Method for outputting low-delay driving track information of vehicle based on RTK data

Abstract

The invention discloses a method for outputting low-delay driving track information of a vehicle based on RTK data. A base station, a GPS satellite and a moving station are included. Comprising the following steps: S1, calculating to obtain a GPS positioning error, and sending the GPS positioning error to a moving station; s2, the moving station obtains RTK position data, three-dimensional coordinates and precision of the moving station through GPS positioning errors; s3, the moving station obtains a roadside video and obtains RTK position data of the floating vehicle in the roadside video; s4, virtual unified coordinate reconstruction is carried out through the RTK position data, and virtual unified coordinates are obtained; s5, delimiting a data reading area in the roadside video picture through the virtual unified coordinates; s6, track information and speed information of the vehicle in the roadside video range are obtained through calculation of the data reading area; and S7, pushing each vehicle to each detected vehicle in real time, and performing early warning to remind the surrounding vehicles and any traffic hidden danger.

Description

Technical Field

[0001] The present invention relates to the field of vehicle safety technology, and in particular to a method for outputting low-latency driving trajectory information of a vehicle based on RTK data. Background Art

[0002] With the progress of urbanization and the increase in the number of vehicles, problems such as traffic congestion, accidents and safety are becoming increasingly prominent, so accurate monitoring and analysis of road traffic has become a key task.

[0003] The output of vehicle trajectory from roadside monitoring video is an important research and application direction in the field of transportation. Mining vehicles within the field of view of video detection can reduce the deployment of video detection equipment and optimize construction costs and efficiency. The development of roadside detection video systems and urban intelligent transportation has made vehicle trajectory analysis more comprehensive and accurate, and real-time and automation are increasingly becoming requirements. This technology has broad application prospects in the fields of traffic management, planning, intelligent transportation and autonomous driving. It can be used to optimize traffic signal control, improve traffic flow distribution, improve road safety, and provide perception and decision support for networked and autonomous driving systems.

[0004] However, at present, the output of vehicle trajectories from roadside monitoring videos still faces some challenges and problems. First, there is still room for improvement in the accuracy of vehicle detection, especially in cases of occlusion and lighting changes in complex scenes. Second, vehicle tracking algorithms may be affected by factors such as vehicle occlusion, confusion of similar vehicles, and changes in motion patterns, resulting in tracking interruptions or incorrect associations. In addition, the data association problem in multi-camera systems remains challenging, and it is necessary to solve the difficulties caused by factors such as different perspectives and spatiotemporal differences. The processing and real-time output of large-scale video data have high requirements for computing resources and algorithms, and efficient processing methods need to be sought. Finally, privacy and data security issues also need to be taken seriously to ensure the protection of vehicle and pedestrian information. In summary, solving these problems requires further research and development of more accurate and robust detection and tracking algorithms, improved data association and trajectory modeling methods, and strengthened technical measures for data processing and privacy protection.

[0005] The technology of this application combines the RTK precise positioning technology of floating vehicles on the road with the road-side detection video images, and uses virtual unified coordinate reconstruction technology to output the vehicle's low-latency (based on video 10HZ) driving trajectory information in real time, which not only provides real-time and precise positioning of the vehicle, but also informs its corresponding lane position and surrounding traffic status (the position of each surrounding car), providing protection for real-time instantaneous traffic safety.

[0006] At present, the methods for solving the problem of vehicle driving trajectory output by roadside detection video mainly include the following: Solutions based on traditional computer vision methods: Use traditional image processing and computer vision algorithms, such as background modeling, inter-frame difference, inter-frame similarity matching, etc. to detect and track vehicles. These methods perform well in some simple scenarios, but still have certain limitations for vehicle detection and tracking in complex scenarios and under occlusion.

[0007] Deep learning-based solutions: Use deep learning algorithms, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and target detectors (such as YOLO, Faster R-CNN), to detect, track, and predict vehicle trajectories. These methods can provide more accurate vehicle identification and tracking results in complex scenarios, but they have high requirements for real-time performance and computing resources.

[0008] However, there are such problems in the prior art: Accuracy of vehicle detection and tracking: In complex traffic scenarios, such as vehicle occlusion, lighting changes, and similar vehicles, the vehicle detection and tracking algorithm still has certain false detection and missed detection problems, which affects the accuracy of the trajectory; Trajectory continuity and consistency: Due to the instability of the vehicle tracking algorithm and factors such as occlusion, the vehicle trajectory may be interrupted, broken, or incorrectly associated, resulting in the continuity and consistency of the trajectory being affected.

