Data verification method, device, equipment and readable storage medium

Abstract

This invention provides a data verification method, apparatus, device, and readable storage medium. The method includes: overlaying point cloud data and images collected by sensor devices with images collected by an external environment camera, wherein the sensor devices include LiDAR, a forward-looking camera, and millimeter-wave radar; if the point cloud data and images collected by the sensor devices overlap with the images collected by the external environment camera, then the point cloud data and images collected by the sensor devices are determined to be correct; if the point cloud data and images collected by the sensor devices do not overlap with the images collected by the external environment camera, then the point cloud data and images collected by the sensor devices are determined to be incorrect. This invention solves the problem that the lack of verification of collected data leads to unsatisfactory vehicle monitoring and easily biased data analysis results.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a data verification method, apparatus, device, and readable storage medium. Background Technology

[0002] In the development of intelligent driving, vehicles need to collect data in all directions, and vehicle monitoring and data analysis are based on the collected data. Currently, this is mainly achieved by using external data acquisition equipment to access a complete set of sensor information and vehicle information. However, because the collected data is not verified, the vehicle monitoring is not ideal, and the data analysis results are prone to deviation. Therefore, how to quickly verify the data has become an urgent technical problem to be solved. Summary of the Invention

[0003] The main objective of this invention is to provide a data verification method, apparatus, device, and readable storage medium, which aims to quickly verify data.

[0004] In a first aspect, the present invention provides a data verification method, the data verification method comprising:

[0005] The point cloud data and images collected by sensor devices are superimposed with images collected by external environment cameras. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar.

[0006] If the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera, then the point cloud data and images collected by the sensor device are correct.

[0007] If the point cloud data and images collected by the sensor device cannot overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are incorrect.

[0008] Optionally, after determining that the point cloud data and images acquired by the sensor device are correct, the process includes:

[0009] The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit;

[0010] If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission.

[0011] Optionally, after the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following steps are included:

[0012] If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices are obtained from the electronic control unit and the host computer processing module.

[0013] If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is confirmed to be correct.

[0014] Optionally, after the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following steps are included:

[0015] The host computer processing module sends the vehicle's positioning data, map information of the vehicle's location, and point cloud data and images collected by the sensor devices to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene.

[0016] Optionally, after the step of overlaying the point cloud data and images acquired by the sensor device with the images acquired by the external environment camera, the method includes:

[0017] The degree of superposition of point cloud data collected by lidar, images collected by forward-looking camera, point cloud data collected by millimeter-wave radar, and images collected by external environment camera is obtained.

[0018] The accuracy of LiDAR, forward-looking cameras, and millimeter-wave radar is determined by the degree of superposition; the higher the degree of superposition, the higher the accuracy.

[0019] Secondly, the present invention also provides a data verification device, the data verification device comprising:

[0020] The overlay module is used to overlay point cloud data and images collected by sensor devices with images collected by external environment cameras. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar.

[0021] The first determining module is used to determine that the collected data is correct if the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera.

[0022] The second determining module is used to determine that the collected data is incorrect if the point cloud data and images collected by the sensor device do not overlap with the images collected by the external environment camera.

[0023] Optionally, the data verification device further includes an inspection module for:

[0024] The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit;

[0025] If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission.

[0026] Optionally, the data verification device further includes an inspection module, which is also used for:

[0027] If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices are obtained from the electronic control unit and the host computer processing module.

[0028] If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is confirmed to be correct.

[0029] Thirdly, the present invention also provides a data verification device, the data verification device including a processor, a memory, and a data verification program stored in the memory and executable by the processor, wherein when the data verification program is executed by the processor, it implements the steps of the data verification method as described above.

[0030] Fourthly, the present invention also provides a readable storage medium storing a data verification program, wherein when the data verification program is executed by a processor, it implements the steps of the data verification method described above.

[0031] In this invention, point cloud data and images collected by sensor devices, including LiDAR, a forward-looking camera, and millimeter-wave radar, are overlaid with images collected by an external environment camera. If the point cloud data and images collected by the sensor devices overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered correct. If the point cloud data and images collected by the sensor devices do not overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered incorrect. This invention simplifies the process by overlaying the point cloud data and images collected by the sensor devices with the images collected by the external environment camera. The overlay result allows for the verification of the point cloud data and images collected by the sensor devices, solving the problem of unsatisfactory vehicle monitoring and biased data analysis results due to the lack of verification of the collected data. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the hardware structure of the data verification device involved in the embodiment of the present invention;

[0033] Figure 2 This is a flowchart illustrating the first embodiment of the data verification method of the present invention;

[0034] Figure 3 This is a flowchart illustrating the second embodiment of the data verification method of the present invention;

[0035] Figure 4 This is a flowchart illustrating the third embodiment of the data verification method of the present invention;

[0036] Figure 5 This is a schematic diagram of the functional modules of an embodiment of the data verification device of the present invention.

