Roadside camera calibration system, method, device, equipment and medium

Abstract

The embodiment of the invention discloses a road side camera calibration system, method, device and equipment and a medium, the system comprises edge computing equipment, a target vehicle in communication connection with the edge computing equipment and a to-be-calibrated camera, the target vehicle is configured to run in a calibration field, and the to-be-calibrated camera is configured to run in the calibration field. Positioning data of the current target vehicle is uploaded to the edge computing device, and the positioning data is first position information, obtained through a positioning sensor on the target vehicle, of the target vehicle in a world coordinate system; the to-be-calibrated camera is configured to collect a driving image of the target vehicle and upload the collected image data to the edge computing device; and the edge computing equipment is configured to acquire second position information of the target vehicle in the image from the image data, and establish an association relationship between the first position information and the second position information according to the timestamp. According to the technical scheme, the real-time performance, rapidity and safety of road side camera calibration are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of camera calibration technology, and in particular, to a calibration system, method, device, equipment and medium for a roadside camera. Background Art

[0002] Roadside cameras are usually used in traffic monitoring, vehicle detection and other application scenarios, which require very high accuracy and stability of the camera. Through camera calibration, the internal and external parameters of the camera can be obtained, and then applied to the recognition and positioning of road targets.

[0003] For the external parameters of roadside cameras, traditional calibration methods usually require special calibration boards or targets, or use RTK (Real Time Kinematic) to mark points on the road to calibrate the road test camera. The above methods are offline and are not suitable for application scenarios that require real-time calibration. In addition, the above methods all require manual operation, with low calibration efficiency and poor safety. Summary of the invention

[0004] Embodiments of the present invention provide a roadside camera calibration system, method, apparatus, device and medium to improve the real-time, rapidity and safety of roadside camera calibration.

[0005] The specific technical solutions are as follows:

[0006] In a first aspect, an embodiment of the present invention provides a roadside camera calibration system, the system comprising: an edge computing device, a target vehicle and a camera to be calibrated that are in communication connection with the edge computing device, wherein the target vehicle, the camera to be calibrated and the edge computing device are timed by the same timing device.

[0007] The target vehicle is configured to travel in the calibration field and upload the positioning data of the current target vehicle to the edge computing device, wherein the positioning data is the first position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle;

[0008] The camera to be calibrated is configured to collect driving images of the target vehicle and upload the collected image data to the edge computing device;

[0009] The edge computing device is configured to obtain the second position information of the target vehicle in the image from the image data, establish an association relationship between the first position information and the second position information according to the timestamp, and use the association relationship as the calibration data of the camera to be calibrated.

[0010] Optionally, the edge computing device is specifically configured as:

[0011] Acquire the position information of other target objects to be measured in the image except the target vehicle in the image data;

[0012] Based on the association relationship, the position information to be measured is converted into position information based on the world coordinate system.

[0013] In a second aspect, an embodiment of the present invention provides a roadside camera calibration method, which is applied to an edge computing device, and the method includes:

[0014] Receive first position information uploaded by the target vehicle, and receive image data containing the target vehicle sent by the camera to be calibrated, wherein the target vehicle, the camera to be calibrated and the current edge computing device are timed by the same timing device, and the first position information is the position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle;

[0015] Acquire second position information of the target vehicle in the image from the image data;

[0016] An association relationship is established between the first position information and the second position information according to the timestamp, and the association relationship is used as calibration data of the camera to be calibrated.

[0017] Optionally, the method provided by the embodiment of the present invention further includes:

[0018] Based on the interpolation algorithm, interpolation processing is performed on the second position information in the association relationship to obtain the first position information corresponding to the interpolated second position information;

[0019] Accordingly, generating an association relationship between the first location information and the second location information according to the timestamp includes:

[0020] According to the timestamp, and based on all the first position information and the corresponding second position information before and after the interpolation, an association relationship table between the first position information and the second position information is generated.

