A method, system and device for detecting the clock synchronization accuracy of roadside perception devices

Abstract

The present invention provides a method, system and device for detecting the clock synchronization accuracy of roadside perception devices. A testing machine synchronously receives the sensing data of a test vehicle sensed by the roadside perception device to be tested, the video data of the test vehicle captured by a test camera, and the reference positioning data and corresponding reference time of the test vehicle recorded by a real-time kinematic positioning subsystem. The testing machine obtains the critical point timestamp when the roadside perception device to be tested first senses the test vehicle and the corresponding critical point video frame in the video data, determines the critical point positioning based on the critical point video frame, and finds the reference time corresponding to the point corresponding to it in the reference positioning data as the standard timestamp. The difference between the standard timestamp and the critical point timestamp is used as the clock synchronization accuracy deviation of the roadside perception device to be tested. The present invention can perform clock synchronization accuracy testing without changing the program of the device to be tested.

Description

Technical Field

[0001] The present invention relates to the technical field of roadside perception, and in particular, to a method, system and device for detecting the clock synchronization accuracy of roadside perception devices. Background Art

[0002] Currently, the clock synchronization accuracy index of roadside perception devices is mainly tested using a clock synchronization tester. During the test, the tester sends a message as a test request message, which is sent in a multicast manner. After the master clock of the tester and the device under test receive the test request message, they stamp their respective local timestamps into the test response message, and then return the test response message to the tester respectively. After the tester receives the test response message, it extracts the timestamp, and the difference between the timestamps of the device under test and the master clock is the clock synchronization deviation to be tested. This test method requires the device under test to develop corresponding functions to cooperate with the test, and is not very suitable for the acceptance test of the deployed device under test.

[0003] Therefore, there is an urgent need for a method that can achieve clock synchronization accuracy testing without changing the program of the device under test. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, system and device for detecting the clock synchronization accuracy of roadside perception devices to eliminate or improve one or more defects existing in the prior art, and to solve the problem that the prior art cannot achieve the detection of the clock synchronization accuracy of roadside perception devices in the deployed state.

[0005] On the one hand, the present invention provides a method for detecting the clock synchronization accuracy of roadside perception devices, which is used to be executed on a test machine. The test machine is connected to the roadside perception device under test, a test camera and a real-time kinematic positioning subsystem installed on a test vehicle. There are standard position scales within the sensing range of the roadside perception device under test. The method includes the following steps:

[0006] Send a test initialization instruction to the roadside perception device under test, the test camera and the real-time kinematic positioning subsystem to instruct power-on and self-check.

[0007] Send a test instruction to the roadside perception device under test, the test camera and the real-time kinematic positioning subsystem to synchronously initiate a test.

[0008] During the process that the test vehicle passes through the sensing area of the to-be-tested roadside sensing device along a preset route, receive the sensing data of the test vehicle from the to-be-tested roadside sensing device at a first set frequency, where the sensing data includes interaction data of the test vehicle and the time stamps corresponding to the respective interaction data; receive the video data captured by the test camera for the sensing area at a second set frequency, and receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time;

[0009] Align the sensing data and the video data with the local time of the tester, find the critical-point video frame corresponding to the moment when the to-be-tested roadside sensing device first senses the test vehicle, and obtain the critical-point time stamp recorded in the corresponding sensing data when the test vehicle is first sensed;

[0010] Determine the critical-point positioning of the test vehicle according to the standard position scale recorded in the critical-point video frame;

[0011] Find the reference time corresponding to the critical-point positioning in the reference positioning data to obtain the standard time stamp;

[0012] Take the difference between the standard time stamp and the critical-point time stamp as the clock synchronization accuracy deviation of the to-be-tested roadside sensing device.

[0013] In some embodiments, the to-be-tested roadside sensing device is an ETC transaction antenna, and a test on-vehicle tag is loaded on the test vehicle;

[0014] The method further includes: preloading the relative position information between the test on-vehicle tag and the real-time kinematic positioning subsystem, and determining a positioning offset for the real-time kinematic positioning subsystem to add the positioning offset to the collected positioning data to obtain the reference positioning data of the on-vehicle tag.

[0015] In some embodiments, the first set frequency is less than or equal to the second set frequency, and the second set frequency is less than or equal to the third set frequency.

