Vehicle track information acquisition method, vehicle track information acquisition equipment and medium

Abstract

The invention discloses a vehicle track information obtaining method, vehicle track information obtaining equipment and a medium, and relates to the technical field of vehicle positioning, and the vehicle track information obtaining method comprises the steps that when a vehicle enters a signal positioning blind area, world coordinates of the vehicle in a world coordinate system are determined according to a camera device at the current position; determining track information of the vehicle based on the world coordinates, and outputting the track information to navigation equipment corresponding to the vehicle; and when the vehicle enters the shooting area of the next camera device, updating the track information based on the coordinate information shot by the next camera device. After the vehicle enters the signal positioning blind area, the real-time world coordinate information of the vehicle is obtained, the vehicle track information is generated, and finally the track information is output to the navigation equipment, so that the driving safety is improved, the track information is updated in real time, and the accuracy of the track information is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle positioning technology, and in particular to a vehicle trajectory information acquisition method, a vehicle trajectory information acquisition device and a medium. Background Art

[0002] Traditional global positioning systems are prone to losing satellite signals in one or all directions in complex urban road conditions, such as tunnels, viaducts, and tree-lined roads, causing basic vehicle positioning to deviate or even be lost, which poses a huge safety hazard to vehicle navigation and reduces driving safety.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a vehicle trajectory information acquisition method, a vehicle trajectory information acquisition device and a medium, aiming to solve the technical problem that when the vehicle is in a signal positioning blind spot, the lack of positioning leads to reduced driving safety.

[0005] To achieve the above objectives, the present application proposes a method for obtaining vehicle trajectory information, the method comprising: When the vehicle enters a signal positioning blind area, determining the world coordinates of the vehicle in a world coordinate system according to the camera device at the current position; Determining trajectory information of the vehicle based on the world coordinates, and outputting the trajectory information to a navigation device corresponding to the vehicle; When the vehicle enters a shooting area of ​​a next camera device, the trajectory information is updated based on coordinate information shot by the next camera device.

[0006] In one embodiment, before the step of determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position when the vehicle enters the signal positioning blind area, the step further includes: Acquire initial calibration information of an initial camera device in the signal positioning blind area, and determine a mapping relationship between camera coordinates and world coordinates in the initial camera device based on the initial calibration information and camera device internal reference information; Based on the mapping relationship and the calibration information corresponding to each of the other continuous camera devices, the world coordinate system synchronous calibration processing is performed on the other camera devices.

[0007] In one embodiment, the step of performing synchronous calibration processing of the world coordinate system on other camera devices based on the mapping relationship and the calibration information corresponding to each of the other consecutive camera devices includes: Obtaining the camera coordinates and the calibrated world coordinates of the calibration object captured in the repeated images of the calibrated camera device and the next uncalibrated camera device; Based on the calibrated world coordinates, the camera coordinates and the mapping relationship, performing a world coordinate system synchronous calibration process on the next uncalibrated camera device; When the next uncalibrated camera device is not the last camera device, based on the currently calibrated camera device, jump to execute the step of obtaining the position information of the calibration object captured in the repeated pictures of the calibrated camera device and the next uncalibrated camera device, and determining the calibrated world coordinates of the calibration object.

[0008] In one embodiment, when the vehicle enters a signal positioning blind spot, the step of determining the world coordinates of the vehicle in a world coordinate system according to a camera device at a current position includes: When it is detected that the vehicle enters the signal positioning blind area, the camera device identifies boundary information of the vehicle based on a target detection algorithm; Determine the pixel coordinates of the center point of the vehicle in each frame of the camera device according to the boundary information; The pixel coordinates are converted to the world coordinates.

[0009] In one embodiment, after the step of updating the trajectory information based on the coordinate information captured by the next camera device when the vehicle enters the capturing area of ​​the next camera device, the step further includes: When it is detected that the vehicle leaves the signal positioning blind area, obtaining the target world coordinates captured by each continuous camera device in the signal positioning blind area; Generate a plurality of to-be-processed trajectory information corresponding to each of the continuous camera devices based on the target world coordinates; The to-be-processed trajectory information is deduplicated to obtain a target trajectory, and the target trajectory is output to a monitoring system corresponding to the vehicle.

[0010] In one embodiment, the step of determining the trajectory information of the vehicle based on the world coordinates and outputting the trajectory information to a navigation device corresponding to the vehicle includes: Determine the world coordinates of the vehicle in each video frame of the camera device when the vehicle is in the shooting area of ​​the camera device; Based on the world coordinates of each frame, the trajectory information of the vehicle is generated, and the trajectory information is output to the navigation device corresponding to the vehicle.