[0009] Real-time and computing resource requirements: For real-time application scenarios, such as traffic management and autonomous driving, it is necessary to process a large amount of video data in a short time and output accurate vehicle trajectories. Therefore, real-time and computing resource requirements are a challenge.

[0010] Road condition complexity and data association: In a multi-camera system, the vehicle trajectories from different cameras need to be associated to obtain the complete vehicle trajectory. However, the complexity of road conditions and the spatiotemporal changes of vehicles may lead to difficulties in data association.

[0011] Therefore, improvements are needed. Summary of the invention

[0012] The purpose of the present invention is to provide a method for outputting low-latency driving trajectory information of a vehicle based on RTK data, so as to overcome the deficiencies in the prior art.

[0013] To achieve the above object, the present invention provides the following technical solutions: The present application discloses a method for outputting low-latency driving trajectory information of a vehicle based on RTK data, including a base station, a GPS satellite and a mobile station; and includes the following steps: S1: Calculate and obtain the GPS positioning error, and send the GPS positioning error to the mobile station; S2: The mobile station obtains its own RTK position data, three-dimensional coordinates and accuracy through GPS positioning error; S3: The mobile station obtains the roadside video and the RTK position data of the floating vehicle in the roadside video; S4: reconstructing virtual unified coordinates through RTK position data to obtain virtual unified coordinates; S5: Delimiting a data reading area in the roadside video screen through virtual unified coordinates; S6: Obtaining the trajectory information and speed information of the vehicle within the roadside video range by calculating the data reading area; S7: Push notifications to each detected vehicle in real time, and issue warnings to surrounding vehicles and any traffic hazards.

[0014] Preferably, S1 comprises the following sub-steps: S11: GPS satellites broadcast navigation signals to all parts of the earth; S12: The base station receives the GPS navigation signal, obtains the distance from the satellite to the base station, and calculates the GPS positioning error; S13: The base station sends the distance from the satellite to the base station and the GPS positioning error to the mobile station.

[0015] Preferably, S2 comprises the following sub-steps: S21: The mobile station receives the GPS navigation signal and obtains the distance from the satellite to the mobile station; S22: The mobile station receives the distance from the satellite to the base station and the GPS positioning error, and corrects the distance data from the satellite to the mobile station; S23: The mobile station calculates its own three-dimensional coordinates and accuracy.

[0016] Preferably, S4 comprises the following steps: S41: capturing a picture of a roadside video; S42: setting a coordinate origin in the roadside video screen, and dividing the screen into equal parts to form a number of coordinate points; S43: Acquire the longitude and latitude according to the RTK position data of the floating vehicle, and find the RTK longitude and latitude coordinate values ​​corresponding to the coordinate point in the video screen according to the longitude and latitude; S44: Calculating the longitude and latitude coordinate values ​​of each lane in the roadside video screen according to the longitude and latitude coordinate values ​​obtained in the roadside video screen; S45: According to the longitude and latitude coordinate values ​​in the RTK position data of the floating vehicle, the longitude and latitude values ​​of the virtual coordinate points based on the RTK longitude and latitude are formed, and then the virtual unified coordinates are reconstructed.

[0017] Preferably, the RTK position data is generated once every 0.1 seconds, and the picture frequency of the road test video is 10 Hz.

[0018] A device for outputting low-latency driving trajectory information of a vehicle based on RTK data, comprising a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, they are used to implement the above-mentioned method for outputting low-latency driving trajectory information of a vehicle based on RTK data.

[0019] A computer-readable storage medium stores a program thereon, which, when executed by a processor, implements the above-mentioned method of outputting low-latency driving trajectory information of a vehicle based on RTK data.

[0020] Beneficial effects of the present invention: (1) This method combines RTK (floating vehicle) data and roadside detection video to achieve low-latency output of vehicle trajectory information based on RTK floating vehicle. The method is simple and easy to implement, does not require complex data calculation and deep learning of data, and is compatible with roadside detection videos in different postures and complex scenes. (2) This method can be combined with existing road detection video equipment. Without adding new roadside equipment detection video equipment, by comparing the detection images and RTK data, a fusion algorithm is performed to achieve low-latency trajectory information output of vehicles on regional roads, thereby achieving low investment and high output.