[0016] In some embodiments, the method further includes: having the test vehicle pass through the sensing area of the to-be-tested roadside sensing device along the preset route at different speeds multiple times, respectively detecting the corresponding clock synchronization accuracy deviations and then taking the average to obtain the standard clock synchronization accuracy deviation.

[0017] In some embodiments, the method further includes: the test vehicle travels through the sensing area of the road-side sensing device to be tested along a preset route at different speeds multiple times, and after detecting the corresponding clock synchronization accuracy deviation respectively, calculates the standard deviation value of each clock synchronization accuracy deviation. When the standard deviation value is greater than a first set value, the detection process is terminated and an alarm prompt message is generated.

[0018] In some embodiments, after determining the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame, it further includes:

[0019] Obtain the rated sensing range of the road-side sensing device to be tested, and estimate the estimated sensing positioning of the test vehicle that can be sensed according to the rated sensing range;

[0020] Calculate the position deviation between the estimated sensing positioning and the critical point positioning. If the position deviation is greater than a second set value, the detection process is terminated and an alarm prompt message is generated.

[0021] In some embodiments, the method further includes performing timing processing on the road-side sensing device to be tested according to the clock synchronization accuracy deviation.

[0022] On the other hand, the present invention also provides a road-side sensing device clock synchronization accuracy detection system, and the system includes:

[0023] A road-side sensing device to be tested, which is used to sense a test vehicle;

[0024] A test camera, which is used to photograph the sensing area of the road-side sensing device to be tested and record the process of the test vehicle passing through the sensing area;

[0025] A real-time kinematic positioning subsystem, which is installed on the test vehicle and records the reference positioning data of the test vehicle and marks the corresponding reference time based on real-time kinematic positioning technology;

[0026] A testing machine, which is connected to the roadside sensing device to be tested, the testing camera, and the real-time kinematic positioning subsystem; the testing machine is configured to receive the sensing data of the roadside sensing device to be tested for the test vehicle at a first set frequency during the process that the test vehicle travels through the sensing area of the roadside sensing device to be tested along a preset route, where the sensing data includes interaction data with the test vehicle and the timestamps corresponding to each piece of interaction data; receive the video data captured by the testing camera for the sensing area at a second set frequency, receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time; align the sensing data and the video data with the local time of the testing machine, find the critical point video frame corresponding to the moment when the roadside sensing device to be tested first senses the test vehicle, and obtain the critical point timestamp recorded in the corresponding sensing data when the test vehicle is first sensed; determine the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame; find the reference time corresponding to the critical point positioning in the reference positioning data to obtain the standard timestamp; and take the difference between the standard timestamp and the critical point timestamp as the clock synchronization accuracy deviation of the roadside sensing device to be tested.

[0027] On the other hand, the present invention further provides a device for detecting the clock synchronization accuracy of a roadside sensing device, including a processor and a memory, where computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the above method.

[0028] On the other hand, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0029] The beneficial effects of the present invention at least include:

[0030] In the method, system and device for detecting the clock synchronization accuracy of the roadside sensing device of the present invention, the testing machine synchronously receives the sensing data of the roadside sensing device to be tested for the test vehicle, the video data of the test vehicle captured by the testing camera, and the reference positioning data of the test vehicle and the corresponding reference time recorded by the real-time kinematic positioning subsystem. The testing machine obtains the critical point timestamp when the roadside sensing device to be tested first senses the test vehicle and the corresponding critical point video frame in the video data, determines the critical point positioning based on the critical point video frame, and finds the reference time corresponding to the corresponding point in the reference positioning data as the standard timestamp. The difference between the standard timestamp and the critical point timestamp is used as the clock synchronization accuracy deviation of the roadside sensing device to be tested. The present invention can perform clock synchronization accuracy testing without changing the program of the device to be tested.

[0031] Additional advantages, objects, and features of the present invention will be partly set forth in the description which follows, and will partly become obvious to those of ordinary skill in the art upon examination of the following, or may be learned by practice of the present invention. The objects and other advantages of the present invention may be realized and obtained by the structure particularly pointed out in the specification and the drawings.

[0032] Those skilled in the art will understand that the objects and advantages that can be achieved by the present invention are not limited to those specifically described above, and the above and other objects that the present invention can achieve will be more clearly understood according to the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and do not limit the present invention. In the drawings:

[0034] Figure 1 It is a schematic flowchart of a method for detecting the clock synchronization accuracy of a roadside perception device according to an embodiment of the present invention.

