Offset determination method and device, positioning compensation method and device, electronic equipment and storage medium
By acquiring and aligning typical route information and RTK data in the camera field of view, and calculating the vehicle positioning offset, the problem of inaccurate 3D coordinates of the roadside camera vehicle is solved, and the compensation of positioning errors and improvement of accuracy is achieved.
Patent Information
- Application Number
- CN202411415690.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-11
- Publication Date
- 2024-12-06
AI Technical Summary
When using roadside cameras for 2D perceived positioning, the 3D coordinates of the vehicle are inaccurate, resulting in inconsistent positioning of the same vehicle perceived by multiple cameras, which poses challenges to fusion and digital twins. There is an error in positioning of the 2D vehicle detection frame, which requires Reduce this error.
By obtaining multiple typical route information in the camera field of view, using a true value car to drive along typical routes in the camera field of view, and aligning the video image with the RTK data frame, extracting pixel driving trajectory and RTK data information, determining the initial 3D coordinates, and calculating Position the offset, make an offset compensation table for positioning compensation of the target vehicle.
It effectively reduces the errors in positioning of the 2D vehicle detection frame, improves the accuracy of the vehicle positioning, and enhances the accuracy of the vehicle track rectangular detection frame.
Smart Images

Figure CN119087483A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of error correction, and in particular to an offset determination method, a positioning compensation method, a device, an electronic device, and a storage medium. Background Art
[0002] The roadside camera can be used to perform 2D perception and positioning of the perceived vehicle in the captured image and convert it into 3D coordinates.
[0003] In scenario 1, Figure 1 As shown in the figure, when the 3D coordinates of the vehicle perceived and positioned by the roadside camera are inaccurate, the same vehicle perceived by multiple cameras will not be in the same position (the positions of the two vehicles displayed), which will bring great challenges to fusion and digital twins. In scenario 2, Figure 2 As shown in the figure, the black box is a schematic diagram of the detected rectangular box, where point A is the grounding point of the currently selected representative vehicle, and point B is the ideal grounding point, and there is an error between the two. In addition, the lines represent typical driving trajectories.
[0004] For the above scenario, the vehicle position located by the current 2D vehicle detection frame has errors, and this error needs to be reduced. Summary of the invention
[0005] The embodiments of the present application provide an offset determination method, a positioning compensation method, a device, an electronic device, and a storage medium to determine the offset and implement positioning compensation.
[0006] The present application embodiment adopts the following technical solutions:
[0007] In a first aspect, an embodiment of the present application provides a method for determining an offset, wherein the method comprises:
[0008] Get information about multiple typical routes in the camera's field of view;
[0009] Based on each piece of typical route information, a true value vehicle is used to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the true value vehicle, wherein the true value vehicle at least includes an RTK module, and the true value vehicle is further used to output a timestamp and its own 3D coordinates corresponding to the timestamp;
[0010] Extracting a pixel driving trajectory of the true value vehicle in the image according to the video image, and determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory;
[0011] The positioning offset is determined according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0012] In some embodiments, the method further comprises:
[0013] Subtract the 3D coordinates in the RTK data information corresponding to each frame in the trajectory from the initial 3D coordinates to obtain the positioning offset;
[0014] For the entire driving trajectory, the positioning offset, the heading angle in the RTK data information corresponding to each frame in the trajectory, and the 2D coordinates of the true value vehicle in the pixel driving trajectory in the image are recorded and extracted from the video image, and saved as a set of data in the current typical route information.
[0015] In some embodiments, the method further comprises:
[0016] Traverse each typical route and make an offset compensation table.
[0017] In some embodiments, the offset compensation table further includes the following optimization steps:
[0018] For different vehicle models, the corresponding true value vehicle is selected and the offset compensation table for the different vehicle models is prepared.
[0019] In some embodiments, the camera includes a roadside camera, and obtaining information of a plurality of typical routes in the camera field of view includes:
[0020] Counting the vehicle driving trajectories that can be identified within the field of view of the roadside camera over a period of time;
[0021] Removing repeated or similar trajectories from the vehicle driving trajectory;
[0022] The plurality of typical route information within the field of view of the roadside camera is extracted.
[0023] In some embodiments, determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory includes:
[0024] Extract the pixel driving trajectory of the real value car in the video and search it in the pre-saved 2D-3D relationship conversion table to obtain the trajectory composed of the corresponding initial 3D coordinates;
[0025] Record the true 3D coordinates and heading angles contained in the RTK output information corresponding to each frame in the trajectory.