[0021] The features and advantages of the present invention will be described in detail through embodiments in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of the steps of a method for outputting low-latency driving trajectory information of a vehicle based on RTK data of the present invention; Figure 2 It is a schematic diagram of the structure of the present invention; Figure 3 It is a schematic diagram of the device of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below through the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the scope of the present invention. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0024] See also Figure 1The embodiment of the present invention provides a method for outputting low-latency driving trajectory information of a vehicle based on RTK data, which needs to solve the above-mentioned technical problems: 1. Instantly and accurately locate the vehicle position to centimeter level; 2. Establish virtual unified coordinates based on high-frequency RTK road data measured by floating vehicles to correct roadside detection video data; 3. Instantly and accurately locate the exact position of the car in the actual road lane in the video and its surrounding cars (traffic status) and obstacles; There are six technical steps that need to be implemented: 1. Calibrate the static and precise position along the road, and use the floating vehicle RTK for precise positioning and calibration; 2. Obtain the image of the RTK floating vehicle in the roadside detection video; 3. Based on RTK data, virtual unified coordinate reconstruction is performed in the road test video; 4. Define the data reading area in the current roadside video screen through the determined virtual unified coordinates; 5. Read the virtual unified coordinate information and speed of the vehicle in the roadside detection video; 6. Output the real-time trajectory information of each vehicle based on the roadside detection video (10HZ), and warn the surrounding vehicles and any traffic hazards.

[0025] The specific contents are: Including base station, GPS satellite and mobile station; including the following steps: S1: Calculate and obtain the GPS positioning error, and send the GPS positioning error to the mobile station; S2: The mobile station obtains its own RTK position data, three-dimensional coordinates and accuracy through GPS positioning error; S3: The mobile station obtains the roadside video and the RTK position data of the floating vehicle in the roadside video; S4: reconstructing virtual unified coordinates through RTK position data to obtain virtual unified coordinates; S5: Delimiting a data reading area in the roadside video screen through virtual unified coordinates; S6: Obtaining the trajectory information and speed information of the vehicle within the roadside video range by calculating the data reading area; S7: Push notifications to each detected vehicle in real time, and issue warnings to surrounding vehicles and any traffic hazards.

[0026] Among them: the generation frequency of RTK position data is once every 0.1 seconds, and the picture frequency of the road test video is 10HZ.

[0027] Wherein, the S1 includes the following contents: RTK precise positioning and calibration RTK is differential positioning (separating errors). On the basis of GPS, a ground base station (i.e., base station, which is a public facility and does not need to be built by yourself) is set up. The ground base station obtains satellite positioning and compares it with its own real position (since the base station is fixed, the position is absolute), calculates the positioning error with GPS, and sends the current error to the mobile station (or self-provided floating vehicle) via GPRS. The mobile station will use this error to correct the positioning data obtained from the satellite. Based on the base station data and its own data, the mobile station performs real-time differential operations according to the principle of relative positioning, thereby solving the three-dimensional coordinates and accuracy of the mobile station, and its positioning accuracy can reach 1cm~2cm. See also Figure 2 , the data transmission flow path between the base station, mobile station and GPS satellite in the RTK system is: 1.GPS satellites continuously broadcast navigation signals to all parts of the earth.

[0028] 2. The base station antenna receives navigation signals from all visible GPS satellites.

[0029] 3. The receiver in the base station processes the navigation signals of each GPS satellite, calculates the distance from each satellite to the base station, and compares it with its own actual position to calculate the GPS positioning error.

[0030] 4. The base station sends these precise satellite-to-station distances and GPS positioning errors in the form of a radio data link.

[0031] 5. The rover antenna also receives signals from all visible GPS satellites.

[0032] 6. The receiver in the mobile station also calculates the distance from each satellite to the mobile station.

[0033] 7. The mobile station receives the satellite-to-station distance and error data sent by the base station via radio.

[0034] 8. The processor in the mobile station will use the errors transmitted by the base station to correct the satellite distance data calculated by itself.

[0035] 9. The mobile station calculates the three-dimensional coordinates and accuracy of the mobile station through real-time differential calculation based on the base station data and its own data; the mobile station can eliminate atmospheric errors and obtain centimeter-level positioning results.

[0036] 10. This precise positioning result is used as the output of the mobile station and provided to the vehicle navigation system.

[0037] In this way, high-precision vehicle positioning and navigation functions are achieved through radio distance data transmission between the base station and the mobile station and real-time differential calculation in the mobile station.