[0037] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0038] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0039] In a first aspect, embodiments of the present invention provide a data verification device, which may be a device with data processing capabilities such as a personal computer (PC), a laptop computer, or a server.

[0040] Reference Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of the data verification device involved in the embodiment of the present invention. In this embodiment, the data verification device may include a processor 1001 (e.g., a Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize communication between these components; the user interface 1003 may include a display screen or an input unit such as a keyboard; the network interface 1004 may optionally include a standard wired interface or a wireless interface (e.g., Wireless Fidelity, Wi-Fi); the memory 1005 may be high-speed random access memory (RAM) or stable memory (non-volatile memory), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that… Figure 1 The hardware structure shown does not constitute a limitation of the invention and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0041] Continue to refer to Figure 1 , Figure 1 The memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a data verification program. The processor 1001 can call the data verification program stored in the memory 1005 and execute the data verification method provided in this embodiment of the invention.

[0042] Secondly, embodiments of the present invention provide a data verification method.

[0043] In one embodiment, reference is made to Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the data verification method of the present invention. Figure 2 As shown, the data validation method includes:

[0044] Step S10: Overlay the point cloud data and images collected by the sensor devices with the images collected by the external environment camera. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar.

[0045] In this embodiment, point cloud data and images collected by sensor devices are acquired, namely point cloud data collected by LiDAR, images collected by a forward-looking camera, and point cloud data collected by millimeter-wave radar. The point cloud data collected by LiDAR, the images collected by the forward-looking camera, and the point cloud data collected by millimeter-wave radar are superimposed with images collected by an external environment camera for detection of the point cloud data and images collected by the sensor devices.

[0046] Step S20: If the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are correct.

[0047] In this embodiment, if the point cloud data and images collected by the sensor device, namely the point cloud data collected by the lidar, the images collected by the forward-looking camera, and the point cloud data collected by the millimeter-wave radar, overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are correct.

[0048] Step S30: If the point cloud data and images collected by the sensor device cannot overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are incorrect.

[0049] In this embodiment, if the point cloud data and images collected by the sensor device, i.e., the point cloud data collected by the lidar and / or the images collected by the forward-looking camera and / or the point cloud data collected by the millimeter-wave radar, do not overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are incorrect.

[0050] In this embodiment, point cloud data and images collected by sensor devices, including LiDAR, a forward-facing camera, and millimeter-wave radar, are overlaid with images collected by an external environment camera. If the point cloud data and images collected by the sensor devices overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered correct. If the point cloud data and images collected by the sensor devices do not overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered incorrect. This embodiment only requires overlaying the point cloud data and images collected by the sensor devices with the images collected by the external environment camera. Based on the overlay result, the point cloud data and images collected by the sensor devices can be confirmed, solving the problem of unsatisfactory vehicle monitoring and biased data analysis results due to the lack of data confirmation.

[0051] Furthermore, in one embodiment, reference is made to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the data verification method of the present invention. Figure 3 As shown, after confirming that the point cloud data and images collected by the sensor device are correct, the process includes:

[0052] Step S110: The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit;

[0053] Step S120: If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission.

[0054] In this embodiment, after confirming that the point cloud data and images collected by the sensor device are correct, the point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit. If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device were tampered with during the transmission from the sensor device to the electronic control unit or that the point cloud data and images collected by the sensor device were tampered with during the transmission from the electronic control unit to the host computer.

[0055] Furthermore, in one embodiment, reference continues to be made to... Figure 3 After the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following steps are included:

[0056] Step S130: If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then obtain the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices from the electronic control unit and the host computer processing module.

[0057] Step S140: If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is determined to be correct.