[0035] Figure 2 It is a schematic flowchart of a method for testing the clock synchronization accuracy based on the proximal critical point of the detection area of a roadside perception device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] To make the objects, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but do not limit the present invention.

[0037] Here, it should also be noted that in order to avoid obscuring the present invention with unnecessary details, only the structures and / or processing steps closely related to the solution of the present invention are shown in the drawings, and other details less related to the present invention are omitted.

[0038] It should be emphasized that the term "comprising / including" when used herein refers to the presence of features, elements, steps, or components, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0039] Here, it should also be noted that if not specifically stated, the term "connection" in this document can not only refer to direct connection, but also represent indirect connection with an intermediate.

[0040] In a lane control system such as ETC (Electronic Toll Collection), multiple devices need to work together, which requires time synchronization of each device. The detection of the clock synchronization accuracy of roadside sensing devices is usually processed with the help of a clock synchronization tester. This method requires corresponding function development and preloading of the device under test to cooperate with the test, so it cannot be directly applied to devices that have been deployed. This application constructs a complete set of test schemes for the clock synchronization accuracy of roadside sensing devices, enabling the detection of the clock synchronization accuracy of roadside sensing devices that have been deployed without additional function configuration.

[0041] The roadside sensing devices described in this application may include lidar, millimeter-wave radar, cameras, edge computing nodes, ETC transaction antennas, license plate recognizers, inductive loops, or other devices related to lane transactions.

[0042] Specifically, the present invention provides a method for detecting the clock synchronization accuracy of roadside sensing devices. The method is executed on a test machine, which is connected to the device under test of the roadside sensing device, a test camera, and a real-time kinematic positioning subsystem installed on a test vehicle. Standard position scales are set within the sensing range of the device under test of the roadside sensing device. As Figure 1 shown, the method includes the following steps S101 to S107:

[0043] Step S101: Send a test initialization instruction to the device under test of the roadside sensing device, the test camera, and the real-time kinematic positioning subsystem to instruct power-on and self-check.

[0044] Step S102: Send a test instruction to the device under test of the roadside sensing device, the test camera, and the real-time kinematic positioning subsystem to synchronously initiate the test.

[0045] Step S103: During the process of the test vehicle passing through the sensing area of the device under test of the roadside sensing device along a preset route, receive the sensing data of the test vehicle from the device under test of the roadside sensing device at a first set frequency. The sensing data includes interaction data with the test vehicle and time stamps corresponding to each interaction data; receive the video data of the sensing area captured by the test camera at a second set frequency, and receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time.

[0046] Step S104: Align the sensing data and video data with the local time of the test machine as the standard, find the critical point video frame corresponding to the first time the device under test of the roadside sensing device senses the test vehicle, and obtain the critical point time stamp recorded in the corresponding sensing data when the test vehicle is first sensed.

[0047] Step S105: Determine the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame.

[0048] Step S106: Search for the reference time corresponding to the critical point positioning in the reference positioning data to obtain the standard timestamp.

[0049] Step S107: Subtract the standard timestamp from the critical point timestamp, and use the result as the clock synchronization accuracy deviation of the measured roadside sensing device.

[0050] In steps S101 to S107 of this embodiment, during the process of the vehicle passing through the driving lane, the position where the vehicle generates sensing interaction with the measured roadside sensing device in the lane is relatively determined. For example, the sensing range of the ETC transaction antenna is relatively fixed, and each time the vehicle passes, the initial trigger and interaction position are also relatively determined. Similarly, roadside sensing devices including lidar, millimeter-wave radar, cameras, edge computing nodes, and inductive loops also have similar properties. In order to efficiently detect the clock synchronization accuracy of the deployed roadside sensing devices, this application uses a real-time kinematic (RTK) positioning subsystem installed on a test vehicle to record the reference position information and the corresponding reference time of the test vehicle, and completes the detection of the clock synchronization accuracy by querying the difference between the timestamp of the measured roadside sensing device and the reference time when the test vehicle is at a specified position.