[0026] In a second aspect, an embodiment of the present application further provides a positioning compensation method, which is applied to the offset determination method described in the first aspect, and the positioning compensation method includes:
[0027] Determine the target vehicle to be processed;
[0028] According to the target vehicle, obtaining the model of the target vehicle and initial 2D trajectory information composed of continuous frames;
[0029] According to the initial 2D trajectory information and the vehicle type, determining which typical route information it belongs to;
[0030] According to the typical route information to which the initial 2D trajectory information belongs, and according to the 2D coordinates and heading angle of each frame in the initial 2D trajectory information, a current positioning offset is obtained;
[0031] The initial 3D coordinates corresponding to the initial 2D coordinates are compensated according to the current positioning offset to obtain compensated 3D point coordinates.
[0032] In a third aspect, an embodiment of the present application further provides an offset determination device, wherein the device comprises:
[0033] An acquisition module is used to obtain information of multiple typical routes in the camera's field of view;
[0034] A truth module, used for, based on each piece of typical route information, using a truth vehicle to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the truth vehicle, wherein the truth vehicle at least includes an RTK module, and the truth vehicle is further used for outputting a timestamp and its own 3D coordinates corresponding to the timestamp;
[0035] An extraction and determination module, configured to extract a pixel driving trajectory of the true value vehicle in the image according to the video image, and determine a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory;
[0036] The offset determination module is used to determine the positioning offset according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0037] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.
[0038] In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.
[0039] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: obtaining multiple typical route information in the camera field of view, and then based on each of the typical route information, using a true value vehicle to travel along the typical route in the camera field of view and obtain the video image of the camera. The image frame in the video image is aligned with the RTK data frame of the true value vehicle, and the true value vehicle at least includes an RTK module, and the true value vehicle is also used to output a timestamp and its own 3D coordinates corresponding to the timestamp. Further, the pixel driving trajectory of the true value vehicle in the image is extracted according to the video image, and the trajectory composed of the initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory are determined according to the pixel driving trajectory. Finally, the positioning offset is determined according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates. Through the above method, the offset can be determined, and positioning compensation can be achieved, thereby reducing the error in the positioning of the traditional 2D vehicle detection frame. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0041] Figure 1 This is a schematic diagram of digital twins in related technologies;
[0042] Figure 2 This is a schematic diagram of a roadside camera sensing a vehicle in the related art;
[0043] Figure 3 A schematic diagram of a method for determining an offset in an embodiment of the present application;
[0044] Figure 4 A schematic diagram of a positioning compensation method in an embodiment of the present application;
[0045] Figure 5 This is a schematic diagram of the structure of the offset determination device in an embodiment of the present application;
[0046] Figure 6 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0048] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0049] The present application embodiment provides a method for determining an offset, such as Figure 3 As shown, a schematic flow chart of a method for determining an offset in an embodiment of the present application is provided, and the method at least includes the following steps S310 to S340:
[0050] Step S310, obtaining information of multiple typical routes in the camera field of view.
[0051] When a camera is deployed at an intersection, the camera needs to be calibrated or jointly calibrated, and can capture and obtain image information. The camera field of view can be selected according to the actual situation of the intersection.
[0052] "Multiple typical route information" needs to cover all common driving routes in intersection scenarios as much as possible, such as Figure 2 As shown, the lines in “multiple typical route information” are used to represent the vehicle driving trajectory.
[0053] Step S320: Based on each piece of typical route information, a true value vehicle is used to travel along the typical route information within the camera field of view and obtain a video image of the camera, and the image frame in the video image is aligned with the RTK data frame of the true value vehicle. The true value vehicle includes at least an RTK module, and the true value vehicle is also used to output a timestamp and its own 3D coordinates corresponding to the timestamp.
[0054] Based on each of the typical route information, a true value car needs to be used to travel along the route trajectory within the camera field of view. It can be understood that the "true value car" can be a true value car that can output a timestamp and its own 3D coordinates. Its own 3D coordinates refer to the position coordinates of the true value car in the world coordinate system in the real scene. It should be noted that the "true value car" includes at least an RTK module, and through the RTK module, the true value car can output a timestamp and its own 3D coordinates corresponding to the timestamp. In addition, the RTK module can also output the heading angle information YAW corresponding to the timestamp.
[0055] It should be noted that the image frames in the video image need to be aligned with the RTK data frames of the ground truth vehicle, that is, the video and RTK data are extracted at the same time, and the video frames and RTK data frames are aligned.
[0056] Step S330: extracting a pixel driving trajectory of the true value vehicle in the image according to the video image, and determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory.