[0058] In this embodiment, if the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have not been tampered with during transmission. Then, the identification results of the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device are obtained by the electronic control unit and the host computer processing module. After the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device are collected, the host computer fusion playback system does not rely on any external devices. The external video information stream is directly played back on the host computer processing module via video. Specifically, for example, when displaying traffic cones on the roadside via video on the host computer processing module, the point cloud data of the traffic cones detected by millimeter-wave radar, the image of the traffic cones detected by the forward-facing camera, and the point cloud data of the traffic cones detected by lidar will all be presented simultaneously. Similarly, for lane markings, when displaying lane markings on the video, the lane marking image captured by the forward-facing camera and the lane marking data sent from the map information of the vehicle's location based on the vehicle's location data will all be presented for playback. The map information of the vehicle's location is high-precision map information.

[0059] If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is determined to be correct. That is, since the host computer processing module displays the traffic cones via video, if the recognition result output by the electronic control unit is also a traffic cone, then the electronic control unit is determined to be correct.

[0060] Furthermore, if the recognition result output by the electronic control unit is different from the recognition result output by the host computer processing module, it is determined that the verification algorithm of the electronic control unit is incorrect.

[0061] Further, in one embodiment, after the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following is included:

[0062] The host computer processing module sends the vehicle's positioning data, map information of the vehicle's location, and point cloud data and images collected by the sensor devices to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene.

[0063] In this embodiment, after the point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit, since the electronic control unit does not store the point cloud data and images collected by the sensor device, the host computer processing module sends the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene based on the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device.

[0064] Furthermore, relevant technical personnel can also check whether there are any faults in the autonomous driving algorithm during the vehicle's operation by reproducing the scenario. If there are faults, they will be repaired. After the software faults are repaired, the scenario will be reproduced again. If the reproduced scenario shows that the autonomous driving algorithm still has faults, the faults will continue to be repaired.

[0065] If no faults are found in the autonomous driving algorithm in the reproduced scenario, it is determined that the faults in the autonomous driving algorithm have been successfully repaired. By reproducing the scenario to detect whether the faults in the autonomous driving algorithm have been successfully repaired, it is not necessary to collect and analyze data again on the actual site, which reduces the detection cost and improves the detection efficiency.

[0066] Furthermore, in one embodiment, reference is made to Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the data verification method of the present invention. Figure 4 As shown, after the step of overlaying the point cloud data and images collected by the sensor device with the images collected by the external environment camera, the following steps are included:

[0067] Step S210: Obtain the superposition degree of point cloud data collected by lidar, image collected by forward-looking camera, and point cloud data collected by millimeter-wave radar with image collected by external environment camera.

[0068] Step S220: Determine the accuracy of the LiDAR, forward-looking camera, and millimeter-wave radar based on the degree of superposition. The higher the degree of superposition, the higher the accuracy.

[0069] In this embodiment, the point cloud data and images collected by the sensor device are superimposed with the images collected by the external environment camera to obtain the superposition degree of the point cloud data collected by the lidar, the images collected by the forward-looking camera, and the point cloud data collected by the millimeter-wave radar with the images collected by the external environment camera.

[0070] If the superposition degree between the point cloud data collected by the LiDAR and the image collected by the external environment camera is greater than that between the image collected by the forward-looking camera and the image collected by the external environment camera, and the superposition degree between the image collected by the forward-looking camera and the image collected by the external environment camera is greater than that between the point cloud data collected by the millimeter-wave radar and the image collected by the external environment camera, then the accuracy of the LiDAR is greater than that of the forward-looking camera, and the accuracy of the forward-looking camera is greater than that of the millimeter-wave radar. In other words, the higher the superposition degree, the higher the accuracy.

[0071] Thirdly, embodiments of the present invention also provide a data verification device.

[0072] In one embodiment, reference is made to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the data verification device of the present invention. Figure 5 As shown, the data verification device includes:

[0073] The overlay module 10 is used to overlay point cloud data and images collected by sensor devices with images collected by external environment cameras. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar.

[0074] In this embodiment, point cloud data and images collected by sensor devices are acquired, namely point cloud data collected by LiDAR, images collected by a forward-looking camera, and point cloud data collected by millimeter-wave radar. The point cloud data collected by LiDAR, the images collected by the forward-looking camera, and the point cloud data collected by millimeter-wave radar are superimposed with images collected by an external environment camera for detection of the point cloud data and images collected by the sensor devices.

[0075] The first determining module 20 is used to determine that the collected data is correct if the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera.

[0076] In this embodiment, if the point cloud data and images collected by the sensor device, namely the point cloud data collected by the lidar, the images collected by the forward-looking camera, and the point cloud data collected by the millimeter-wave radar, overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are correct.