[0021] Optionally, the second position information includes horizontal coordinate information and vertical coordinate information of the image pixel, and the first position information includes longitude information and latitude information in a world coordinate system;

[0022] Correspondingly, based on the interpolation algorithm, the second position information in the association relationship is interpolated, including:

[0023] Based on a linear interpolation algorithm, an interpolation operation is performed on the horizontal coordinate information in the second position information to obtain longitude information in a world coordinate system corresponding to the interpolated horizontal coordinate information; and

[0024] Based on the Lagrange interpolation algorithm, an interpolation operation is performed on the ordinate information in the second position information to obtain latitude information in the world coordinate system corresponding to the interpolated ordinate information.

[0025] Optionally, after establishing the association relationship, the method provided by the embodiment of the present invention further includes:

[0026] Obtaining position information of other target objects in the image data other than the target vehicle in the image;

[0027] Based on the association relationship, the position information in the image is converted into position information based on the world coordinate system.

[0028] In a third aspect, an embodiment of the present invention further provides a calibration device for a roadside camera, the device comprising:

[0029] A first position information receiving module is configured to receive first position information uploaded by a target vehicle, and receive image data containing the target vehicle sent by a camera to be calibrated, wherein the target vehicle, the camera to be calibrated and the current edge computing device are timed by the same timing device, and the first position information is the position information of the target vehicle in the world coordinate system obtained by a positioning sensor on the target vehicle;

[0030] A second position information determination module is configured to obtain second position information of the target vehicle in the image from the image data;

[0031] The association relationship establishing module is configured to establish an association relationship between the first location information and the second location information according to the timestamp.

[0032] Optionally, the association relationship establishment module is specifically configured as follows:

[0033] Generate an association relationship table between the first location information and the second location information according to the timestamp;

[0034] Accordingly, the device provided by the embodiment of the present invention further includes:

[0035] An interpolation module is configured to perform interpolation processing on the second position information in the association relationship based on an interpolation algorithm to obtain first position information corresponding to the interpolated second position information;

[0036] Correspondingly, the association relationship establishment module is specifically configured as follows:

[0037] According to the timestamp, and based on all the first position information and the corresponding second position information before and after the interpolation, an association relationship table between the first position information and the second position information is generated.

[0038] Optionally, the second position information includes horizontal coordinate information and vertical coordinate information of the image pixel, and the first position information includes longitude information and latitude information in a world coordinate system;

[0039] Correspondingly, the interpolation module is specifically configured as follows:

[0040] Based on a linear interpolation algorithm, an interpolation operation is performed on the horizontal coordinate information in the second position information to obtain longitude information in a world coordinate system corresponding to the interpolated horizontal coordinate information; and

[0041] Based on the Lagrange interpolation algorithm, an interpolation operation is performed on the ordinate information in the second position information to obtain latitude information in the world coordinate system corresponding to the interpolated ordinate information.

[0042] Optionally, the device provided by the embodiment of the present invention further includes:

[0043] The position determination module is configured to obtain the position information of other target objects in the image data other than the target vehicle in the image, and based on the association relationship, convert the position information in the image into position information based on the world coordinate system.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer device, the computer device comprising:

[0045] At least one processor is coupled to a memory, and the memory stores a program or instruction running on the processor. When the program or instruction is executed by the processor, the calibration method of the roadside camera provided in any embodiment of the present invention is implemented.

[0046] In a fifth aspect, an embodiment of the present invention provides a readable storage medium having a program or instruction stored thereon, which, when executed by a processor, implements a roadside camera calibration method as provided in any embodiment of the present invention.

[0047] In a sixth aspect, an embodiment of the present invention provides a vehicle, which includes the calibration device for a roadside camera provided by any embodiment of the present invention, or includes the computer device provided by any embodiment of the present invention.