[0057] Then, the pixel driving trajectory of the true value vehicle in the image is extracted according to the video image, and the trajectory composed of the initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory are determined according to the pixel driving trajectory. In other words, by extracting the pixel driving trajectory of the true value vehicle in the video, the trajectory composed of the 3D coordinates before optimization corresponding to the 2D pixel coordinates can be obtained, and the RTK output information corresponding to each frame in the trajectory is recorded, including the true value 3D coordinates and the heading angle.
[0058] Step S340: determining a positioning offset according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0059] The RTK data information corresponding to each frame in the trajectory contains 3D coordinate information. The positioning offset can be determined based on the initial 3D coordinates and the 3D coordinate information contained in the RTK data information.
[0060] Through the above method, the problem of excessive error caused by the vehicle trajectory rectangular detection frame can be effectively solved by determining the positioning offset in the scene.
[0061] Different from the related art, the commonly used method is: sense and output the rectangular frame of the target vehicle in the current frame image, select the center point of the lower edge of the rectangular frame as the vehicle grounding point, and find the corresponding 3D coordinates through the pixel value of the point. However, in many cases, the lower center of the detection frame cannot accurately describe the vehicle grounding point, because no matter what the current posture of the vehicle in the field of view is, the rectangular frame only focuses on the outermost edge of the vehicle. Through the above method, a different driving route is pre-made, and the offset corresponding to different vehicle postures is compensated.
[0062] In one embodiment of the present application, the method also includes: subtracting the 3D coordinates in the RTK data information corresponding to each frame in the trajectory from the initial 3D coordinates to obtain the positioning offset; for the entire driving trajectory, recording the positioning offset, the heading angle in the RTK data information corresponding to each frame in the trajectory, and the video image to extract the 2D coordinates of the pixel driving trajectory of the true value vehicle in the image, and saving them as a set of data in the current typical route information.
[0063] The initial 3D coordinates are subtracted from the 3D coordinates in the RTK data information corresponding to each frame in the trajectory to finally obtain the positioning offset. At the same time, the following are recorded in the entire trajectory: the 2D coordinates in the pixel driving trajectory (2D coordinates before optimization), the currently calculated offset, and the heading angle output by RTK.
[0064] In one embodiment of the present application, the method further includes: traversing each typical route to generate an offset compensation table.
[0065] For multiple typical route information, the offset compensation table is created by traversing each track. The offset compensation table records each typical route information, and the typical route information includes the 2D coordinates in the pixel driving track (2D coordinates before optimization), the currently calculated offset, and the heading angle output by RTK.
[0066] In one embodiment of the present application, the offset compensation table further includes the following optimization steps: for different vehicle models, corresponding true value vehicles are selected and the offset compensation tables for different vehicle models are prepared.
[0067] Since different models require different true value vehicles to improve accuracy, for different models such as cars, trucks, vans, etc., select the corresponding true value vehicles and make offset compensation tables for different models. The offset compensation tables for different models can be selected according to the model, thereby improving the accuracy of positioning compensation.
[0068] In one embodiment of the present application, the camera includes a roadside camera, and the obtaining of multiple typical route information in the camera's field of view includes: counting recognizable vehicle driving trajectories within the field of view of the roadside camera over a period of time; removing repeated or approximate trajectories from the vehicle driving trajectories; and extracting the multiple typical route information within the field of view of the roadside camera.
[0069] Count and extract the typical routes of the current camera field of view, count all the identifiable vehicle driving trajectories in the field of view within a period of time, and remove repeated or close trajectories, such as trajectories of the same lane at different times. Finally, extract multiple typical routes in the field of view, so as to cover all the regular driving routes of the scene as much as possible as multiple typical route information.
[0070] In one embodiment of the present application, determining the trajectory composed of initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory based on the pixel driving trajectory includes: extracting the pixel driving trajectory of the true value vehicle in the video and searching in a pre-saved 2D-3D relationship conversion table to obtain the trajectory composed of the corresponding initial 3D coordinates; recording the true value 3D coordinates and heading angle contained in the RTK output information corresponding to each frame in the trajectory.
[0071] Extract the pixel driving trajectory of the real value vehicle in the video and find the corresponding trajectory composed of 3D coordinates before optimization in the pre-saved 2D-3D relationship conversion table. And record the RTK output information corresponding to each frame in the trajectory, including the real value 3D coordinates and heading angle.
[0072] like Figure 4As shown, in an embodiment of the present application, a positioning compensation method is also provided, wherein the positioning compensation method is applied to the offset determination method, and the positioning compensation method includes:
[0073] Step S410, determining the target vehicle to be processed.
[0074] Step S420: acquiring the model of the target vehicle and initial 2D trajectory information consisting of continuous frames according to the target vehicle.
