Automobile automatic driving risk detection method and device, medium and equipment

Abstract

The invention discloses an automobile automatic driving risk detection method and device, a medium and equipment, and relates to the technical field of automobile automatic driving. Comprising the following steps: acquiring a real-time driving video shot by an in-vehicle camera within a preset time and a reference driving video shot in advance; and according to each frame of image in the real-time driving video and the reference driving video, judging whether the automobile automatic driving operation corresponding to the real-time driving video meets a preset standard or not. And if yes, determining that the automobile automatic driving operation corresponding to the real-time driving video has no risk, and continuing to obtain the real-time driving video until the automobile automatic driving detection task is completed. If not, it is determined that the risk exists, and the automobile automatic driving detection task is ended. Whether a problem occurs or not is not judged only by a vehicle-mounted automatic driving system, the risk of automatic driving can be comprehensively judged through the picture shot by the camera in the vehicle and the detection of driving smoothness and efficiency, and double guarantees are provided for automatic driving detection.

Description

Technical Field

[0001] The present invention relates to the field of automobile autonomous driving technology, and in particular to a method, device, medium and equipment for risk detection of automobile autonomous driving. Background Art

[0002] At present, with the widespread use of artificial intelligence, the technology of autonomous driving is also developing rapidly. With the use of autonomous driving technology, cars can automatically perform driving tasks and bring passengers a good driving experience. As the sensor configuration of autonomous driving cars becomes richer and richer, the number of functions increases, and the autonomous driving capabilities become more mature, people are paying more and more attention to the problems that may arise in the process of autonomous driving, which they are increasingly dependent on.

[0003] In the existing process of automatic driving, when a problem occurs in the automatic driving vehicle, the automatic driving system on the vehicle needs to determine whether the problem needs to be handled according to the severity of the problem. In order to better handle the severity of the problem, a qualitative safety analysis can be conducted on the severity of the problem, and the severity of the impact of different problems can be divided, and then each problem can be graded according to the severity of its impact on automatic driving. In this way, it is equivalent to the automatic driving system on the vehicle not only needing to execute the process of automatic driving, but also needing to be able to judge and handle the problems that arise during the automatic driving process.

[0004] However, in this way, when a problem occurs, the vehicle's onboard autonomous driving system may not be able to respond quickly to the problem. In this case, the autonomous driving system often does not judge that the decision it made has deviated from the normal decision, or even makes a wrong decision.

[0005] To this end, this specification provides a risk detection method, device, medium and equipment for autonomous driving of a vehicle. Summary of the invention

[0006] This specification provides a risk detection method, device, medium and equipment for autonomous driving of a car to partially solve the above-mentioned problems existing in the prior art.

[0007] This manual adopts the following technical solutions: This specification provides a risk detection method for autonomous driving of a vehicle, including: Acquire a real-time driving video captured by an in-vehicle camera at a preset time and a reference driving video captured in advance, wherein the preset time is the same as the shooting duration of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle and is used to capture a video including a driving scene and a windshield during the automatic driving process; Determine a real-time driving image sequence according to each frame of the real-time driving video, and determine a reference driving image sequence according to each frame of the reference driving video; According to the real-time driving image sequence and the reference driving image sequence, determining whether the automatic driving operation of the vehicle corresponding to the real-time driving video meets a preset standard; If yes, it is determined that there is no risk in the automatic driving operation of the vehicle corresponding to the real-time driving video, and the real-time driving video captured by the in-vehicle camera is continuously obtained until the automatic driving detection task of the vehicle is completed; If not, it is determined that the automatic driving operation of the car corresponding to the real-time driving video is risky, and the automatic driving detection task of the car is terminated.

[0008] Optionally, judging whether the automatic driving operation of the vehicle corresponding to the real-time driving video meets a preset standard according to the real-time driving image sequence and the reference driving image sequence includes: Determining the number of image comparison rounds according to the number of images in the real-time driving image sequence; According to the image comparison round number and the shooting order of each frame image in the real-time driving image sequence and the reference driving image sequence, perform the image comparison operation corresponding to the image comparison round number, and determine the similarity between the images in the real-time driving image sequence and the reference driving image sequence, wherein for the Nth round of image comparison operation, according to the shooting order, determine the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, and calculate the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, where N is a positive integer not less than 1; Determining, according to each similarity, a similarity between the real-time driving image sequence and the reference driving image sequence; It is determined whether the similarity between the real-time driving image sequence and the reference driving image sequence meets a preset similarity value.

[0009] According to the above technical means, by determining the number of image comparison rounds and performing corresponding image comparison operations based on the shooting order, it is possible to ensure that the corresponding frames in the two sets of image sequences are accurately matched. This helps to identify the differences between the two sets of images at the same time point or driving conditions. Calculating the similarity of each pair of corresponding images makes it possible to quantify the overall similarity between the two sets of image sequences, which helps to determine whether the real-time driving situation is consistent with the preset reference scene.