[0048] In a seventh aspect, an embodiment of the present invention provides a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the calibration method of a roadside camera provided in any embodiment of the present invention is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0050] Figure 1a A structural block diagram of a roadside camera calibration system provided in Embodiment 1 of the present invention;

[0051] Figure 1b A schematic diagram of a roadside camera calibration scene effect provided in Embodiment 1 of the present invention;

[0052] Figure 2 A flowchart of a roadside camera calibration method provided in Embodiment 2 of the present invention;

[0053] Figure 3 A structural block diagram of a roadside camera calibration device provided in Embodiment 3 of the present invention;

[0054] Figure 4 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0056] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0057] The embodiments of the present invention disclose a roadside camera calibration system, method, device, equipment and medium, which are described in detail below.

[0058] Embodiment 1

[0059] Figure 1a This is a structural block diagram of a roadside camera calibration system provided in Embodiment 1 of the present invention. Figure 1b A schematic diagram of a roadside camera calibration scene effect provided in the first embodiment of the present invention is shown in FIG. Figure 1a and 1b As shown, the system includes: an edge computing device 110, a target vehicle 120 that is in communication connection with the edge computing device 110, and a camera to be calibrated 130, wherein the edge computing device 110, the target vehicle 120 and the camera to be calibrated 130 are timed by the same timing device, so that information from different data sources is synchronized in time, that is, the time information is on the same time axis.

[0060] In this embodiment, the target vehicle 120 has MEC (Mobile Edge Computing) communication capability. In the calibration field, the target vehicle travels at a constant speed along the lane within the field of view of the roadside camera at a set speed. Each lane can be traveled once. During the driving process, the vehicle tries to stay in the middle of the lane and uploads the vehicle positioning data to the edge computing device in real time. Among them, the positioning data is the first position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle, such as GPS (Global Positioning System) or GNSS (Global Navigation Satellite System) and other high-precision positioning devices. The first position information includes longitude and latitude.

[0061] The camera 130 to be calibrated is configured to collect driving images of the target vehicle 120 and upload the collected image data to the edge computing device 110 .

[0062] The number of cameras to be calibrated may be one or more, which is not specifically limited in this embodiment.

[0063] The edge computing device 110 is configured to obtain the second position information of the target vehicle in the image from the image data based on the detection and tracking algorithm, and establish an association relationship between the first position information and the second position information according to the timestamp as calibration data of the camera to be calibrated.

[0064] Specifically, a detection and tracking algorithm based on deep learning can be deployed on the edge computing device to achieve stable tracking of dynamic targets. Among them, the detection and tracking algorithm may include two parts: target detection and target tracking. Based on the target detection algorithm, the edge computing device can locate the target vehicle in the image. Among them, the target detection algorithm can be specifically implemented through neural network models such as R-CNN (Regions with CNN features, regional convolutional neural network) or Fast R-CNN (fast regional convolutional neural network). After the target vehicle is detected, the target vehicle can be tracked based on the target tracking algorithm. Among them, the target tracking algorithm can be a feature matching method, an optical flow method, or the target vehicle can be tracked by a deep learning-based method such as a convolutional neural network or a recurrent neural network. By detecting and tracking the target vehicle, the two-dimensional position information of the target vehicle in the image can be obtained in real time.

[0065] Furthermore, the edge computing device obtains the calibration data of the camera to be calibrated by establishing an association relationship between the first position information and the second position information. Specifically, the edge computing device can establish an association relationship table between the first position information and the second position information, and then interpolate the first position information in the association relationship table based on the interpolation algorithm to obtain the corresponding second position information. The advantage of such a setting is that the positioning information corresponding to the pixel points of the entire image ground point can be obtained, which improves the accuracy and continuity of the data and provides reliable calibration data for subsequent applications. Among them, for the image data, the second position information includes the horizontal coordinate information and the vertical coordinate information of the image pixel, and the first position information includes the longitude information and the latitude information in the world coordinate system. This embodiment can interpolate the horizontal coordinate information and the vertical coordinate information of the image pixel respectively to obtain the longitude information in the world coordinate system corresponding to the horizontal coordinate information, and the latitude information in the world coordinate system corresponding to the vertical coordinate information.