[0011] In one embodiment, after the step of determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position when the vehicle enters the signal positioning blind area, the method further includes: Constructing a digital model of the vehicle and the current signal positioning blind area, and outputting the digital model to the navigation device; After the step of determining the trajectory information of the vehicle based on the world coordinates and outputting the trajectory information to a navigation device corresponding to the vehicle, the method further includes: Determine simulated position information of the vehicle model in the digital model based on the trajectory information; The current simulated position information is added to the digital model, and the simulated position information is updated based on a preset time interval.

[0012] In one embodiment, after the step of determining the trajectory information of the vehicle based on the world coordinates and outputting the trajectory information to a navigation device corresponding to the vehicle, the method further includes: Determine the shooting position of the vehicle in the current camera device, and when the shooting position is in a position that overlaps with the shooting position of the next camera device, determine that the vehicle enters the shooting area of ​​the next camera device; or Acquire vehicle information of the vehicle, the vehicle information including the color, shape and license plate number of the vehicle; Synchronize the vehicle information to all camera devices, and when the next camera device recognizes the vehicle, determine that the vehicle enters the shooting area of ​​the next camera device; or Determine a timestamp of the vehicle entering the overlapping position of the shooting of the camera device, synchronize the timestamp to the next camera device, and determine that the vehicle enters the shooting area when the next camera device detects the vehicle.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle trajectory information acquisition device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle trajectory information acquisition method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle trajectory information acquisition method described above are implemented.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: After the vehicle enters the signal positioning blind spot, the real-time world coordinates of the vehicle are determined through the information captured by the camera device associated with the world coordinates, and the world coordinates are converted into the vehicle's trajectory information. Finally, the trajectory information is output to the navigation device, so that the driver can clearly understand the current position and positioning information based on the trajectory information, thereby improving driving safety. At the same time, the trajectory information of the navigation device is updated in real time based on the world coordinates captured by the continuous camera device, thereby improving the effectiveness and accuracy of the trajectory information. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for obtaining vehicle trajectory information of the present application; Figure 2 A flowchart diagram of the second embodiment of the vehicle trajectory information acquisition method of the present application; Figure 3 A flowchart diagram of the third embodiment of the vehicle trajectory information acquisition method of the present application; Figure 4 A flowchart of the fourth embodiment of the vehicle trajectory information acquisition method of the present application is provided; Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle trajectory information acquisition method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] Because traditional global positioning systems are prone to losing satellite signals in one or all directions in complex urban road conditions, such as tunnels, viaducts, and tree-lined roads, the basic vehicle positioning may be offset or even lost, which poses a great safety hazard to vehicle navigation and reduces driving safety.

[0022] The main solution of the embodiment of the present application is: when a vehicle enters a signal positioning blind area, the world coordinates of the vehicle in the world coordinate system are determined according to the camera device at the current position; Determining trajectory information of the vehicle based on the world coordinates, and outputting the trajectory information to a navigation device corresponding to the vehicle; When the vehicle enters a shooting area of ​​a next camera device, the trajectory information is updated based on coordinate information shot by the next camera device.

[0023] In this embodiment, the world coordinate information of the vehicle is captured by the camera device to generate the corresponding trajectory information of the vehicle, and the trajectory is output to the navigation device. The current trajectory information is then updated with the trajectory information of the vehicle entering another camera area, thereby realizing real-time positioning of the vehicle in the signal positioning blind spot and improving driving safety in the signal positioning blind spot.

[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The present application provides a method for obtaining vehicle trajectory information. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle trajectory information acquisition method of the present application.

[0026] In this embodiment, the vehicle trajectory information acquisition method includes steps S10 to S30: Step S10, when the vehicle enters the signal positioning blind area, determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position; It should be noted that the signal positioning blind area refers to the location where the current satellite positioning signal is poor or cannot receive the satellite positioning signal, including but not limited to urban underground areas, remote mountainous areas, high-rise buildings, strong magnetic field areas, tunnels, viaducts and tree-lined roads, etc. When driving in these places, it is easy to lose a certain direction or all satellite signals, and the vehicle positioning is offset or even lost, reducing driving safety. The camera device can be an infrared camera, an industrial camera, etc.