[0051] In the preparatory work, the measured roadside sensing device is installed in the lane according to general layout requirements, and the test camera conducts comprehensive video monitoring of the sensing area of the measured roadside sensing device. In order to calibrate the specific position of the test vehicle within the sensing area, it is also necessary to mark the position of the sensing area. In this embodiment, by laying out standard position scales, the vehicle position information is synchronously recorded in the video data collected by the test camera. The standard position scales can be set to include scale markings in the horizontal and vertical directions. In other embodiments, an infrared rangefinder can also be set on the camera to synchronously record the relative distance from the infrared rangefinder to a specified position on the test vehicle. Based on the relatively fixed position of the infrared rangefinder, the accurate position of the test vehicle can be deduced in combination with this relative distance.

[0052] In this embodiment, the test machine can use the lane control machine already deployed in the lane, or a dedicated test machine can be assumed separately. The test machine can use a single-chip microcomputer, a computer, or other electronic devices that can load and run computer programs.

[0053] In steps S101 to 102, the test machine instructs the measured roadside sensing device, the test camera, and the real-time kinematic positioning subsystem to perform power-on self-check through test initialization instructions to wait for testing. The initialization process can include preloading of test parameters. After completing the self-check, a test is initiated based on the test instructions.

[0054] In step S103, the test vehicle travels along a fixed route to ensure the accuracy of the test. Specifically, the test vehicle is required to travel at a constant speed, which can be set with reference to the sampling frequencies of the roadside sensing device under test, the test camera, and the real-time kinematic positioning subsystem in the system. When the sampling frequency is high, the speed of the test vehicle can be appropriately increased; when the sampling frequency is low, the speed of the test vehicle can be appropriately decreased. Specifically, the speed of the test vehicle can be set at 30 - 40 KM / h according to the general vehicle passing speed. The sampling frequencies of the roadside sensing device under test, the test camera, and the real-time kinematic positioning subsystem can adopt the preset values of the devices. Generally, it is required that the sampling frequency of the roadside sensing device under test is less than or equal to the sampling frequency of the test camera, and the sampling frequency of the test camera is less than or equal to the sampling frequency of the real-time kinematic positioning subsystem to ensure detection can be achieved. That is, the first set frequency is less than or equal to the second set frequency, and the second set frequency is less than or equal to the third set frequency.

[0055] In some embodiments, the sampling frequencies of the roadside sensing device under test, the test camera, and the real-time kinematic positioning subsystem can be set to be the same. Since the sensing range of the roadside sensing device under test is fixed, the position when it first senses the test vehicle is relatively fixed. To simplify the process, in this embodiment, the position when the test vehicle is first sensed is directly used as the critical point for scaling and comparison. The sensing data records the interaction data and its timestamp, the video data records the images in the sensing area and the timestamp of each frame, and the reference positioning data marks the corresponding reference time to calibrate the precise position of the test vehicle and the time at that position.

[0056] In step S104, the sensing data and the video data are aligned. Since this is directly collected by the test machine, it can be scaled based on the local time of the test machine. When the roadside sensing device under test first senses the test vehicle, the time in the roadside sensing device under test is recorded as the critical point timestamp. When the sensing data and the video data are aligned, the critical point video frame when the test vehicle is first sensed is searched for.

[0057] In steps S105 - S107, the critical point positioning of the test vehicle can be determined in the critical point video frame by comparing with the set standard position scale. The corresponding value of the critical point positioning coordinate in the reference positioning data is searched for and the corresponding standard timestamp is marked. At this time, the times recorded by the roadside sensing device under test and the roadside sensing device at the same critical point positioning are obtained, and the difference can be used to obtain the clock synchronization accuracy deviation of the roadside sensing device under test.

[0058] In some embodiments, the roadside sensing device under test is an ETC transaction antenna, and a test vehicle-mounted tag is loaded on the test vehicle. In this case, the sensing position of the test vehicle needs to be accurate to the vehicle-mounted tag, so it is also necessary to further supplement the relative position deviation between the vehicle-mounted tag and the real-time kinematic positioning subsystem. Therefore, the method further includes: preloading the relative position information between the test vehicle-mounted tag and the real-time kinematic positioning subsystem, and determining the positioning offset for the real-time kinematic positioning subsystem to add the positioning offset to the collected positioning data to obtain the reference positioning data of the vehicle-mounted tag.

