoz plane in the positive x-axis direction. Details are not repeated here.

[0081] In an optional embodiment, the representation of each axis of the first cylindrical camera coordinate system can be set according to actual needs, for example, the Z-axis represents the direction of the camera optical axis, the Y-axis represents the direction of the cylindrical height, and the X-axis represents the direction of the arc with an angle of 90 degrees. In this case, the x-axis, y-axis and z-axis directions of the first Euclidean coordinate system are the same as the Z-axis, X-axis and Y-axis directions of the first cylindrical camera coordinate system, respectively, and the coordinate origin o of the first Euclidean coordinate system is the same as the coordinate origin O of the first cylindrical camera coordinate system. As long as the conversion relationship between the first cylindrical camera coordinate system and the first Euclidean camera coordinate system can be clearly represented.

[0082] Step 20423, converting the second coordinate point to a target observation coordinate system to obtain a third coordinate point.

[0083] Wherein, the target observation coordinate system can be a preset plane coordinate system of the vehicle coordinate system, for example, the Z=0 plane coordinate system of the vehicle coordinate system, which can be set according to actual needs.

[0084] Exemplarily, Figure 8 is a schematic diagram of the conversion principle of the second coordinate point to the third coordinate point provided by an exemplary embodiment of the present disclosure. The x and y coordinates of the second coordinate point can be converted to the Z=0 plane of the vehicle coordinate system according to the proportional relationship between the z-axis coordinate z1 of the second coordinate point and the installation height H of the first camera. The scale change of the third coordinate point relative to the second coordinate point in the Z direction is H / (-z1), and the x and y coordinates of the second coordinate point are mapped to the Z=0 plane according to the scale change.

[0085] Step 20424, converting the third coordinate point to a second cylindrical camera coordinate system corresponding to the second cylindrical image to obtain a fourth coordinate point.

[0086] The conversion of the third coordinate point to the second cylindrical camera coordinate system can be implemented by using a conversion rule from the target observation coordinate system to the second cylindrical camera, and details are not described herein again.

[0087] In step 20425, the fourth coordinate point is converted to the second cylindrical image coordinate system to obtain a target pixel point.

[0088] The conversion of the fourth coordinate point to the second cylindrical image coordinate system can be implemented based on the intrinsic parameters of the second cylindrical camera, and details are not described herein again.

[0089] In the embodiment, the current pixel point of the first cylindrical image is converted to the second cylindrical image coordinate system of the second cylindrical image through a series of coordinate system conversions, so that the determination of the boundary of the overlapping region is facilitated.

[0090] In an optional embodiment, the target image boundary includes a third side boundary below the vanishing line of the second cylindrical image and a second lower boundary; and the determination of the overlapping region of the first cylindrical image and the second cylindrical image based on the target pixel point set and the target image boundary in step 205 includes:

[0091] In step 2051, a target image boundary pixel point set corresponding to the target image boundary is determined based on the target image boundary.

[0092] The third side boundary can be determined as a left side boundary (when the first camera is located on the left side of the second camera) or a right side boundary (when the first camera is located on the right side of the second camera) below the vanishing line of the second cylindrical image according to the positional relationship between the first camera and the second camera, the second lower boundary can be the overall lower boundary of the second cylindrical image, and the target image boundary pixel point set is a pixel point set on the target image boundary of the second cylindrical image. The pixel points of the corresponding target image boundary can be extracted from the second cylindrical image based on the size of the second cylindrical image to form the target image boundary pixel point set.

[0093] In step 2052, boundary pixel points belonging to the contour of the overlapping region are determined from the target image boundary pixel point set based on the target pixel point set to obtain a boundary pixel point set.

[0094] The boundary pixel points belonging to the contour of the overlapping region can be determined based on the target pixel point closest to the target image boundary in the target pixel point set, such as determining a first pixel point closest to the target pixel point from the target image boundary pixel point set based on the target pixel point. The boundary pixel points between the first pixel point and the vanishing line of the second cylindrical image are all boundary pixel points belonging to the contour of the overlapping region, so as to form the boundary pixel point set of the boundary pixel points belonging to the contour of the overlapping region.