[0038] The mobile station can also be realized by installing RTK equipment on a floating vehicle.

[0039] Specifically, it includes the following sub-steps: S11: GPS satellites broadcast navigation signals to all parts of the earth; S12: The base station receives the GPS navigation signal, obtains the distance from the satellite to the base station, and calculates the GPS positioning error; S13: The base station sends the distance from the satellite to the base station and the GPS positioning error to the mobile station.

[0040] The S2 comprises the following sub-steps: S21: The mobile station receives the GPS navigation signal and obtains the distance from the satellite to the mobile station; S22: The mobile station receives the distance from the satellite to the base station and the GPS positioning error, and corrects the distance data from the satellite to the mobile station; S23: The mobile station calculates its own three-dimensional coordinates and accuracy.

[0041] The S3 includes the following contents: Get the image of the RTK floating vehicle in the road test video Log in to the roadside inspection video system, find the image of the RTK floating vehicle in the roadside inspection video, and download the video recording.

[0042] The S4 includes the following contents: Reconstruct virtual unified coordinates in the drive test video based on RTK data; RTK data is generated every 0.1 seconds and contains information such as longitude and latitude. Therefore, it is possible to combine the current roadside detection video (10HZ) image to reconstruct the virtual coordinates within the roadside detection video image based on the RTK data.

[0043] The following sub-steps are included: S41: capturing a picture of a roadside video; S42: setting a coordinate origin in the roadside video screen, and dividing the screen into equal parts to form a number of coordinate points; S43: Acquire the longitude and latitude according to the RTK position data of the floating vehicle, and find the RTK longitude and latitude coordinate values ​​corresponding to the coordinate point in the video screen according to the longitude and latitude; S44: Calculating the longitude and latitude coordinate values ​​of each lane in the roadside video screen according to the longitude and latitude coordinate values ​​obtained in the roadside video screen; S45: According to the longitude and latitude coordinate values ​​in the RTK position data of the floating vehicle, the longitude and latitude values ​​of the virtual coordinate points based on the RTK longitude and latitude are formed, and then the virtual unified coordinates are reconstructed.

[0044] Among them, virtual unified coordinate reconstruction technology includes the following contents: Virtual coordinate reconstruction technology refers to the reconstruction of objects or scenes in the actual scene into models or representations in a three-dimensional virtual coordinate system through computer vision and image processing technology.

[0045] Virtual unified coordinate reconstruction is mainly divided into the following steps: 1. Capture the roadside detection video obtained in the second step; 2. Take the lower right corner of the captured image as the coordinate origin, divide the image into equal parts through an algorithm, and form several coordinate points based on the 10HZ frequency of the video; 3. According to the longitude and latitude values ​​of the RTK floating vehicle, find the longitude and latitude coordinate values ​​of the RTK corresponding to the coordinate points marked in the video screen (frequency of 10HZ); 4. Use the algorithm to calculate the longitude and latitude values ​​of the coordinate points of the adjacent lanes in the video image based on the longitude and latitude values ​​of the coordinate points of the roadside detection video image (10HZ) that have been determined; 5. Based on the data from the RTK floating vehicle, the longitude and latitude values ​​of the virtual coordinate points are formed based on the RTK longitude and latitude values, and the virtual coordinates are reconstructed.

[0046] S5 includes the following contents: defining the data reading area in the current roadside video screen by determining the virtual unified coordinates; The virtual coordinates of the roadside detection video reconstructed based on RTK data are used to form the video data reading range.

[0047] The S6 includes the following contents: reading the virtual coordinate information and speed information of the vehicle in the roadside detection video screen; According to the range defined in the fourth step, the trajectory information and speed information of each frame of the vehicle appearing in the roadside detection video range are read.

[0048] The S7 includes the following contents: outputting the real-time trajectory information of each vehicle based on the roadside detection video (10HZ), and warning the surrounding vehicles and any traffic hazards The trajectory, speed and time of each vehicle on each screen are acquired, and the changes in the vehicle's trajectory and its interaction with surrounding vehicles are tracked at 10-20Hz (10-20 times per second), so that the most critical safety information can be delivered to the vehicle in a timely manner to avoid traffic hazards.