[0010] Optionally, each frame image of the real-time driving video includes at least a dashboard and a steering wheel; For the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, calculating the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence specifically includes: Determine a target object in an N-th frame image in the real-time driving image sequence and an N-th frame image in the reference driving image sequence, wherein the target object is one of the instrument panel and the steering wheel; Performing image segmentation on the Nth frame image in the real-time driving image sequence to determine a first target object image, and performing image segmentation on the Nth frame image in the reference driving image sequence to determine a second target object image; The similarity between the first target object image and the second target object image is calculated as the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence.

[0011] According to the above technical means, by performing image segmentation on the Nth frame image in the real-time driving image sequence and the reference driving image sequence, the dashboard image (when the target object is the dashboard) can be accurately extracted. Since the dashboard is an important indicator of the vehicle's operating status (such as speed, turn signal, gear position, etc.), focusing on the comparison of this area helps to more accurately evaluate the consistency of the two driving scenes. It is also possible to perform similarity calculation only on the segmented first steering wheel image (when the target object is the steering wheel) and the second steering wheel image, rather than the entire image, which can significantly reduce the impact of background changes (such as road environment, weather conditions, etc.) on the comparison results, thereby improving the accuracy of the similarity calculation.

[0012] Optionally, before continuing to obtain the real-time driving video captured by the in-vehicle camera, the method further includes: Acquire data collected by various vibration sensors pre-installed on the seat cushion, seat back and floor of the vehicle; Determining a total weighted root mean square value of acceleration on the seat cushion, the seat back, and the floor according to the data collected by the vibration sensors; Determining a navigation distance recorded by a terminal device for navigation pre-installed in the vehicle, and determining a driving distance corresponding to the reference driving video; Determining a distance difference according to the navigation distance and the driving distance; Determine a score corresponding to the real-time driving video according to a preset scoring rule text, the total weighted acceleration root mean square value, and the distance difference value, wherein the scoring rule text records a scoring rule for scoring the real-time driving video; When the score corresponding to the real-time driving video does not reach the preset score and the automatic driving system of the car corresponding to the real-time driving video is in the minimum risk strategy state, a prompt message is issued, and the prompt message is used to prompt the user in the car to perform manual driving.

[0013] According to the above technical means, vibration data generated during vehicle driving can be collected in all directions by pre-installing vibration sensors on the seat cushions, seat backs and floors in the vehicle. These data are very important for evaluating driving comfort, detecting potential mechanical problems or unstable driving behaviors. Calculating the total weighted acceleration root mean square value based on the data collected by each vibration sensor can provide an objective measurement standard to quantify the smoothness of the vehicle during driving. A lower total weighted acceleration root mean square value usually means a smoother driving experience. Combining the navigation distance recorded by the terminal device and the driving distance corresponding to the reference driving video to determine the distance difference can help identify whether the actual driving route meets expectations. Determining the score corresponding to the real-time driving video based on the preset scoring rules, the total weighted acceleration root mean square value and the distance difference provides a comprehensive method to evaluate driving quality. This scoring not only takes into account the accuracy of the driving route, but also includes multiple factors such as driving smoothness. When the score corresponding to the real-time driving video does not meet the preset standard and the autonomous driving system is in the minimum risk strategy state, a prompt message is issued to encourage the user to take over manual driving. This enhances the safety of the system by ensuring that control is handed over to the driver in a timely manner when autonomous driving may not be sufficient to cope with current road conditions, thereby avoiding potential dangers.

[0014] Optionally, determining a score corresponding to the real-time driving video according to a preset scoring rule text, the total weighted acceleration root mean square value, and the distance difference value specifically includes: Determine whether there is a risk in the automatic driving operation of the vehicle corresponding to the real-time driving video; If so, it is determined that the automatic driving operation of the automobile corresponding to the real-time driving video obtains a safety compliance score that accounts for 50% of the preset total score; according to the preset interval ranges, the interval range corresponding to the total weighted acceleration root mean square value is determined, and the smoothness score is determined according to the interval range corresponding to the total weighted acceleration root mean square value; according to the preset difference ranges and the distance difference, the efficiency score is determined; according to the safety compliance score, the smoothness score and the efficiency score, the score corresponding to the real-time driving video is determined; If not, no safety compliance score is obtained, and the scoring score corresponding to the real-time driving video is determined to be 0.