[0027] Therefore, in this embodiment, a camera device is installed in the signal positioning blind spot, the position of the vehicle is photographed in real time based on the camera device, and the position is converted into world coordinates, so that the vehicle trajectory information of the vehicle in the signal positioning blind spot can be analyzed based on continuous world coordinates, and the vehicle trajectory information is sent to the vehicle's navigation device, so that the driver can check the current actual positioning and improve driving safety.

[0028] It is understandable that continuous cameras are set up in the signal positioning blind spot, and there are repeated pictures between each adjacent camera, and the repeated picture ratio is usually less than 50%. For example, in a tunnel, from the entrance to the exit of the tunnel, the camera numbers are 1, 2, 3...n-1, n, and the pictures of adjacent cameras have about 1 / 4 repeated pictures.

[0029] Specifically, after the vehicle enters the signal positioning blind spot, the camera device can use the target detection algorithm YOLO (You Only Look Once, real-time target detection) algorithm to identify the boundary information of the vehicle entering the current shooting range, and calculate the pixel coordinates of the camera device of the center point of the vehicle, and finally convert the pixel coordinates into world coordinates.

[0030] As an optional implementation, when a vehicle is detected entering a signal positioning blind spot, the camera device identifies the boundary information of the vehicle based on a target detection algorithm, and then determines the pixel coordinates of the center point of the vehicle in each frame of the camera device based on the boundary information, and finally converts the pixel coordinates into world coordinates.

[0031] Before the camera devices in the signal positioning blind spot are put into use, the world coordinate system is calibrated, wherein the world coordinate system usually takes the shooting center point of the first camera device as the world coordinate center point.

[0032] Exemplarily, the signal positioning blind spot is an underground parking lot. When a vehicle enters the monitoring range of the first camera in the underground parking lot, the camera triggers the YOLO algorithm, and then quickly identifies the vehicle in the captured image and determines its boundary information. This process is completed almost instantly, ensuring real-time performance. The specific YOLO algorithm is not limited here. After the camera identifies the boundary information of the vehicle, it calculates the position of the center point corresponding to each captured frame in the current pixel coordinate system based on the boundary information, and then based on the calibrated world coordinate system, after coordinate conversion processing, obtains the position of the vehicle in each frame of the camera, and the world coordinates in the current world coordinate system.

[0033] Optionally, the camera device can also identify the vehicle information, including the vehicle's license plate, color and shape, etc. Therefore, when the vehicle enters the signal positioning blind spot and the first camera device captures the vehicle, the camera device obtains the vehicle information through image acquisition, preprocessing, feature processing and target recognition, and then synchronizes the vehicle information to the corresponding shooting systems of all camera devices, so that after the vehicle enters the shooting area of ​​other camera devices, the camera device can identify the vehicle and connect the vehicle with the information captured by the previous camera device, thereby obtaining more accurate coordinate information and improving the accuracy of trajectory information.

[0034] Step S20, determining the track information of the vehicle based on the world coordinates, and outputting the track information to a navigation device corresponding to the vehicle; It should be noted that the trajectory information includes existing trajectory information and predicted trajectory information. The existing trajectory information refers to the existing trajectory generated according to the world coordinates corresponding to the vehicle in a preset number of consecutive frames, and the predicted trajectory information is the predicted trajectory for a continuous period of time in the future generated by analyzing the existing trajectory. Wherein, while generating real-time trajectory information, the camera device can synchronize the trajectory information to the navigation device corresponding to the vehicle in real time, so that the driver can determine the current position based on the real-time changing trajectory information. The navigation device can be a vehicle-mounted terminal, a driver's mobile phone or tablet, etc. Before the camera device is put into use, it can send the corresponding trajectory information to the navigation device after authorization processing. When the navigation device receives the trajectory information, it displays the trajectory information through a window display, and then performs auxiliary positioning without affecting the original navigation, or without affecting the normal use of the navigation device.

[0035] It can be understood that the camera device generates existing trajectory information and predicted trajectory information in real time based on the captured content. Therefore, after it generates trajectory information for a period of time or a preset length, it will synchronize the trajectory information to the vehicle's navigation device in real time. As time goes by, the camera device continuously updates the trajectory information and synchronizes the real-time updated trajectory information to the navigation device, ensuring the real-time nature of the trajectory information.