[0049] An embodiment of a device for outputting low-latency driving trajectory information of a vehicle based on RTK data according to the present invention can be applied to any device with data processing capabilities, and the device with data processing capabilities can be a device or apparatus such as a computer. The device embodiment can be implemented through software, or through hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, the processor of any device with data processing capabilities reads the corresponding computer program instructions in the non-volatile memory into the internal memory and runs them. From a hardware perspective, if Figure 3 As shown, it is a hardware structure diagram of any device with data processing capability where a device for outputting low-latency driving trajectory information of a vehicle based on RTK data of the present invention is located, except Figure 3 In addition to the processor, memory, network interface, and non-volatile memory shown, any device with data processing capabilities in the embodiment of the device may also include other hardware according to the actual function of the device with data processing capabilities, which will not be described in detail. The implementation process of the functions and effects of each unit in the above device is specifically detailed in the implementation process of the corresponding steps in the above method, which will not be described in detail here.

[0050] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present invention. Ordinary technicians in this field can understand and implement it without paying creative work.

[0051] An embodiment of the present invention also provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, a device in the above embodiment is implemented to output low-latency driving trajectory information of a vehicle based on RTK data.

[0052] The computer-readable storage medium may be an internal storage unit of any device with data processing capability described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of any device with data processing capability, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of any device with data processing capability. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capability, and may also be used to temporarily store data that has been output or is to be output.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent substitution or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for outputting low-latency driving trajectory information of a vehicle based on RTK data, characterized in that: Including base station, GPS satellite and mobile station; including the following steps: S1: Calculate and obtain the GPS positioning error, and send the GPS positioning error to the mobile station; S2: The mobile station obtains its own RTK position data, three-dimensional coordinates and accuracy through GPS positioning error; S3: The mobile station obtains the roadside video and the RTK position data of the floating vehicle in the roadside video; S4: reconstructing virtual unified coordinates through RTK position data to obtain virtual unified coordinates; S5: Delimiting a data reading area in the roadside video screen through virtual unified coordinates; S6: Obtaining the trajectory information and speed information of the vehicle within the roadside video range by calculating the data reading area; S7: Push notifications to each detected vehicle in real time, and issue warnings to surrounding vehicles and any traffic hazards.

2. A method for outputting low-latency driving trajectory information of a vehicle based on RTK data as claimed in claim 1, characterized in that: The S1 comprises the following sub-steps: S11: GPS satellites broadcast navigation signals to all parts of the earth; S12: The base station receives the GPS navigation signal, obtains the distance from the satellite to the base station, and calculates the GPS positioning error; S13: The base station sends the distance from the satellite to the base station and the GPS positioning error to the mobile station.

3. A method for outputting low-latency vehicle driving trajectory information based on RTK data as claimed in claim 1, characterized in that: The S2 comprises the following sub-steps: S21: The mobile station receives the GPS navigation signal and obtains the distance from the satellite to the mobile station; S22: The mobile station receives the distance from the satellite to the base station and the GPS positioning error, and corrects the distance data from the satellite to the mobile station; S23: The mobile station calculates its own three-dimensional coordinates and accuracy.

4. A method for outputting low-latency vehicle driving trajectory information based on RTK data as claimed in claim 1, characterized in that: The S4 comprises the following steps: S41: capturing a picture of a roadside video; S42: setting a coordinate origin in the roadside video screen, and dividing the screen into equal parts to form a number of coordinate points; S43: Acquire the longitude and latitude according to the RTK position data of the floating vehicle, and find the RTK longitude and latitude coordinate values ​​corresponding to the coordinate point in the video screen according to the longitude and latitude; S44: Calculating the longitude and latitude coordinate values ​​of each lane in the roadside video screen according to the longitude and latitude coordinate values ​​obtained in the roadside video screen; S45: According to the longitude and latitude coordinate values ​​in the RTK position data of the floating vehicle, the longitude and latitude values ​​of the virtual coordinate points based on the RTK longitude and latitude are formed, and then the virtual unified coordinates are reconstructed.

5. The method for outputting low-latency driving trajectory information of a vehicle based on RTK data according to claim 1, characterized in that: The RTK position data is generated every 0.1 seconds, and the image frequency of the road test video is 10HZ.

6. A device for outputting low-latency driving trajectory information of a vehicle based on RTK data, characterized in that: It includes a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, it is used to implement a method for outputting low-latency driving trajectory information of a vehicle based on RTK data as described in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, a method for outputting low-latency driving trajectory information of a vehicle based on RTK data as described in any one of claims 1 to 5 is implemented.

Images