[0015] Optionally, before ending the vehicle automatic driving detection task, the method further includes: Determining whether the automatic driving system of the vehicle corresponding to the real-time driving video is in a minimum risk strategy state; If so, determining that the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time; If not, an alarm message is issued, wherein the alarm message is used to prompt that the minimum risk strategy is not triggered within the target time.

[0016] Based on the above-mentioned technical means, by real-time monitoring of whether the automatic driving system triggers the minimum risk strategy within the target time and issuing an alarm when necessary, the safety of the driving process is effectively enhanced, ensuring that when the automatic driving system cannot respond to emergencies in time, manual intervention can be carried out quickly, thereby protecting the safety of passengers in the car and other road users.

[0017] Optionally, the method further includes: When there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and when the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time, a prompt message is issued, and the prompt message is used to prompt the user in the car to perform manual driving; Receive instruction information for continuing to execute the vehicle automatic driving detection task, and continue to obtain the real-time driving video captured by the in-vehicle camera according to the instruction information until the vehicle automatic driving detection task is completed.

[0018] Based on the above-mentioned technical means, through effective risk response mechanisms, user interaction design and continuous driving monitoring, it is ensured that during the autonomous driving process, potential risks can be responded to quickly and the user's decision-making power can be fully respected, thereby improving the safety and satisfaction of the overall driving experience.

[0019] This specification provides a risk detection device for automatic driving of a vehicle, including: an acquisition module, used to acquire a real-time driving video shot by an in-vehicle camera at a preset time and a reference driving video shot in advance, wherein the preset time is the same as the shooting time of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle and is used to shoot a video including a driving scene and a windshield during the automatic driving process; A determination module, configured to determine a real-time driving image sequence according to each frame of the real-time driving video, and to determine a reference driving image sequence according to each frame of the reference driving video; The judgment module is used to judge whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard according to the real-time driving image sequence and the reference driving image sequence; if so, it is determined that there is no risk in the automatic driving operation of the car corresponding to the real-time driving video, and the real-time driving video captured by the in-vehicle camera is continuously obtained until the automatic driving detection task of the car is completed; if not, it is determined that there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and the automatic driving detection task of the car is terminated.

[0020] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the risk detection method for autonomous driving of a vehicle is implemented.

[0021] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a risk detection method for autonomous driving of a vehicle when executing the program.

[0022] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects: The risk detection method for the automatic driving of a car provided in this specification first obtains a real-time driving video of a preset time shot by an in-car camera and a reference driving video shot in advance, and the preset time is the same as the shooting time of the reference driving video. According to each frame of the real-time driving video, a real-time driving image sequence is determined, and according to each frame of the reference driving video, a reference driving image sequence is determined. According to the real-time driving image sequence and the reference driving image sequence, it is determined whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard. If so, it is determined that there is no risk in the automatic driving operation of the car corresponding to the real-time driving video, and the real-time driving video shot by the in-car camera continues to be obtained until the automatic driving detection task of the car is completed. If not, it is determined that there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and the automatic driving detection task of the car is ended.

[0023] Real-time driving videos of the car's autonomous driving process are captured through in-car cameras that are independent of the car's autonomous driving system. The real-time driving videos are then analyzed to determine whether there are any problems with the car's autonomous driving process. This means that when the on-board sensors connected to the autonomous driving system are affected by extreme weather (heavy rain / dense fog) or hardware failures, it is no longer necessary to rely solely on the on-board autonomous driving system to determine whether there are any problems. Images captured by the in-car cameras can still be used for image comparison, providing dual protection for driving safety and autonomous driving detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings: Figure 1 A schematic diagram of a process flow of a risk detection method for autonomous driving of a vehicle provided in an embodiment of this specification; Figure 2 A schematic diagram of a process of automatic driving detection of a car provided in this manual; Figure 3 A schematic diagram of a risk detection device for automatic driving of a vehicle provided in this specification; Figure 4 A method corresponding to the Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0027] Figure 1 A flow chart of a risk detection method for automatic driving of a vehicle provided in an embodiment of this specification includes the following steps: S100: Acquire a real-time driving video captured by an in-vehicle camera at a preset time and a pre-shot reference driving video, wherein the preset time is the same as the shooting duration of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle, and is used to capture a video including the driving seat and the windshield during the automatic driving process.

[0028] The risk detection process for the automatic driving of a car in this specification generally involves the processing of image data. In the embodiments of this specification, the risk detection process for the automatic driving of a car can be performed by an on-board electronic control unit (ECU) or an edge computing device. Of course, this specification does not limit the type of device or platform that implements the risk detection process for the automatic driving of a car. For example, devices or platforms such as personal computers and mobile terminals can also be used to perform risk detection for the automatic driving of a car. For ease of description, the following description is based on the terminal device as the execution subject. For example, the terminal device can be a terminal device that is set on a car and can be used for computing and image processing.