[0095] In step 2053, the overlapping region of the first cylindrical image and the second cylindrical image is determined based on the target pixel point set and the boundary pixel point set.

[0096] The target pixel set and the boundary pixel set form the boundary pixel set of the overlapping region between the first cylindrical image and the second cylindrical image in the second cylindrical image coordinate system. The region enclosed by this boundary pixel set can be used as the overlapping region of the two perspectives.

[0097] In an optional embodiment, the pixel set at the boundary of the overlapping region can be processed, such as regularization or reducing the number of points. The overlapping region of the two views can be determined based on the processed pixel set. The specific settings can be configured according to actual needs.

[0098] This embodiment uses the third side boundary below the vanishing line of the second cylindrical image and the second lower boundary as the target image boundary, which reduces the number of calculations for the first distance of the target pixels, avoids invalid calculations, and further improves processing efficiency. Furthermore, it can determine the overlapping region based on the determined set of target pixels and the set of pixels at the target image boundary, thus realizing the determination of the overlapping region under the cylindrical image.

[0099] Figure 9 This is a flowchart illustrating step 2053 provided in an exemplary embodiment of this disclosure.

[0100] In an optional embodiment, step 2053, determining the overlapping region between the first cylindrical image and the second cylindrical image based on the target pixel set and the boundary pixel set, includes:

[0101] Step 20531: Use the target pixel set and the boundary pixel set as the initial overlapping region contour point set.

[0102] Step 20532: Determine the shape of the overlapping region contour based on the initial overlapping region contour point set.

[0103] The outline shape of the overlapping area can be set according to actual needs.

[0104] In one optional example, to facilitate the subsequent reduction of contour points, the contour shape of the overlapping region can be determined as a circumscribed convex polygon. The specific determination method can be implemented using any feasible convex hull algorithm, such as the Graham scan method, the Jarvis step method (also known as the roll wrapping method), etc., without any particular limitation.

[0105] Step 20533: Based on the preset algorithm, perform contour point sampling processing on the contour shape of the overlapping area to obtain the processed target overlapping area contour point set.

[0106] The preset algorithm can be set according to actual requirements, for example, the Douglas-Peucker algorithm. The preset algorithm is used to approximately represent the contour shape of the overlapping region as a series of contour points, and reduce the number of contour points, to obtain a target overlapping region contour point set including fewer contour points.

[0107] In step 20534, the overlapping region of the first cylindrical image and the second cylindrical image is determined based on the target overlapping region contour point set.

[0108] The region surrounded by the target overlapping region contour point set is the overlapping region of the first cylindrical image and the second cylindrical image.

[0109] The embodiment reduces the number of contour points by determining the contour line based on the initial overlapping region contour point set, and then sampling the contour points of the contour line, to improve the subsequent use efficiency.

[0110] In an optional embodiment, the first boundary pixel point set in the first cylindrical image coordinate system is determined based on the first cylindrical image in step 202, including:

[0111] In step 2021, the vanishing line of the first cylindrical image is determined based on the first cylindrical image and a vanishing line determination rule.

[0112] The determination rule of the vanishing line is described above and will not be repeated here.

[0113] In step 2022, the first boundary pixel point set is determined based on the boundary pixel points below the vanishing line in the first cylindrical image.

[0114] The first boundary pixel point set is described above and will not be repeated here. Figure 4

[0115] The embodiment forms the first boundary pixel point set by the boundary pixel points below the vanishing line of the first cylindrical image, to ensure the accuracy of the conversion from the first cylindrical image coordinate system to the second cylindrical image coordinate system.

[0116] The above embodiments or optional examples of the present disclosure can be implemented alone or in any combination without conflict, and can be set according to actual requirements. The present disclosure is not limited.