[0075] Step S430: Determine which typical route information the vehicle belongs to based on the initial 2D trajectory information and the vehicle model.
[0076] For the current target vehicle, the initial 2D trajectory consisting of its vehicle model and continuous frames is obtained, and it is determined which typical trajectory in the corresponding vehicle model compensation table the trajectory belongs to.
[0077] Step S440 , obtaining a current positioning offset according to the typical route information to which the initial 2D trajectory information belongs and the 2D coordinates and heading angle of each frame in the initial 2D trajectory information.
[0078] Step S450: Compensate the initial 3D coordinates corresponding to the initial 2D coordinates according to the current positioning offset to obtain compensated 3D point coordinates.
[0079] The 2D coordinates and heading angles of each frame are looked up in a table to obtain the offset, and the preliminary 3D points corresponding to the 2D points are compensated to obtain the compensated 3D points. The table lookup compensation method is used to solve the error caused by inaccurate positioning of the rectangular frame.
[0080] Through the above method, the problem of excessive error caused by the rectangular detection frame of the vehicle trajectory can be effectively solved in scenario 2.
[0081] The present application also provides an offset determination device 500, such as Figure 5 As shown, a schematic diagram of the structure of an offset determination device in an embodiment of the present application is provided, wherein the offset determination device 500 at least includes: an acquisition module 510, a truth value module 520, an extraction and determination module 530, and an offset determination module 540, wherein:
[0082] In one embodiment of the present application, the acquisition module 510 is specifically used to: acquire information of multiple typical routes in the camera field of view.
[0083] When the camera is deployed at the intersection, it is calibrated and can capture and obtain image information. The camera field of view can be selected according to the actual situation of the intersection.
[0084] "Multiple typical route information" needs to cover all common driving routes in intersection scenarios as much as possible, such as Figure 2 As shown, the lines in “multiple typical route information” are used to represent the vehicle driving trajectory.
[0085] In one embodiment of the present application, the truth value module 520 is specifically used to: based on each piece of the typical route information, use a truth value vehicle to travel along the typical route within the camera field of view and obtain the video image of the camera, the image frame in the video image is aligned with the RTK data frame of the truth value vehicle, the truth value vehicle includes at least an RTK module, and the truth value vehicle is also used to output a timestamp and its own 3D coordinates corresponding to the timestamp.
[0086] Based on each of the typical route information, a true value car needs to be used to travel along the route trajectory within the camera field of view. It can be understood that the "true value car" can be a true value car that can output a timestamp and its own 3D coordinates. Its own 3D coordinates refer to the position coordinates of the true value car in the world coordinate system in the real scene. It should be noted that the "true value car" includes at least an RTK module, and through the RTK module, the true value car can output a timestamp and its own 3D coordinates corresponding to the timestamp. In addition, the RTK module can also output the heading angle information corresponding to the timestamp.
[0087] It should be noted that the image frames in the video image need to be aligned with the RTK data frames of the ground truth vehicle, that is, the video and RTK data are extracted at the same time, and the video and RTK data frames are aligned.
[0088] In one embodiment of the present application, the extraction and determination module 530 is specifically used to: extract the pixel driving trajectory of the true value vehicle in the image according to the video image, and determine the trajectory composed of initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory.
[0089] Then, the pixel driving trajectory of the true value vehicle in the image is extracted according to the video image, and the trajectory composed of the initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory are determined according to the pixel driving trajectory. In other words, by extracting the pixel driving trajectory of the true value vehicle in the video and searching in the pre-saved 2D-3D relationship conversion table, the trajectory composed of the 3D coordinates before optimization corresponding to the 2D pixel coordinates is obtained, and the RTK output information corresponding to each frame in the trajectory is recorded, including the true value 3D coordinates and the heading angle.
[0090] In one embodiment of the present application, the offset determination module 540 is specifically used to determine the positioning offset according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0091] The RTK data information corresponding to each frame in the trajectory contains 3D coordinate information. The positioning offset can be determined based on the initial 3D coordinates and the 3D coordinate information contained in the RTK data information.
[0092] It can be understood that the above-mentioned offset determination device can implement each step of the offset determination method provided in the above-mentioned embodiment, and the relevant explanations about the offset determination method are applicable to the offset determination device, which will not be repeated here.