[0036] In this embodiment, the world coordinates of the vehicle in each video frame of the camera device when the vehicle is in the shooting area of ​​the camera device can be first determined, and then the trajectory information of the vehicle can be generated based on the world coordinates of each frame, and the trajectory information can be synchronously output to the navigation device corresponding to the vehicle. Specifically, the camera device can generate the trajectory information of the vehicle based on the world coordinate information of the vehicle in a preset number of consecutive frames. For example, when a vehicle is monitored to enter an underground parking lot and is in the shooting area of ​​a certain camera device, the camera device will record its world coordinate position in each frame. As time goes by, these discrete coordinate points are connected to form a trajectory in a time series. By analyzing these trajectory data, the speed and driving direction of the vehicle can be evaluated, and its future position can be predicted.

[0037] Optionally, in the process of generating the trajectory information, the trajectory information can be extracted from the world coordinate system of the current camera device by using the multi-target tracking algorithm DeepSort. In addition, the trajectory information can also be processed by using a geodetic coordinate system conversion algorithm, etc. The method of extracting the trajectory information based on the world coordinate system is not limited here.

[0038] Step S30, when the vehicle enters the shooting area of ​​the next camera device, the trajectory information is updated based on the coordinate information shot by the next camera device.

[0039] It should be noted that after the trajectory information is output to the navigation device, the range corresponding to the trajectory information is the range captured by a certain camera device. Therefore, it is necessary to synchronize and update the trajectory information displayed in the current device in real time through the information captured by the continuous camera devices, so as to improve the real-time nature of the trajectory information and the accuracy of positioning in the signal positioning blind area. When the next camera device recognizes the vehicle, it is determined that the vehicle enters the shooting area of ​​the next camera device.

[0040] Specifically, in this embodiment, since the shooting devices set in the signal positioning blind area are continuous, when the vehicle enters the shooting area of ​​the next consecutive camera device, the next camera device can be used to identify the vehicle and extract the new world coordinates of the vehicle in each frame under the next device, and then generate new trajectory information based on the new world coordinates, and update the original trajectory information of the previous shooting device, so that the driver can update the trajectory information synchronously with the change of the shooting device during the driving process, thereby improving the positioning accuracy. Among them, the method of extracting the coordinate information of the vehicle based on the shooting of the next camera device, and generating new trajectory information based on the coordinate information, is the same as the aforementioned processing method, and will not be repeated here. It can be understood that after the vehicle enters the shooting area of ​​the new camera device, the trajectory information will be updated based on the real-time coordinate information.

[0041] Exemplarily, the signal positioning blind spot is a tunnel. When a vehicle enters a tunnel, the first camera in the tunnel captures the vehicle. After the vehicle is identified based on the target detection algorithm, the pixel coordinates of the vehicle are extracted and converted into world coordinates. The shooting range of all cameras is 200 meters, and the speed of the vehicle is 15 meters per second. At this time, the camera will calculate the world coordinates corresponding to each frame of the vehicle passing through the shooting range of the camera, so as to determine the real-time trajectory information corresponding to the vehicle in the tunnel based on the continuous world coordinates. Then, the trajectory information corresponding to the first two seconds of the vehicle entering the first camera can be generated, and then the trajectory information can be synchronized to the navigation terminal. Then, with the real-time movement information of the vehicle, the trajectory information of the navigation terminal is based on the new world coordinates. After the vehicle enters the shooting position of the next camera, the world coordinates of the vehicle at the current moment captured by the previous camera device and the coordinates of the next camera device are synchronized, so that the trajectory information corresponding to the next camera device can be connected to the trajectory information of the previous camera device, thereby completing the update of the trajectory information, improving the real-time and accuracy of positioning, and finally repeating the step of updating the trajectory information when the vehicle enters the shooting area of ​​the next camera device until the vehicle leaves the tunnel.

[0042] This embodiment provides a method for acquiring vehicle trajectory information. When a vehicle enters a signal positioning blind spot, trajectory information is generated based on the world coordinates of a camera device, and the real-time generated trajectory information is added to a navigation device, so that the driver can make accurate position judgments in the signal positioning blind spot based on the real-time updated trajectory information. At the same time, when the vehicle enters a shooting area of ​​a next consecutive camera device, the trajectory information is updated in real time based on the coordinate information captured by the next consecutive camera device, thereby further improving the effectiveness and accuracy of the trajectory information, providing the driver with corresponding positioning assistance in the signal positioning blind spot, and thus improving driving safety.