[0066] The interpolation algorithm includes a linear interpolation algorithm and a nonlinear interpolation algorithm. There are many nonlinear interpolation algorithms, such as Lagrange interpolation, cubic spline interpolation, and an interpolation algorithm based on wavelet transform, etc. This embodiment does not specifically limit this. The interpolation process of the second position information is introduced below.

[0067] If linear interpolation is used, it can be achieved through the following formula:

[0068] x is the pixel point of the vehicle in the image, and y is the high-precision latitude and longitude of the vehicle, where the horizontal coordinate of the pixel point corresponds to the longitude in the map, and the vertical coordinate of the pixel point corresponds to the latitude in the map. The horizontal coordinate of the image pixel point can be converted according to the following formula to obtain the longitude information, and the vertical coordinate can be converted according to the following formula to obtain the latitude information:

[0069]

[0070] In the above formula, when x represents the horizontal coordinate of the image pixel point, the above formula is to obtain the longitude y corresponding to the horizontal coordinate x of the image pixel point in the world coordinate system. 0 , x 1 is the prior data after device alignment, that is, the known horizontal coordinate information, y 0 and yes and x 0 The corresponding longitude information, y 1 is with x 1 Longitude information.

[0071] In the case where x represents the vertical coordinate of the image pixel point, the above formula is to obtain the latitude y corresponding to the vertical coordinate x of the image pixel point in the map. 0 , x 1is the prior data after device alignment, that is, the known ordinate information, y 0 and yes and x 0 Corresponding latitude information, y 1 is with x 1 The latitude information.

[0072] In addition, if the Lagrange interpolation algorithm is used, it can be implemented by the following formula:

[0073]

[0074] Where n represents the number of pixels in the image, k represents the kth pixel, and x represents the horizontal or vertical coordinate corresponding to the unaligned image pixel. k (x) represents the longitude information in the world coordinate system corresponding to the horizontal coordinate; when x represents the vertical coordinate, l k (x) represents the latitude information in the world coordinate system corresponding to the horizontal coordinate.

[0075] x 0 、x k 、x k-1 、x k+1 、x n Both represent the position information of the aligned pixel points, which can be the horizontal coordinate or vertical coordinate of the pixel point. When the above parameters are all horizontal coordinates, the l calculated by the above formula k (x) represents the longitude information of the horizontal coordinate of the pixel point in the image in the world coordinate system; when the above parameters are all horizontal coordinates, the l calculated by the above formula k (x) represents the latitude information of the horizontal coordinate of the pixel point in the image in the world coordinate system.

[0076] It should be noted that, considering that the camera shooting direction is usually along the road surface direction, and the road surface generally does not fluctuate greatly in the tangential direction, the horizontal true scale of the pixel corresponding to the camera can be approximated as a linear system, that is, the horizontal coordinate information in the second position information of the image pixel can be interpolated using a linear interpolation algorithm to obtain the longitude information in the world coordinate system corresponding to the interpolated horizontal coordinate information. Since the road direction has uphill and downhill, the vertical true scale of the pixel is nonlinear. Therefore, the vertical coordinate information in the second position information of the image pixel can be interpolated using a nonlinear interpolation algorithm, such as the Lagrange interpolation algorithm, to obtain the latitude information in the world coordinate system corresponding to the interpolated vertical coordinate information. This setting makes the interpolated first position information and second position information more consistent with the actual situation of the camera shooting, and the interpolation result is more accurate.

[0077] After the above interpolation processing, an association table between the first position information and the second position information can be generated according to the timestamp and based on all the first position information and the corresponding second position information before and after the interpolation. The association table can cover all pixels in the image, thereby improving the comprehensiveness and accuracy of the data. In the subsequent application of the roadside camera, the high-precision position information of the vehicle in the world coordinate system can be obtained based on the vehicle position information in the image captured by the roadside camera.

[0078] Furthermore, according to the position information of all other target objects in the image and based on the obtained association relationship, the image position information can be converted into position information based on the world coordinate system.