[0117] ​Any of the determination methods of the overlapping area of images provided in the embodiments of the present disclosure can be executed by any appropriate device with data processing capability, including but not limited to: terminal devices and servers, etc. Alternatively, any of the determination methods of the overlapping area of images provided in the embodiments of the present disclosure can be executed by a processor, such as a processor executing any of the determination methods of the overlapping area of images provided in the embodiments of the present disclosure by calling corresponding instructions stored in a memory. Details are not described herein.

[0118] EXEMPLARY DEVICE

[0119] Figure 10 is a structural schematic diagram of a determination apparatus of an overlapping area of images provided in an example embodiment of the present disclosure. The apparatus of this embodiment can be used to implement the corresponding method embodiments of the present disclosure, such as the determination method of the overlapping area of images shown in Figure 10 The apparatus shown in comprises: a first acquisition module 501, a first processing module 502, a second processing module 503, a third processing module 504, and a fourth processing module 505.

[0120] The first acquisition module 501 is configured to acquire a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system.

[0121] The first processing module 502 is configured to determine a first boundary pixel point set in the first cylindrical image coordinate system based on the first cylindrical image.

[0122] The second processing module 503 is configured to determine a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image, the target image boundary comprising at least one boundary of the second cylindrical image.

[0123] The third processing module 504 is configured to convert each pixel point in the first boundary pixel point set to the second cylindrical image coordinate system to obtain a target pixel point set corresponding to the first boundary pixel point set in the second cylindrical image coordinate system.

[0124] The fourth processing module 505 is configured to determine an overlapping area of the first cylindrical image and the second cylindrical image based on the target pixel point set and the target image boundary.

[0125] Figure 11 is a structural schematic diagram of a determination apparatus of an overlapping area of images provided in another example embodiment of the present disclosure.

[0126] In an optional embodiment, the third processing module 504 comprises: a first processing unit 5041, a second processing unit 5042, a third processing unit 5043, and a fourth processing unit 5044.

[0127] The first processing unit 5041 is configured to determine a current pixel point based on the first boundary pixel point set and a preset order.

[0128] The second processing unit 5042 is configured to convert the current pixel point to a second cylindrical image coordinate system to obtain a target pixel point corresponding to the current pixel point.

[0129] The third processing unit 5043 is configured to determine a first distance between the target pixel point and each boundary in the target image boundary.

[0130] The fourth processing unit 5044 is configured to, in response to the first distance corresponding to any boundary in the boundaries being less than a preset distance threshold, take a set of target pixel points corresponding to the current pixel point and a previous pixel point as a target pixel point set, the previous pixel point including each pixel point determined based on the first boundary pixel point set and the preset order before the current pixel point.

[0131] In an optional embodiment, the first boundary pixel point set includes each pixel point of a first side boundary below a vanishing line of the first cylindrical image, each pixel point of a first lower boundary, and each pixel point of a second side boundary below the vanishing line; and the first processing unit 5041 is specifically configured to:

[0132] In response to a first camera corresponding to the first cylindrical image being on a first side of a second camera corresponding to the second cylindrical image, the first processing unit 5041 is configured to take a pixel point of a second side boundary of the first boundary pixel point set close to the vanishing line as a starting pixel point, and determine the current pixel point in a clockwise order; or in response to the first camera being on a second side of the second camera, the first processing unit 5041 is configured to take a pixel point of the first side boundary close to the vanishing line as the starting pixel point, and determine the current pixel point in a counterclockwise order.

[0133] In an optional embodiment, the second processing unit 5042 is specifically configured to:

[0134] The second processing unit 5042 is configured to convert the current pixel point to a first cylindrical camera coordinate system corresponding to the first cylindrical image to obtain a first coordinate point in the first cylindrical camera coordinate system; convert the first coordinate point to a first Euclidean coordinate system corresponding to the first cylindrical image to obtain a second coordinate point in the first Euclidean coordinate system; convert the second coordinate point to a target observation coordinate system to obtain a third coordinate point; convert the third coordinate point to a second cylindrical camera coordinate system corresponding to the second cylindrical image to obtain a fourth coordinate point; and convert the fourth coordinate point to the second cylindrical image coordinate system to obtain the target pixel point.