[0059] Similarly, in some other embodiments, if the roadside sensing device under test is a license plate recognizer, the relative position information between the license plate and the real-time kinematic positioning subsystem needs to be corrected. If the roadside sensing device under test is a ground loop, the relative position information between the response area where the test vehicle can be sensed and the real-time kinematic positioning subsystem needs to be corrected, and the position information is corrected.

[0060] In some embodiments, the method further includes: the test vehicle travels along a preset route through the sensing area of the roadside sensing device under test at different speeds multiple times, and respectively detects the corresponding clock synchronization accuracy deviation and then calculates the average value to obtain the standard clock synchronization accuracy deviation. This embodiment is mainly to improve the detection accuracy by averaging multiple measurements.

[0061] In some embodiments, the method further includes: the test vehicle travels along a preset route through the sensing area of the roadside sensing device under test at different speeds multiple times, and respectively detects the corresponding clock synchronization accuracy deviation, and then calculates the standard deviation value of each clock synchronization accuracy deviation. When the standard deviation value is greater than the first set value, the detection process is terminated and an alarm prompt message is generated. In this embodiment, considering that the sensing position of the roadside sensing device under test relative to the test vehicle is relatively fixed, if the deviation is too large after multiple detections, it indicates that there is a fault in the detection system or the roadside sensing device under test has a fault, and an alarm prompt is given.

[0062] In some embodiments, after determining the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame, steps S201 to S202 are further included:

[0063] Step S201: Obtain the rated sensing range of the roadside sensing device under test, and estimate the estimated sensing positioning where the test vehicle can be sensed according to the rated sensing range.

[0064] Step S202: Calculate the position deviation between the estimated sensing positioning and the critical point positioning. If the position deviation is greater than the second set value, the detection process is terminated and an alarm prompt message is generated.

[0065] In this embodiment, considering that the perceived position of the roadside perception device under test relative to the test vehicle is relatively fixed, if the position deviation between the predicted perception positioning and the critical point positioning in the actual detection process is too large, it proves that the roadside perception device under test is faulty and an alarm prompt is required.

[0066] In some embodiments, the method further includes performing timing processing on the roadside perception device under test according to the clock synchronization accuracy deviation.

[0067] On the other hand, the present invention also provides a roadside perception device clock synchronization accuracy detection system, which includes: a roadside perception device under test, a test camera, a real-time kinematic positioning subsystem, and a test machine.

[0068] The roadside perception device under test is used to sense the test vehicle. The test camera is used to photograph the sensing area of the roadside perception device under test and record the process of the test vehicle passing through the sensing area. The real-time kinematic positioning subsystem is installed on the test vehicle and records the reference positioning data of the test vehicle and marks the corresponding reference time based on the real-time kinematic positioning technology.

[0069] The test machine is connected to the roadside perception device under test, the test camera, and the real-time kinematic positioning subsystem; the test machine is used to receive the sensing data of the test vehicle from the roadside perception device under test at a first set frequency during the process of the test vehicle passing through the sensing area of the roadside perception device under test along a preset route, and the sensing data includes interaction data with the test vehicle and the time stamps corresponding to each interaction data; receive the video data of the sensing area photographed by the test camera at a second set frequency, receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time; align the sensing data and the video data with the local time of the test machine, find the critical point video frame corresponding to the first time the roadside perception device under test senses the test vehicle, and obtain the critical point time stamp recorded in the sensing data at the first time of sensing the test vehicle; determine the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame; find the reference time corresponding to the critical point positioning in the reference positioning data and obtain the standard time stamp; calculate the difference between the standard time stamp and the critical point time stamp as the clock synchronization accuracy deviation of the roadside perception device under test.

[0070] Specifically, the description of the roadside perception device clock synchronization accuracy detection system can refer to the above text.

[0071] On the other hand, the present invention also provides a roadside perception device clock synchronization accuracy detection device, including a processor and a memory, wherein computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the above method.

[0072] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0073] The present invention will be described below in conjunction with a specific embodiment:

[0074] To solve the problem of clock synchronization accuracy testing without changing the program of the device under test, this embodiment provides a clock synchronization accuracy testing method based on the proximal critical point of the detection area of the roadside perception device. This method runs on a test computer, and the test computer is connected to a test camera, the device under test, and a vehicle-mounted true value system (RTK real-time kinematic positioning subsystem). The test camera captures the proximal detection area of the device under test, as Figure 2 shown, and the method includes steps S301 to S307:

[0075] Step S301: Lay a meter stick in the horizontal and vertical directions in the proximal detection area of the device under test, and the test camera captures the proximal detection area of the device under test.