[0079] In the calibration process of the roadside camera in this embodiment, by using a vehicle with high-precision positioning and MEC communication capabilities as the shooting object of the camera to be calibrated, the reliability and accuracy of the vehicle position data are ensured. By using the detection and tracking algorithm of the edge computing device, the 2D position information of the target vehicle in the image can be quickly and accurately extracted. This real-time image processing enables the vehicle to perceive obstacles, signs and other vehicles on the road in real time, providing timely visual feedback for the autonomous driving system. In addition, by establishing the association between the 2D image position of the vehicle and the real-time high-precision positioning position of the vehicle, the precise relationship between the 2D image coordinates of the vehicle and the world coordinates can be obtained, providing a solid foundation for subsequent data processing and application. In addition, by using the interpolation algorithm to implement data interpolation, the continuity and accuracy of the data are further improved, and the consistency of the above-mentioned association in time and space is ensured, thereby providing reliable calibration data for various applications. In addition, the calibration system of the roadside camera provided in this embodiment can process and communicate in real time, ensuring the timely transmission and application of data, and is suitable for multiple fields such as autonomous driving, traffic management and intelligent transportation systems, providing reliable technical support for vehicle perception and navigation, and helping to improve road safety and traffic efficiency.

[0080] Embodiment 2

[0081] Figure 2 This is a flow chart of a roadside camera calibration method provided in the second embodiment of the present invention. The method provided in this embodiment can be applied to the application scenario of real-time calibration of roadside cameras. The method provided in this embodiment can be executed by an edge computing device, which can be implemented by software and / or hardware, for example, a cloud server. Figure 2 As shown, the method provided in this embodiment specifically includes:

[0082] S210, receiving first position information uploaded by the target vehicle, and receiving image data containing the target vehicle sent by the camera to be calibrated.

[0083] Among them, the target vehicle, the camera to be calibrated and the current edge computing device are synchronized by the same timing device, so that the information from different data sources is synchronized in time. The first position information is the position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle.

[0084] S220: Acquire second position information of the target vehicle in the image from the image data.

[0085] S230: Establish an association relationship between the first position information and the second position information according to the timestamp, and use the association relationship as calibration data of the camera to be calibrated.

[0086] Exemplarily, an association relationship table between the first position information and the second position information may be generated, and then the first position information and the corresponding second position information in the association relationship table may be interpolated based on an interpolation algorithm to obtain an interpolated association relationship table.

[0087] Optionally, different interpolation algorithms may be used for the horizontal pixels and the vertical pixels in the image, so that the interpolated data can cover all pixels or even sub-pixels in the image, thereby improving the continuity and accuracy of the data. For example, an interpolation operation is performed on the second position information of the image data located in the horizontal pixels, and based on the Lagrange interpolation algorithm, an interpolation operation is performed on the second position information of the image data located in the vertical pixels. Then, all the second position information before and after the interpolation process and its corresponding first position information are used to form an association relationship table between the first position information and the second position information.

[0088] Furthermore, after the association relationship is established, the position information of other target objects other than the target vehicle in the image data can be obtained, and based on the established association relationship, the position information can be converted into position information based on the world coordinate system.

[0089] In this embodiment, the specific implementation of steps S210-S230 can refer to the description of the above embodiment and will not be repeated here.

[0090] The technical solution provided in this embodiment can quickly and accurately extract the 2D position information of the target vehicle in the image by using the detection and tracking algorithm of the edge computing device. By establishing the correlation between the 2D image position of the vehicle and the real-time high-precision positioning position of the vehicle, the precise relationship between the 2D image coordinates of the vehicle and the world coordinates can be obtained, which provides a solid foundation for subsequent data processing and application. In addition, by using the interpolation algorithm to implement data interpolation, the continuity and accuracy of the data are further improved, ensuring that the above-mentioned correlation is consistent in time and space, and providing reliable calibration data for various applications. In addition, the calibration system of the roadside camera provided in this embodiment can process and communicate in real time, ensuring the timely transmission and application of data, and is suitable for multiple fields such as autonomous driving, traffic management and intelligent transportation systems. It provides reliable technical support for vehicle perception and navigation, and helps to improve road safety and traffic efficiency. Compared with the offline calibration and manual calibration methods in related technologies, the roadside camera calibration solution provided in this embodiment is more efficient and safer.