[0043] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated in the following. Figure 2 Before step S10, the vehicle trajectory information acquisition method further includes steps S01-S02: Step S01, obtaining initial calibration information of an initial camera device within the signal positioning blind area, and determining a mapping relationship between camera coordinates and world coordinates in the initial camera device based on the initial calibration information and camera device internal reference information; In this embodiment, in order to improve the accuracy and real-time performance of the generated trajectory information, it is necessary to calibrate the continuous camera devices. The calibration process here refers to building a unified world coordinate system for the continuous camera devices so that the data captured by different camera devices can be uniformly processed and analyzed within the same framework. The origin of the world coordinate system is usually at the center of the screen of the initial camera device. The mapping relationship refers to the translation matrix and rotation matrix when converting the camera coordinates of the camera device into the world coordinates, thereby determining the relationship between the camera coordinates of the camera device and the world coordinates.

[0044] Specifically, the initial calibration information refers to the pixel coordinates of the four corners of the calibration plate in the initial camera device and the real GPS coordinates when the calibration plate is placed at the center of the initial camera device screen. Based on the real GPS coordinates, the world coordinates corresponding to the four corners are generated. The camera device internal parameter information includes the focal length of the camera device, the coordinates of the principal point of the camera device, etc. After obtaining the pixel coordinates and world coordinates corresponding to the initial calibration information, and the focal length and principal point coordinates corresponding to the camera device internal parameter information, the camera coordinates can be determined based on the pixel coordinates and the camera device internal parameter information, and then the rotation matrix and translation matrix for coordinate conversion between the camera coordinates and the world coordinates are calculated based on the conversion relationship between the camera coordinates and the world coordinates.

[0045] Exemplarily, a calibration plate of a fixed size is placed at the center of the initial camera screen, and the pixel coordinates of the four corners of the calibration plate in the initial camera are recorded. At the same time, the real GPS coordinates of the four corners of the calibration plate are recorded. Based on this, the pixel coordinates of one corner p on the calibration plate are obtained as (u, v), the camera coordinates are (xc, yc, zc), and the world coordinates are (xw, yw, zw). These parameters are all known parameters, and the relationship between the pixel coordinates, camera coordinates, and world coordinates is shown in the following formula: , , , , .

[0046] It should be noted that f is the focal length of the camera device, dx and dy are the distances between unit pixels in the image plane in the x and y directions, respectively, Cx and Cy are the coordinates of the principal point of the camera device, and these parameters are all internal parameters determined when the camera device leaves the factory, R is the rotation matrix, and T is the translation matrix. Furthermore, Zc is the focal length of the camera device, that is, Zc=f.

[0047] Based on the above calculation formula, the pixel coordinates and world coordinates corresponding to the non-collinear points at the four corners of the calibration plate, as well as the internal parameter information of the camera device, are used to solve the rotation matrix R and translation matrix T for coordinate transformation between the camera coordinates and the world coordinates, that is, the mapping relationship between the initial camera device and the world coordinate system, so that the transformation relationship between the next camera device in a continuous and repeated shooting area and the world coordinate system can be calculated based on the mapping relationship.

[0048] Step S02: Based on the mapping relationship and the calibration information corresponding to each of the other consecutive camera devices, perform a world coordinate system synchronous calibration process on the other camera devices.

[0049] In this embodiment, the calibration information of other consecutive camera devices refers to two camera coordinates corresponding to one point of the calibration object in the camera device and the previously calibrated camera device in the overlapping shooting area between the two, as well as the world coordinates.

[0050] As an optional implementation, in this process, the camera coordinates and calibrated world coordinates of the calibrated object captured in the repeated images of the calibrated camera device and the next uncalibrated camera device can be obtained, and then the next uncalibrated camera device can be synchronously calibrated in the world coordinate system based on the calibrated world coordinates, the camera coordinates and the mapping relationship.

[0051] For example, during the calibration process, camera 1 is the calibrated initial camera, and camera 2 is an uncalibrated camera with overlapping images with camera 1. During calibration, the calibration plate is placed in the overlapping images of camera 1 and camera 2, and both cameras can fully capture the calibration plate. The coordinates of point P on the calibration plate are (xc1, yc1, zc1) for camera 1 and (xc2, yc2, zc2) for camera 2. At this time, the world coordinates of point N can be calculated based on the following formula: , Among them, in the process of calculating the mapping relationship between the camera coordinates of the initial calibration camera and the world coordinates, R and T are obtained, and camera No. 1 is the initial calibration information, so R1=R, T1=T, and the known R and T are substituted into the above calculation formula to obtain the world coordinates of point N (xn, yn, zn). Then, the world coordinate system synchronization calibration processing is performed on camera No. 2 based on the following formula: , After substituting the world coordinates of point N as (xn, yn, zn), solve T2 and R2 to obtain the relationship between the camera coordinates and the world coordinates of camera 2, based on which the calibration of camera 2 is completed.