[0076] Step S302: The vehicle-mounted true value system is installed on the test vehicle, and the lane bilateral cone barrels prompt and control the driving route of the test vehicle.

[0077] Step S303: Power on the device under test, the test camera, and the vehicle-mounted true value system and ensure they are working properly. The test computer simultaneously monitors the detection data output interface of the device under test and the test camera interface and records the screen.

[0078] Step S304: The test vehicle equipped with the vehicle-mounted true value system reversely and slowly drives to the proximal detection area of the device under test, and the computer stops recording the screen after the test vehicle passes through the proximal detection area of the device under test.

[0079] Step S305: Play the computer screen recording frame by frame until the device under test first outputs the detection information of the test vehicle. According to the scale information of the test vehicle relative to the horizontal and vertical meter sticks in the test camera image corresponding to this frame, obtain the proximal critical point information of the device under test detecting the test vehicle in the actual test environment.

[0080] Step S306: Collect the position information of this proximal critical point with the vehicle-mounted true value system in the actual test environment, and the test vehicle drives through the proximal recognition area of the device under test again along the previous test route.

[0081] Step S307: Export the position information of the vehicle in this round of test recorded by the vehicle ground truth system and the device under test, match the time when the test vehicle passes the proximal critical point according to the collected position information, and calculate the difference between this time and the time when the device under test first outputs the test vehicle in this test. This time difference is the clock synchronization accuracy.

[0082] In this embodiment, the proximal critical point of the detection area of the roadside sensing device is stable, that is, when the same traffic participant passes the proximal part of the detection area of the roadside sensing device along the same route in reverse each time, the position where the roadside sensing device under test first detects the traffic participant is the same. The vehicle ground truth system collects the position information of the proximal critical point of the detection area of the device under test, and calculates the difference between the time when the vehicle ground truth system passes through the position of this critical point and the time when the device under test first outputs the test vehicle. This time difference is the clock synchronization accuracy. The present invention solves the problem of clock synchronization accuracy test without changing the program of the device under test.

[0083] In summary, in the method, system and device for detecting the clock synchronization accuracy of the roadside sensing device according to the present invention, the test machine synchronously receives the sensing data of the test vehicle by the roadside sensing device under test, the video data of the test vehicle captured by the test camera, and the reference positioning data and the corresponding reference time of the test vehicle recorded by the real-time kinematic positioning subsystem. The test machine obtains the critical point timestamp when the roadside sensing device under test first senses the test vehicle and the corresponding critical point video frame in the video data, determines the critical point positioning based on the critical point video frame, and finds the reference time corresponding to the point corresponding to it in the reference positioning data as the standard timestamp. The difference between the standard timestamp and the critical point timestamp is used as the clock synchronization accuracy deviation of the roadside sensing device under test. The present invention can perform the clock synchronization accuracy test without changing the program of the device under test.

[0084] Those of ordinary skill in the art should understand that the various exemplary components, systems, and methods described in connection with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Specifically, whether to implement in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave on a transmission medium or a communication link.

[0085] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0086] In the present invention, features described and / or illustrated for one embodiment can be used in the same or similar manner in one or more other embodiments, and / or combined with the features of other embodiments or replace the features of other embodiments.

[0087] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, various changes and modifications can be made to the embodiments of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting the clock synchronization accuracy of roadside perception devices, characterized in that, The method is used to be executed on a test machine, which is connected to a roadside sensing device under test, a test camera, and a real-time kinematic positioning subsystem installed on a test vehicle. There are standard position scales within the sensing range of the roadside sensing device under test. The method includes the following steps: Send test initialization instructions to the roadside sensing device under test, the test camera, and the real-time kinematic positioning subsystem to instruct power-on and self-check. Send test instructions to the roadside sensing device under test, the test camera, and the real-time kinematic positioning subsystem to synchronously initiate a test. During the process that the test vehicle travels through the sensing area of the roadside sensing device under test along a preset route, receive the sensing data of the test vehicle from the roadside sensing device under test at a first set frequency. The sensing data includes interaction data with the test vehicle and time stamps corresponding to each piece of interaction data. Receive the video data of the sensing area captured by the test camera at a second set frequency, and receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time. Align the sensing data and the video data based on the local time of the test machine, find the critical-point video frame corresponding to the moment when the roadside sensing device under test first senses the test vehicle, and obtain the critical-point time stamp recorded in the corresponding sensing data when the test vehicle is first sensed. Determine the critical-point positioning of the test vehicle according to the standard position scale recorded in the critical-point video frame. Find the reference time corresponding to the critical-point positioning in the reference positioning data to obtain the standard time stamp. Take the difference between the standard time stamp and the critical-point time stamp as the clock synchronization accuracy deviation of the roadside sensing device under test.

2. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 1, characterized in that The roadside sensing device under test is an ETC transaction antenna, and a test on-vehicle tag is installed on the test vehicle. The method further includes: preloading the relative position information between the test on-vehicle tag and the real-time kinematic positioning subsystem, and determining the positioning offset for the real-time kinematic positioning subsystem to add the positioning offset to the collected positioning data to obtain the reference positioning data of the on-vehicle tag.

3. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 1, characterized in that The first set frequency is less than or equal to the second set frequency, and the second set frequency is less than or equal to the third set frequency.

4. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 1, characterized in that The method further includes: having the test vehicle travel through the sensing area of the roadside sensing device under test along the preset route multiple times at different speeds, respectively detecting the corresponding clock synchronization accuracy deviations, and then taking the average to obtain the standard clock synchronization accuracy deviation.

5. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 4, characterized in that The method further includes: having the test vehicle travel through the sensing area of the roadside sensing device under test along the preset route multiple times at different speeds, respectively detecting the corresponding clock synchronization accuracy deviations, and then calculating the standard deviation value of each clock synchronization accuracy deviation. When the standard deviation value is greater than a first set value, terminate the detection process and generate an alarm prompt message.

6. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 1, wherein After determining the critical-point positioning of the test vehicle according to the standard position scale recorded in the critical-point video frame, it further includes: Obtain the rated sensing range of the to-be-tested roadside sensing device, and estimate the estimated sensing positioning of the test vehicle that can be sensed according to the rated sensing range; Calculate the position deviation between the estimated sensing positioning and the critical point positioning. If the position deviation is greater than the second set value, terminate the detection process and generate an alarm prompt message.

7. The method for detecting the clock synchronization accuracy of the roadside perception device according to claim 1, wherein The method further includes performing timing processing on the to-be-tested roadside sensing device according to the clock synchronization accuracy deviation.

8. A road-side perception device clock synchronization accuracy detection system, characterized in that The system includes: A to-be-tested roadside sensing device for sensing a test vehicle; A test camera for photographing the sensing area of the to-be-tested roadside sensing device and recording the process of the test vehicle passing through the sensing area; A real-time kinematic positioning subsystem mounted on the test vehicle and recording the reference positioning data of the test vehicle and marking the corresponding reference time based on real-time kinematic positioning technology; A tester connected to the to-be-tested roadside sensing device, the test camera, and the real-time kinematic positioning subsystem; the tester is configured to receive the sensing data of the test vehicle from the to-be-tested roadside sensing device at a first set frequency during the process of the test vehicle passing through the sensing area of the to-be-tested roadside sensing device along a preset route, where the sensing data includes interaction data with the test vehicle and the time stamps corresponding to each interaction data; receive the video data of the sensing area photographed by the test camera at a second set frequency, receive the reference positioning data of the test vehicle collected by the real-time kinematic positioning subsystem at a third set frequency and mark the corresponding reference time; align the sensing data and the video data with the local time of the tester, find the critical point video frame corresponding to the moment when the to-be-tested roadside sensing device first senses the test vehicle, and obtain the critical point time stamp recorded in the corresponding sensing data when the test vehicle is first sensed; determine the critical point positioning of the test vehicle according to the standard position scale recorded in the critical point video frame; find the reference time corresponding to the critical point positioning in the reference positioning data and obtain the standard time stamp; calculate the difference between the standard time stamp and the critical point time stamp as the clock synchronization accuracy deviation of the to-be-tested roadside sensing device.

9. A device for detecting the clock synchronization accuracy of a roadside perception device, comprising a processor and a memory, characterized in that, Computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images