[0091] Embodiment 3

[0092] Figure 3 A structural block diagram of a roadside camera calibration device provided in Embodiment 2 of the present invention, such as Figure 3 As shown, the device includes: a first location information receiving module 310, a second location information determining module 320 and an association relationship establishing module 330, wherein:

[0093] The first position information receiving module 310 is configured to receive the first position information uploaded by the target vehicle, and receive the image data containing the target vehicle sent by the camera to be calibrated, wherein the target vehicle, the camera to be calibrated and the current edge computing device are timed by the same timing device, and the first position information is the position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle;

[0094] The second position information determination module 320 is configured to obtain the second position information of the target vehicle in the image from the image data;

[0095] The association relationship establishing module 330 is configured to establish an association relationship between the first position information and the second position information according to the timestamp, and use the association relationship as calibration data of the camera to be calibrated.

[0096] Optionally, the association relationship establishment module is specifically configured as follows:

[0097] Generate an association relationship table between the first location information and the second location information according to the timestamp;

[0098] Accordingly, the device provided by the embodiment of the present invention further includes:

[0099] An interpolation module is configured to perform interpolation processing on the second position information in the association relationship based on an interpolation algorithm to obtain first position information corresponding to the interpolated second position information;

[0100] Correspondingly, the association relationship establishment module is specifically configured as follows:

[0101] According to the timestamp, and based on all the first position information and the corresponding second position information before and after the interpolation, an association relationship table between the first position information and the second position information is generated.

[0102] Optionally, the second position information includes horizontal coordinate information and vertical coordinate information of the image pixel, and the first position information includes longitude information and latitude information in a world coordinate system;

[0103] Correspondingly, the interpolation module is specifically configured as follows:

[0104] Based on a linear interpolation algorithm, an interpolation operation is performed on the horizontal coordinate information in the second position information to obtain longitude information in a world coordinate system corresponding to the interpolated horizontal coordinate information; and

[0105] Based on the Lagrange interpolation algorithm, an interpolation operation is performed on the ordinate information in the second position information to obtain latitude information in the world coordinate system corresponding to the interpolated ordinate information.

[0106] Optionally, the device provided by the embodiment of the present invention further includes:

[0107] The position determination module is configured to obtain the position information of other target objects in the image data other than the target vehicle in the image, and based on the association relationship, convert the position information in the image into position information based on the world coordinate system.

[0108] The roadside camera calibration device provided in the embodiment of the present invention can execute the roadside camera calibration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in the above embodiment, please refer to the roadside camera calibration method provided in any embodiment of the present invention.

[0109] Embodiment 3

[0110] Figure 4 A structural block diagram of a computer device provided in Embodiment 4 of the present invention, such as Figure 4 As shown, the computer device includes:

[0111] At least one processor ( Figure 4 A processor 520 is shown,

[0112] The processor 520 is coupled to the memory 510 , and the memory 510 stores a program or instruction running on the processor 520 . When the program or instruction is executed by the processor 520 , the calibration method of the roadside camera provided in any embodiment of the present invention is implemented.

[0113] Based on the above method embodiments, another embodiment of the present invention provides a readable storage medium having a program or instruction stored thereon, which, when executed by a processor, enables the processor to implement the roadside camera calibration method as described in any of the above embodiments.