[0077] The second determining module 30 is used to determine that the collected data is incorrect if the number of point clouds and the image collected by the sensor device cannot overlap with the image collected by the external environment camera.

[0078] In this embodiment, if the point cloud data and images collected by the sensor device, i.e., the point cloud data collected by the lidar and / or the images collected by the forward-looking camera and / or the point cloud data collected by the millimeter-wave radar, do not overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are incorrect.

[0079] Furthermore, in one embodiment, the data verification device further includes a determining module, used for:

[0080] The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit;

[0081] If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission.

[0082] In this embodiment, after confirming that the point cloud data and images collected by the sensor device are correct, the point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit. If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device were tampered with during the transmission from the sensor device to the electronic control unit or that the point cloud data and images collected by the sensor device were tampered with during the transmission from the electronic control unit to the host computer.

[0083] Furthermore, in one embodiment, the determining module is also configured to:

[0084] If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices are obtained from the electronic control unit and the host computer processing module.

[0085] If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is confirmed to be correct.

[0086] In this embodiment, if the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have not been tampered with during transmission. Then, the identification results of the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device are obtained by the electronic control unit and the host computer processing module. After the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device are collected, the host computer fusion playback system does not rely on any external devices. The external video information stream is directly played back on the host computer processing module via video. Specifically, for example, when displaying traffic cones on the roadside via video on the host computer processing module, the point cloud data of the traffic cones detected by millimeter-wave radar, the image of the traffic cones detected by the forward-facing camera, and the point cloud data of the traffic cones detected by lidar will all be presented simultaneously. Similarly, for lane markings, when displaying lane markings on the video, the lane marking image captured by the forward-facing camera and the lane marking data sent from the map information of the vehicle's location based on the vehicle's location data will all be presented for playback. The map information of the vehicle's location is high-precision map information.

[0087] If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is determined to be correct. That is, since the host computer processing module displays the traffic cones via video, if the recognition result output by the electronic control unit is also a traffic cone, then the electronic control unit is determined to be correct.

[0088] Furthermore, if the recognition result output by the electronic control unit is different from the recognition result output by the host computer processing module, it is determined that the verification algorithm of the electronic control unit is incorrect.

[0089] Furthermore, in one embodiment, the data verification device further includes a data transmission module, used for:

[0090] The host computer processing module sends the vehicle's positioning data, map information of the vehicle's location, and point cloud data and images collected by the sensor devices to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene.

[0091] In this embodiment, after the point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit, since the electronic control unit does not store the point cloud data and images collected by the sensor device, the host computer processing module sends the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene based on the vehicle's positioning data, the map information of the vehicle's location, and the point cloud data and images collected by the sensor device.

[0092] Furthermore, relevant technical personnel can also check whether there are any faults in the autonomous driving algorithm during the vehicle's operation by reproducing the scenario. If there are faults, they will be repaired. After the software faults are repaired, the scenario will be reproduced again. If the reproduced scenario shows that the autonomous driving algorithm still has faults, the faults will continue to be repaired.

[0093] If no faults are found in the autonomous driving algorithm in the reproduced scenario, it is determined that the faults in the autonomous driving algorithm have been successfully repaired. By reproducing the scenario to detect whether the faults in the autonomous driving algorithm have been successfully repaired, it is not necessary to collect and analyze data again on the actual site, which reduces the detection cost and improves the detection efficiency.

[0094] Furthermore, in one embodiment, the determining module is also configured to:

[0095] The degree of superposition of point cloud data collected by lidar, images collected by forward-looking camera, point cloud data collected by millimeter-wave radar, and images collected by external environment camera is obtained.

[0096] The accuracy of LiDAR, forward-looking cameras, and millimeter-wave radar is determined by the degree of superposition; the higher the degree of superposition, the higher the accuracy.

[0097] In this embodiment, the point cloud data and images collected by the sensor device are superimposed with the images collected by the external environment camera to obtain the superposition degree of the point cloud data collected by the lidar, the images collected by the forward-looking camera, and the point cloud data collected by the millimeter-wave radar with the images collected by the external environment camera.

[0098] If the superposition degree between the point cloud data collected by the LiDAR and the image collected by the external environment camera is greater than that between the image collected by the forward-looking camera and the image collected by the external environment camera, and the superposition degree between the image collected by the forward-looking camera and the image collected by the external environment camera is greater than that between the point cloud data collected by the millimeter-wave radar and the image collected by the external environment camera, then the accuracy of the LiDAR is greater than that of the forward-looking camera, and the accuracy of the forward-looking camera is greater than that of the millimeter-wave radar. In other words, the higher the superposition degree, the higher the accuracy.