[0135] In an optional embodiment, the target image boundary includes a third side boundary below a vanishing line of the second cylindrical image and a second lower boundary; and the fourth processing module 505 includes a first determination unit 5051, a second determination unit 5052, and a third determination unit 5053.

[0136] The first determination unit 5051 is configured to determine a target image boundary pixel point set corresponding to the target image boundary based on the target image boundary.

[0137] The second determination unit 5052 is configured to determine, from the target image boundary pixel set, boundary pixel points belonging to the overlapping region contour, and obtain a boundary pixel point set.

[0138] The third determination unit 5053 is configured to determine, based on the target pixel point set and the boundary pixel point set, the overlapping region of the first cylindrical image and the second cylindrical image.

[0139] In an optional embodiment, the third determination unit 5053 is specifically configured to:

[0140] take the target pixel point set and the boundary pixel point set as an initial overlapping region contour point set, determine an overlapping region contour shape based on the initial overlapping region contour point set, perform contour point sampling processing on the overlapping region contour shape based on a preset algorithm, and obtain a processed target overlapping region contour point set, and determine the overlapping region of the first cylindrical image and the second cylindrical image based on the target overlapping region contour point set.

[0141] In an optional embodiment, the first processing module 502 includes a fourth determination unit 5021 and a fifth determination unit 5022.

[0142] The fourth determination unit 5021 is configured to determine the vanishing line of the first cylindrical image based on a first cylindrical image and vanishing line determination rule.

[0143] The fifth determination unit 5022 is configured to determine a first boundary pixel point set based on boundary pixel points below the vanishing line in the first cylindrical image.

[0144] The modules or units of any of the embodiments of the present disclosure can also be divided into finer granularity according to actual needs, and can be set according to actual needs, which are not limited by the present disclosure.

[0145] EXEMPLARY ELECTRONIC DEVICE

[0146] The embodiments of the present disclosure further provide an electronic device, including a memory configured to store a computer program, and a processor configured to execute the computer program stored in the memory, and when the computer program is executed, the determination method of the overlapping region of the image according to any of the embodiments of the present disclosure is implemented.

[0147] Figure 12 FIG. 1 is a structural schematic diagram of an electronic device according to an application embodiment of the present disclosure. In this embodiment, the electronic device 10 includes one or more processors 11 and a memory 12.

[0148] The processor 11 can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities and can control other components in the electronic device 10 to perform desired functions.

[0149] The memory 12 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, which the processor 11 can execute to implement the methods of various embodiments of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0150] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0151] For example, the input device 13 can be the microphone or the microphone array described above, which is used to capture the input signal of the sound source.

[0152] In addition, the input device 13 can further include, for example, a keyboard, a mouse, and the like.

[0153] The output device 14 can output various information including the determined distance information, direction information, and the like to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0154] Of course, in order to simplify, Figure 12 Only some of the components in the electronic device 10 related to the present disclosure are shown in FIG. 1, and components such as buses, input / output interfaces, and the like are omitted. In addition, the electronic device 10 can further include any other appropriate components according to specific application cases.

[0155] EXEMPLARY COMPUTER PROGRAM PRODUCT AND COMPUTER-READABLE STORAGE MEDIUM

[0156] In addition to the above-described methods and devices, embodiments of the present disclosure can be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform steps of the methods according to various embodiments of the present disclosure described in the above "Exemplary Methods" section of the specification.

[0157] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.

[0158] Furthermore, embodiments of the present disclosure can also be a computer readable storage medium, having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform steps of the methods described in the above “Exemplary Methods” section according to various embodiments of the present disclosure.