[0052] Furthermore, in the subsequent calibration process, when the next uncalibrated camera device is not the last camera device, based on the currently calibrated camera device, the step of obtaining the position information of the calibration object captured in the repeated images of the calibrated camera device and the next uncalibrated camera device and determining the calibrated world coordinates of the calibration object is jumped to execute. That is, the calibration process of camera No. 2 is repeated until the relationship between the coordinates of all cameras and the world coordinates is determined.

[0053] The present embodiment provides a method for acquiring vehicle trajectory information. First, based on initial calibration information, a mapping relationship between camera coordinates and world coordinates in an initial camera device is determined. Then, based on the mapping relationship, the coordinate system relationship between consecutive devices is synchronized so that when all subsequent cameras capture a vehicle, the real-time camera coordinates of the vehicle can be converted into world coordinates corresponding to the previous camera device, thereby improving the continuity of world coordinates generated based on consecutive cameras, thereby improving the continuity and accuracy of trajectory information.

[0054] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated later. Figure 3 After step S30, the vehicle trajectory information acquisition method further includes steps S40 to S60: Step S40, when it is detected that the vehicle leaves the signal positioning blind area, obtaining the target world coordinates captured by each consecutive camera device in the signal positioning blind area; In this embodiment, after the vehicle has detected the blind spot of the signal positioning, the actual trajectory of the vehicle during this driving distance can also be summarized and processed, thereby drawing a complete driving path, which is helpful for analyzing the driving behavior of the vehicle and improving road safety and traffic efficiency. Based on this, the target world coordinates captured by each continuous camera device can be obtained, so as to generate trajectory information for driving behavior analysis based on the target world coordinates.

[0055] Step S50, generating a plurality of to-be-processed trajectory information corresponding to each of the continuous camera devices based on the target world coordinate system; It is understandable that each camera device can generate a piece of vehicle trajectory information, and this piece of trajectory information is the trajectory information to be processed.

[0056] Step S60, performing deduplication processing on the trajectory information to be processed to obtain a target trajectory, and outputting the target trajectory to a monitoring system corresponding to the vehicle.

[0057] In this embodiment, since there are repeated shooting areas between consecutive cameras, it is also necessary to perform deduplication processing on the generated multiple trajectory information to be processed. During deduplication processing, only the vehicle world coordinates output by the next camera device can be retained according to the camera coordinate relationship between adjacent cameras, and then a complete trajectory is formed based on the deduplicated world coordinate records. That is, the coordinates in the trajectory to be processed that are repeated with the next camera device are removed, and the latest non-repetitive trajectory is obtained.

[0058] This embodiment provides a method for acquiring vehicle trajectory information. In addition to sharing real-time trajectory information to a navigation device, after the vehicle leaves a signal positioning blind spot, all world coordinates during the shooting process are first acquired, and then after removing the coordinate points in the repeated area, trajectory information of the vehicle's driving process in the signal positioning blind spot is generated based on the remaining coordinates, so as to analyze the vehicle's driving behavior based on the trajectory information and improve driving safety.

[0059] Based on the first embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above description and will not be described in detail later. Figure 4 After step S10, the vehicle trajectory information acquisition method further includes step S70: Step S70, constructing a digital model of the vehicle and the current signal positioning blind spot, and outputting the digital model to the navigation device.

[0060] In this embodiment, in addition to outputting the current positioning information in the form of trajectory information, the specific three-dimensional effect of the vehicle when traveling in the signal positioning blind spot can also be displayed in the form of a digital model, so that the driver can determine the specific position information based on the digital model and improve driving safety.

[0061] Specifically, when the camera device is put into use, it will obtain a digital model of the signal positioning blind spot. After a vehicle enters the signal positioning blind spot, it will generate a model of the vehicle by performing image recognition processing on the vehicle. The digital model of the vehicle and the digital model of the signal positioning blind spot are then output to the navigation device so that after receiving the trajectory information, the change information of the vehicle model in the actual model can be adjusted in the digital model based on the trajectory information.

[0062] It should be noted that the digital model can be displayed in the navigation device in a three-dimensional projection so that the driver can determine the current position based on the projection information.