[0099] In this embodiment, point cloud data and images collected by sensor devices, including LiDAR, a forward-facing camera, and millimeter-wave radar, are overlaid with images collected by an external environment camera. If the point cloud data and images collected by the sensor devices overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered correct. If the point cloud data and images collected by the sensor devices do not overlap with the images collected by the external environment camera, the point cloud data and images collected by the sensor devices are considered incorrect. This embodiment only requires overlaying the point cloud data and images collected by the sensor devices with the images collected by the external environment camera. Based on the overlay result, the point cloud data and images collected by the sensor devices can be confirmed, solving the problem of unsatisfactory vehicle monitoring and biased data analysis results due to the lack of data confirmation.

[0100] Fourthly, embodiments of the present invention also provide a readable storage medium.

[0101] The present invention provides a data verification program stored on a readable storage medium, wherein when the data verification program is executed by a processor, it implements the steps of the data verification method described above.

[0102] The method implemented when the data verification program is executed can be referred to in various embodiments of the data verification method of the present invention, and will not be repeated here.

[0103] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0104] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0105] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of the present invention.

[0106] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A data verification method, characterized in that, The data verification method includes: The point cloud data and images collected by sensor devices are superimposed with images collected by external environment cameras. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar. If the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera, then the point cloud data and images collected by the sensor device are correct. If the point cloud data and images collected by the sensor device cannot overlap with the images collected by the external environment camera, then it is determined that the point cloud data and images collected by the sensor device are incorrect. After confirming that the point cloud data and images collected by the sensor device are correct, the process includes: The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit; If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission. After the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following steps are included: If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices are obtained from the electronic control unit and the host computer processing module. If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is confirmed to be correct.

2. The data verification method as described in claim 1, characterized in that, After the step of sending the point cloud data and images collected by the sensor device to the host computer processing module via the electronic control unit, the following steps are included: The host computer processing module sends the vehicle's positioning data, map information of the vehicle's location, and point cloud data and images collected by the sensor devices to the electronic control unit in the order of collection, so that the electronic control unit can control the vehicle to reproduce the scene.

3. The data verification method as described in claim 1, characterized in that, After the step of overlaying the point cloud data and images acquired by the sensor device with the images acquired by the external environment camera, the following steps are included: The degree of superposition of point cloud data collected by lidar, images collected by forward-looking camera, point cloud data collected by millimeter-wave radar, and images collected by external environment camera is obtained. The accuracy of LiDAR, forward-looking cameras, and millimeter-wave radar is determined by the degree of superposition; the higher the degree of superposition, the higher the accuracy.

4. A data verification device, characterized in that, The data verification device includes: The overlay module is used to overlay point cloud data and images collected by sensor devices with images collected by external environment cameras. The sensor devices include LiDAR, forward-looking camera and millimeter-wave radar. The first determining module is used to determine that the collected data is correct if the point cloud data and images collected by the sensor device overlap with the images collected by the external environment camera. The second determining module is used to determine that the collected data is incorrect if the point cloud data and images collected by the sensor device cannot overlap with the images collected by the external environment camera. The data verification device further includes a verification module for: The point cloud data and images collected by the sensor device are sent to the host computer processing module through the electronic control unit; If the point cloud data and images received by the host computer processing module are different from those received by the electronic control unit, it is determined that the point cloud data and images collected by the sensor device have been tampered with during transmission. The data verification device further includes an inspection module, which is also used for: If the point cloud data and images received by the host computer processing module are the same as those received by the electronic control unit, then the positioning data of the vehicle, the map information of the vehicle's location, and the recognition results of the point cloud data and images collected by the sensor devices are obtained from the electronic control unit and the host computer processing module. If the recognition result output by the electronic control unit is the same as the recognition result output by the host computer processing module, then the electronic control unit is confirmed to be correct.

5. A data verification device, characterized in that, The data verification device includes a processor, a memory, and a data verification program stored in the memory and executable by the processor, wherein when the data verification program is executed by the processor, it implements the steps of the data verification method as described in any one of claims 1 to 3.

6. A readable storage medium, characterized in that, The readable storage medium stores a data verification program, wherein when the data verification program is executed by a processor, it implements the steps of the data verification method as described in any one of claims 1 to 3.

Images