[0159] The computer readable storage medium can be a combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] The above describes the basic principles of the present disclosure in combination with specific embodiments, but it should be noted that the advantages, benefits, effects and the like mentioned in the present disclosure are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as the must-haves of each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and understanding, and the above details do not limit the present disclosure to the must-haves of the above specific details.

[0161] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between each embodiment can be referred to each other. For system embodiments, since they are basically corresponding to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0162] The block diagrams of devices, apparatuses, equipment, systems referred to in this disclosure are merely illustrative examples and are not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagrams. These devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner as will be appreciated by those skilled in the art. Words such as "include," "contain," "have," and the like are open-ended words that are to be interpreted to mean "including but not limited to," and are not to be interpreted as limiting the described embodiment to features, elements, and / or steps disclosed herein. The words "or" and "and" as used herein are to be interpreted as the word "and / or," and are not to be interpreted as requiring both features, elements, and / or steps disclosed herein. The word "such as" as used herein is to be interpreted as the phrase "such as but not limited to," and is not to be interpreted as limiting the described embodiment to features, elements, and / or steps disclosed herein.

[0163] The methods and apparatuses of this disclosure can be implemented in a number of ways. For example, the methods and apparatuses of this disclosure can be implemented using software, hardware, firmware, or any combination of these. The above described order of steps for the methods is merely illustrative, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the disclosure can also be implemented as a program recorded in a recording medium, which includes machine readable instructions for implementing the methods according to the disclosure. Thus, the disclosure also covers a recording medium storing a program for executing the methods according to the disclosure.

[0164] It is also important to note that the devices, equipment, and methods of this disclosure can be embodied in a variety of ways. These variations are contemplated as being within the scope of the present disclosure.

[0165] The above description of the disclosed aspects is given for illustrative purposes and is not intended to limit the scope of the disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0166] The above description has been given for illustrative and descriptive purposes. In addition, this description is not intended to limit embodiments of the disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain modifications, permutations, additions, and sub-combinations thereof.

Claims

1. A method for determining an overlapping area of images, comprising: obtaining a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system; determining a first boundary pixel set in the first cylindrical image coordinate system based on the first cylindrical image; determining a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image, the target image boundary comprising at least one boundary of the second cylindrical image; converting each pixel in the first boundary pixel set to the second cylindrical image coordinate system to obtain a target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system; determining an overlapping area of the first cylindrical image and the second cylindrical image based on the target pixel set and the target image boundary; wherein the converting each pixel in the first boundary pixel set to the second cylindrical image coordinate system to obtain a target pixel set corresponding to the first boundary pixel set in the second cylindrical image coordinate system comprises: determining a current pixel based on the first boundary pixel set and a preset order; converting the current pixel to the second cylindrical image coordinate system to obtain a target pixel corresponding to the current pixel; determining a first distance between the target pixel and each boundary in the target image boundary; in response to the first distance corresponding to any boundary in the boundaries being less than a preset distance threshold, taking a set of target pixels corresponding to the current pixel and a previous pixel as the target pixel set, the previous pixel comprising each pixel determined based on the first boundary pixel set and the preset order before the current pixel. the first boundary pixel set comprises each pixel of a first side boundary below a vanishing line of the first cylindrical image, each pixel of a first lower boundary, and each pixel of a second side boundary below the vanishing line; 2. The method of claim 1, wherein, the determining a current pixel based on the first boundary pixel set and a preset order comprises: in response to a first camera corresponding to the first cylindrical image being on a first side of a second camera corresponding to the second cylindrical image, taking a pixel of the second side boundary of the first boundary pixel set close to the vanishing line as a starting pixel, and determining the current pixel in a clockwise order; in response to the first camera being on a second side of the second camera, taking a pixel of the first side boundary close to the vanishing line as the starting pixel, and determining the current pixel in a counterclockwise order. the converting the current pixel to the second cylindrical image coordinate system to obtain a target pixel corresponding to the current pixel comprises:

3. The method of claim 1, wherein, converting the current pixel to a first cylindrical camera coordinate system corresponding to the first cylindrical image to obtain a first coordinate point in the first cylindrical camera coordinate system; converting the first coordinate point to a first Euclidean coordinate system corresponding to the first cylindrical image to obtain a second coordinate point in the first Euclidean coordinate system; converting the second coordinate point to a target observation coordinate system to obtain a third coordinate point; ​ convert the third coordinate point to a second cylindrical camera coordinate system corresponding to the second cylindrical image to obtain a fourth coordinate point; convert the fourth coordinate point to the second cylindrical image coordinate system to obtain the target pixel point.

4. The method of claim 1, wherein, The target image boundary includes a third side boundary and a second lower boundary below a vanishing line of the second cylindrical image. The determining of the overlapping region of the first cylindrical image and the second cylindrical image based on the target pixel point set and the target image boundary includes: determining a target image boundary pixel point set corresponding to the target image boundary based on the target image boundary; determining a boundary pixel point belonging to an overlapping region contour from the target image boundary pixel point set based on the target pixel point set, to obtain a boundary pixel point set; determining the overlapping region of the first cylindrical image and the second cylindrical image based on the target pixel point set and the boundary pixel point set.

5. The method of claim 4, wherein, The determining of the overlapping region of the first cylindrical image and the second cylindrical image based on the target pixel point set and the boundary pixel point set includes: taking the target pixel point set and the boundary pixel point set as an initial overlapping region contour point set; determining an overlapping region contour shape based on the initial overlapping region contour point set; performing contour point sampling processing on the overlapping region contour shape based on a preset algorithm to obtain a processed target overlapping region contour point set; determining the overlapping region of the first cylindrical image and the second cylindrical image based on the target overlapping region contour point set.

6. The method of claim 1, wherein, The determining of the first boundary pixel point set in the first cylindrical image coordinate system based on the first cylindrical image includes: determining a vanishing line of the first cylindrical image based on the first cylindrical image and a vanishing line determination rule; determining the first boundary pixel point set based on a boundary pixel point below the vanishing line in the first cylindrical image.

7. An apparatus for determining an overlapping region of images, comprising: a first acquisition module configured to acquire a first cylindrical image in a first cylindrical image coordinate system and a second cylindrical image in a second cylindrical image coordinate system; a first processing module configured to determine a first boundary pixel point set in the first cylindrical image coordinate system based on the first cylindrical image; a second processing module configured to determine a target image boundary in the second cylindrical image coordinate system based on the second cylindrical image, the target image boundary including at least one boundary of the second cylindrical image; a third processing module configured to convert each pixel point in the first boundary pixel point set to the second cylindrical image coordinate system to obtain a target pixel point set in the second cylindrical image coordinate system corresponding to the first boundary pixel point set; a fourth processing module configured to determine an overlapping region of the first cylindrical image and the second cylindrical image based on the target pixel point set and the target image boundary; The third processing module includes: a first processing unit configured to determine a current pixel point based on the first boundary pixel point set and a preset order. a second processing unit, configured to convert the current pixel point to the second cylindrical image coordinate system to obtain a target pixel point corresponding to the current pixel point; a third processing unit, configured to determine a first distance between the target pixel point and each of the boundaries in the target image boundary; a fourth processing unit, configured to, in response to the first distance corresponding to any of the boundaries being less than a preset distance threshold, take a set of target pixel points corresponding to the current pixel point and a previous pixel point as the target pixel point set, the previous pixel point including each pixel point determined based on the first boundary pixel point set and the preset sequence before the current pixel point. 8.A computer readable storage medium, the storage medium storing a computer program, the computer program being configured to execute the method for determining an overlapping area of images according to any one of claims 1 to 6. 9.An electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor, configured to read the executable instructions from the memory and execute the instructions to implement the method for determining an overlapping area of images according to any one of claims 1 to 6.

Images