[0063] Furthermore, after step S20, the simulated position information of the vehicle model in the digital model can be determined based on the trajectory information, and the current simulated position information is added to the digital model. Finally, the current simulated position information is added to the digital model, and the simulated position information is updated based on a preset time interval. It can be understood that when the vehicle is moving, the vehicle model is controlled to move in the digital model based on the trajectory information, so that the driver can determine the current actual position through the specific moving position of the vehicle model in the model of the signal positioning blind spot, so that the vehicle can provide accurate positioning when it is in the signal positioning blind spot, thereby improving driving safety.

[0064] Based on the first embodiment of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. On this basis, after step S10, it is also necessary to determine whether the vehicle enters the next camera device.

[0065] Specifically, in the method of judging whether a vehicle has entered the shooting area of ​​the next camera device, since there are repeated shooting areas between consecutive cameras, it is possible to judge whether the vehicle is in a position where the shooting of the current camera device overlaps with that of the next camera device. If so, it can be judged that the vehicle has entered the shooting area of ​​the next camera device. That is, the shooting position of the vehicle in the current camera device is determined, and when the shooting position is in a position where the shooting of the next camera device overlaps, it is determined that the vehicle has entered the shooting area of ​​the next camera device.

[0066] Optionally, the judgment can also be made by synchronizing vehicle information, wherein the vehicle information of the vehicle can be obtained, the vehicle information includes the color, shape and license plate number of the vehicle, and then the vehicle information is synchronized to all camera devices. The synchronization method can upload the vehicle information to the camera system, and when the next camera device recognizes the vehicle, it is judged that the vehicle enters the shooting area of ​​the next camera device. Based on this, when other camera devices capture the vehicle, they compare it with the data stored in the shooting system and when the comparison result is obtained, it is determined that the vehicle enters the shooting area.

[0067] Optionally, the judgment may also be made based on the timestamp of the position where the vehicle enters the overlapping position of the camera device. The timestamp of the position where the vehicle enters the overlapping position of the camera device is first determined, the timestamp is synchronized to the next camera device, and when the next camera device detects the vehicle at the current timestamp, it is judged that the vehicle enters the shooting area.

[0068] By determining whether the vehicle enters the next camera device, the real-time position information of the vehicle is determined, thereby improving the accuracy of the world coordinates captured by the continuous camera devices.

[0069] The present application provides a vehicle trajectory information acquisition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle trajectory information acquisition method in the above-mentioned embodiment 1.

[0070] Reference below Figure 5 , which shows a schematic structural diagram of a vehicle trajectory information acquisition device suitable for implementing an embodiment of the present application. Figure 5 The vehicle trajectory information acquisition device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0071] like Figure 5As shown, the vehicle trajectory information acquisition device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle trajectory information acquisition device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle trajectory information acquisition device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle trajectory information acquisition device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0072] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0073] The vehicle trajectory information acquisition device provided by the present application adopts the vehicle trajectory information acquisition method in the above embodiment, which can solve the technical problem that when the vehicle is in a signal positioning blind spot, the lack of positioning leads to reduced driving safety. Compared with the prior art, the beneficial effects of the vehicle trajectory information acquisition device provided by the present application are the same as the beneficial effects of the vehicle trajectory information acquisition method provided by the above embodiment, and the other technical features in the vehicle trajectory information acquisition device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0074] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0076] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle trajectory information acquisition method in the above-mentioned embodiment.

[0077] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0078] The computer-readable storage medium may be included in the vehicle trajectory information acquisition device; or may exist independently without being assembled into the vehicle trajectory information acquisition device.

[0079] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle trajectory information acquisition device, the vehicle trajectory information acquisition device: When the vehicle enters a signal positioning blind area, determining the world coordinates of the vehicle in a world coordinate system according to the camera device at the current position; Determining trajectory information of the vehicle based on the world coordinates, and outputting the trajectory information to a navigation device corresponding to the vehicle; When the vehicle enters a shooting area of ​​a next camera device, the trajectory information is updated based on coordinate information shot by the next camera device.

[0080] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0081] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] The modules involved in the embodiments described in the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0083] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle trajectory information acquisition method, and can solve the technical problem that when the vehicle is in a signal positioning blind spot, the lack of positioning leads to reduced driving safety. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the vehicle trajectory information acquisition method provided by the above-mentioned embodiment, and will not be repeated here.

[0084] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for obtaining vehicle trajectory information, characterized in that: The method comprises: When the vehicle enters a signal positioning blind area, determining the world coordinates of the vehicle in a world coordinate system according to the camera device at the current position; Determining trajectory information of the vehicle based on the world coordinates, and outputting the trajectory information to a navigation device corresponding to the vehicle; When the vehicle enters a shooting area of ​​a next camera device, the trajectory information is updated based on coordinate information shot by the next camera device.