[0093] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0094] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0095] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0096] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an offset determination device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0097] Get information about multiple typical routes in the camera's field of view;
[0098] Based on each piece of typical route information, a true value vehicle is used to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the true value vehicle, wherein the true value vehicle at least includes an RTK module, and the true value vehicle is further used to output a timestamp and its own 3D coordinates corresponding to the timestamp;
[0099] Extracting a pixel driving trajectory of the true value vehicle in the image according to the video image, and determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory;
[0100] The positioning offset is determined according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0101] The above application Figure 3 The method performed by the offset determination device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0102] The electronic device may also perform Figure 3 The method is performed by the offset determination device in the embodiment of the present invention, and the offset determination device is implemented in the embodiment of the present invention. Figure 3The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0103] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 3 The method performed by the offset determination device in the illustrated embodiment is specifically used to perform:
[0104] Get information about multiple typical routes in the camera's field of view;
[0105] Based on each piece of typical route information, a true value vehicle is used to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the true value vehicle, wherein the true value vehicle at least includes an RTK module, and the true value vehicle is further used to output a timestamp and its own 3D coordinates corresponding to the timestamp;
[0106] Extracting a pixel driving trajectory of the true value vehicle in the image according to the video image, and determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory;
[0107] The positioning offset is determined according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0110] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0112] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0113] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0114] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0115] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0116] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0117] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for determining an offset, wherein: The method comprises: Get information about multiple typical routes in the camera's field of view; Based on each piece of typical route information, a true value vehicle is used to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the true value vehicle, wherein the true value vehicle at least includes an RTK module, and the true value vehicle is further used to output a timestamp and its own 3D coordinates corresponding to the timestamp; Extracting a pixel driving trajectory of the true value vehicle in the image according to the video image, and determining a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory; The positioning offset is determined according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
2. The method of claim 1, wherein: The method further comprises: Subtract the 3D coordinates in the RTK data information corresponding to each frame in the trajectory from the initial 3D coordinates to obtain the positioning offset; For the entire driving trajectory, the positioning offset, the heading angle in the RTK data information corresponding to each frame in the trajectory, and the 2D coordinates of the true value vehicle in the pixel driving trajectory in the image are recorded and extracted from the video image, and saved as a set of data in the current typical route information.
3. The method of claim 2, wherein: The method further comprises: Traverse each typical route and make an offset compensation table.
4. The method of claim 3, wherein: The offset compensation table also includes the following optimization steps: For different vehicle models, the corresponding true value vehicle is selected and the offset compensation table for the different vehicle models is prepared.
5. The method of claim 1, wherein: The camera includes a roadside camera, and the acquiring of a plurality of typical route information in the camera field of view includes: Counting the vehicle driving trajectories that can be identified within the field of view of the roadside camera over a period of time; Removing repeated or similar trajectories from the vehicle driving trajectory; The plurality of typical route information within the field of view of the roadside camera is extracted.
6. The method of claim 1, wherein: The determining of the trajectory composed of the initial 3D coordinates and the RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory includes: Extract the pixel driving trajectory of the real value car in the video and search it in the pre-saved 2D-3D relationship conversion table to obtain the trajectory composed of the corresponding initial 3D coordinates; Record the true 3D coordinates and heading angles contained in the RTK output information corresponding to each frame in the trajectory.
7. A positioning compensation method, wherein: Applied to the offset determination method according to any one of claims 1 to 6, the positioning compensation method comprises: Determine the target vehicle to be processed; According to the target vehicle, obtaining the model of the target vehicle and initial 2D trajectory information composed of continuous frames; According to the initial 2D trajectory information and the vehicle type, determining which typical route information it belongs to; According to the typical route information to which the initial 2D trajectory information belongs, and according to the 2D coordinates and heading angle of each frame in the initial 2D trajectory information, a current positioning offset is obtained; The initial 3D coordinates corresponding to the initial 2D coordinates are compensated according to the current positioning offset to obtain compensated 3D point coordinates.
8. An offset determination device, wherein: The device comprises: An acquisition module is used to obtain information of multiple typical routes in the camera's field of view; A truth module, used for, based on each piece of typical route information, using a truth vehicle to drive along the typical route within a camera field of view and obtain a video image of the camera, wherein an image frame in the video image is aligned with an RTK data frame of the truth vehicle, wherein the truth vehicle at least includes an RTK module, and the truth vehicle is further used for outputting a timestamp and its own 3D coordinates corresponding to the timestamp; An extraction and determination module, configured to extract a pixel driving trajectory of the true value vehicle in the image according to the video image, and determine a trajectory composed of initial 3D coordinates and RTK data information corresponding to each frame in the trajectory according to the pixel driving trajectory; The offset determination module is used to determine the positioning offset according to the 3D coordinates in the RTK data information corresponding to each frame in the trajectory and the initial 3D coordinates.
9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.
10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.