[0114] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0115] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0116] 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 roadside camera calibration system, characterized in that: include: an edge computing device, a target vehicle and a camera to be calibrated that are in communication connection with the edge computing device, wherein the target vehicle, the camera to be calibrated, and the edge computing device are timed by the same timing device, The target vehicle is configured to travel in the calibration field and upload the positioning data of the current target vehicle to the edge computing device, wherein the positioning data is the first position information of the target vehicle in the world coordinate system obtained by the positioning sensor on the target vehicle; The camera to be calibrated is configured to collect driving images of the target vehicle and upload the collected image data to the edge computing device; The edge computing device is configured to obtain second position information of the target vehicle in the image from the image data, establish an association relationship between the first position information and the second position information according to a timestamp, and use the association relationship as calibration data of the camera to be calibrated.

2. The system according to claim 1, characterized in that The edge computing device is specifically configured as: Acquire the position information of other target objects other than the target vehicle in the image data to be measured in the image; Based on the association relationship, the position information to be measured is converted into position information based on the world coordinate system.

3. A roadside camera calibration method, applied to edge computing equipment, characterized in that: include: Receive first position information uploaded by a target vehicle, and receive image data containing the target vehicle sent by a camera to be calibrated, wherein the target vehicle, the camera to be calibrated and the current edge computing device are timed by the same timing device, and the first position information is the position information of the target vehicle in the world coordinate system obtained by a positioning sensor on the target vehicle; Acquire second position information of the target vehicle in the image from the image data; An association relationship is established between the first position information and the second position information according to the timestamp, and the association relationship is used as calibration data of the camera to be calibrated.

4. The method according to claim 3, characterized in that: The method further comprises: Based on the interpolation algorithm, interpolation processing is performed on the second position information in the association relationship to obtain the first position information corresponding to the interpolated second position information; Correspondingly, generating an association relationship between the first location information and the second location information according to the timestamp includes: According to the timestamp, and based on all the first position information and the corresponding second position information before and after the interpolation, an association relationship table between the first position information and the second position information is generated.

5. The method according to claim 4, characterized in that The second position information includes horizontal coordinate information and vertical coordinate information of the image pixel, and the first position information includes longitude information and latitude information in a world coordinate system; Correspondingly, the interpolation processing is performed on the second position information in the association relationship based on the interpolation algorithm, including: Based on a linear interpolation algorithm, an interpolation operation is performed on the horizontal coordinate information in the second position information to obtain longitude information in a world coordinate system corresponding to the interpolated horizontal coordinate information; and Based on the Lagrange interpolation algorithm, an interpolation operation is performed on the ordinate information in the second position information to obtain latitude information in a world coordinate system corresponding to the interpolated ordinate information.

6. The method according to any one of claims 3 to 5, characterized in that: After establishing the association relationship, the method further includes: Acquire position information of other target objects in the image data other than the target vehicle in the image; Based on the association relationship, the position information in the image is converted into position information based on the world coordinate system.

7. A roadside camera calibration device, characterized in that: include: A first position information receiving module is configured to receive first position information uploaded by a target vehicle, and receive image data containing the target vehicle sent by a camera to be calibrated, wherein the target vehicle, the camera to be calibrated and the current edge computing device are timed by the same timing device, and the first position information is the position information of the target vehicle in the world coordinate system obtained by a positioning sensor on the target vehicle; A second position information determination module is configured to obtain second position information of the target vehicle in the image from the image data; The association relationship establishing module is configured to establish an association relationship between the first position information and the second position information according to the timestamp, and use the association relationship as calibration data of the camera to be calibrated.

8. The device according to claim 7, characterized in that The device also includes: an interpolation module configured to perform interpolation processing on the second position information in the association relationship based on an interpolation algorithm to obtain first position information corresponding to the interpolated second position information; Accordingly, the association relationship establishing module is specifically configured as follows: According to the timestamp, and based on all the first position information and the corresponding second position information before and after the interpolation, an association relationship table between the first position information and the second position information is generated.

9. A computer device, characterized in that: The method comprises at least one processor, the processor is coupled to a memory, the memory stores a program or instruction running on the processor, and when the program or instruction is executed by the processor, the steps of the roadside camera calibration method as described in any one of claims 3 to 6 are implemented.

10. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps of the roadside camera calibration method as described in any one of claims 3 to 6 are implemented.

Images