2. The method according to claim 1, characterized in that Before the step of determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position when the vehicle enters the signal positioning blind area, the method further includes: Acquire initial calibration information of an initial camera device in the signal positioning blind area, and determine a mapping relationship between camera coordinates and world coordinates in the initial camera device based on the initial calibration information and camera device internal reference information; Based on the mapping relationship and the calibration information corresponding to each of the other continuous camera devices, the world coordinate system synchronous calibration processing is performed on the other camera devices.

3. The method according to claim 2, characterized in that The step of performing synchronous calibration processing of the world coordinate system on other camera devices based on the mapping relationship and the calibration information corresponding to each of the other continuous camera devices comprises: Obtaining the camera coordinates and the calibrated world coordinates of the calibration object captured in the repeated images of the calibrated camera device and the next uncalibrated camera device; Based on the calibrated world coordinates, the camera coordinates and the mapping relationship, performing a world coordinate system synchronous calibration process on the next uncalibrated camera device; When the next uncalibrated camera device is not the last camera device, based on the currently calibrated camera device, jump to execute the step of obtaining the position information of the calibration object captured in the repeated pictures of the calibrated camera device and the next uncalibrated camera device, and determining the calibrated world coordinates of the calibration object.

4. The method according to claim 1, characterized in that When the vehicle enters the signal positioning blind area, the step of determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position comprises: When it is detected that the vehicle enters the signal positioning blind area, the camera device identifies boundary information of the vehicle based on a target detection algorithm; Determine the pixel coordinates of the center point of the vehicle in each frame of the camera device according to the boundary information; The pixel coordinates are converted to the world coordinates.

5. The method according to claim 1, characterized in that After the step of updating the track information based on the coordinate information captured by the next camera device when the vehicle enters the capturing area of ​​the next camera device, the method further includes: When it is detected that the vehicle leaves the signal positioning blind area, obtaining the target world coordinates captured by each continuous camera device in the signal positioning blind area; Generate a plurality of to-be-processed trajectory information corresponding to each of the continuous camera devices based on the target world coordinates; The to-be-processed trajectory information is deduplicated to obtain a target trajectory, and the target trajectory is output to a monitoring system corresponding to the vehicle.

6. The method according to claim 1, characterized in that The step of determining the track information of the vehicle based on the world coordinates and outputting the track information to a navigation device corresponding to the vehicle comprises: Determine the world coordinates of the vehicle in each video frame of the camera device when the vehicle is in the shooting area of ​​the camera device; Based on the world coordinates of each frame, the trajectory information of the vehicle is generated, and the trajectory information is output to the navigation device corresponding to the vehicle.

7. The method according to claim 1, characterized in that After the step of determining the world coordinates of the vehicle in the world coordinate system according to the camera device at the current position when the vehicle enters the signal positioning blind area, the method further includes: Constructing a digital model of the vehicle and the current signal positioning blind area, and outputting the digital model to the navigation device; After the step of determining the trajectory information of the vehicle based on the world coordinates and outputting the trajectory information to a navigation device corresponding to the vehicle, the method further includes: Determine simulated position information of the vehicle model in the digital model based on the trajectory information; The current simulated position information is added to the digital model, and the simulated position information is updated based on a preset time interval.

8. The method according to claim 1, characterized in that After the step of determining the trajectory information of the vehicle based on the world coordinates and outputting the trajectory information to a navigation device corresponding to the vehicle, the method further includes: Determine the shooting position of the vehicle in the current camera device, and when the shooting position is in a position that overlaps with the shooting position of the next camera device, determine that the vehicle enters the shooting area of ​​the next camera device; or Acquire vehicle information of the vehicle, the vehicle information including the color, shape and license plate number of the vehicle; Synchronize the vehicle information to all camera devices, and when the next camera device recognizes the vehicle, determine that the vehicle enters the shooting area of ​​the next camera device; or Determine a timestamp of the vehicle entering the overlapping position of the shooting of the camera device, synchronize the timestamp to the next camera device, and determine that the vehicle enters the shooting area when the next camera device detects the vehicle.

9. A vehicle trajectory information acquisition device, characterized in that: The vehicle trajectory information acquisition device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle trajectory information acquisition method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle trajectory information acquisition method according to any one of claims 1 to 8 are implemented.

Images