[0029] In one or more embodiments of this specification, the object of risk detection for autonomous driving is a car equipped with an autonomous driving system and having autonomous driving capabilities. An in-car camera that can capture the driving scene and the windshield scene is installed on the top of the car, but this specification does not limit the specific installation position of the in-car camera on the top of the car. For example, the in-car camera can be installed on the top of the car above the main driving seat or at the center of the top of the car. The in-car camera can capture the dashboard, steering wheel, etc. in front of the main driving seat, and can also capture the windshield. Based on the nature of the windshield not blocking the line of sight, the in-car camera can capture the road scene presented through the windshield.

[0030] Therefore, before testing the autonomous driving capabilities of a car equipped with an autonomous driving system, a standard reference driving video can be pre-shot through the camera inside the car. The reference driving video is shot and recorded in compliance with road traffic safety regulations and the test rules for subject three of the driver's license test.

[0031] When the terminal device performs the task of detecting the automatic driving of the car, it can obtain the real-time driving video of the preset time taken by the camera inside the car during the detection process. In this manual, in order to test the automatic driving ability of the car more efficiently, when the camera inside the car captures a video of a certain time period, the automatic driving operation within this time period can be analyzed. Of course, there is no limit to the time period for each analysis of the terminal device. Even when the camera inside the car captures a frame of image, the ability of automatic driving can be detected by analyzing this frame of image.

[0032] In one or more embodiments of the present specification, since a standard reference driving video has been pre-shot by the in-vehicle camera before testing the autonomous driving capability, the reference driving video can be used as a reference and compared with the real-time driving video shot by the in-vehicle camera at a preset time during the testing process to facilitate analysis of the vehicle's autonomous driving capability.

[0033] Furthermore, in order to facilitate frame-by-frame image comparison between the reference driving video and the real-time driving video, for the real-time driving video shot by the in-vehicle camera at a preset time, the terminal device also needs to divide the pre-shot reference driving video into segments of reference driving videos. The time length of each reference driving video (i.e., shooting duration) is the same as the shooting time (i.e., preset time) of the real-time driving video.

[0034] S102: Determine a real-time driving image sequence according to each frame of the real-time driving video, and determine a reference driving image sequence according to each frame of the reference driving video.

[0035] In one or more embodiments of the present specification, the terminal device may compose a real-time driving image sequence based on each frame of the real-time driving video. Similarly, the terminal device may compose a reference driving image sequence based on each frame of the reference driving video.

[0036] S104: According to the real-time driving image sequence and the reference driving image sequence, determine whether the automatic driving operation of the vehicle corresponding to the real-time driving video meets the preset standard. If yes, execute step S106, if no, execute step S108.

[0037] In one or more embodiments of the present specification, the terminal device may determine whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standards based on the real-time driving image sequence and the reference driving image sequence.

[0038] Specifically, the terminal device may determine the number of image comparison rounds according to the number of images in the real-time driving image sequence. Of course, the terminal device may also determine the number of image comparison rounds according to the number of images in the reference driving video.

[0039] Afterwards, the terminal device can perform image comparison operations corresponding to the number of image comparison rounds, the shooting order of each frame image in the real-time driving image sequence, and the shooting order of each frame image in the reference driving image sequence, and determine the similarity between the images in the real-time driving image sequence and the reference driving image sequence. Among them, for the Nth round of image comparison operation, according to the shooting order of each frame image in the real-time driving image sequence, the Nth frame image in the real-time driving image sequence is determined, and according to the shooting order of each frame image in the reference driving image sequence, the Nth frame image in the reference driving image sequence is determined, and the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence is calculated, wherein N is a positive integer not less than 1. Of course, the method for calculating image similarity is not limited in this specification, and can be set according to actual conditions, such as comparing based on image pixel values ​​and using mean square error (MSE) to calculate similarity.

[0040] It is worth noting that after the terminal device calculates the image similarity between the real-time driving image sequence and the reference driving image sequence, it can determine the similarity between the real-time driving image sequence and the reference driving image sequence based on the calculated similarities. The method for determining the similarity between the real-time driving image sequence and the reference driving image sequence is not limited in this specification. For example, the sum of the similarities or the mean of the similarities can be used as the similarity between the real-time driving image sequence and the reference driving image sequence. Finally, the terminal device can determine whether the similarity between the real-time driving image sequence and the reference driving image sequence meets the preset similarity value.

[0041] Of course, in this specification, the method for the terminal device to determine whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard based on the real-time driving image sequence and the reference driving image sequence can also be to extract image features of each frame in the real-time driving image sequence and the reference driving image sequence, and match the features of each frame in the real-time driving image sequence and the reference driving image sequence. If the number of matched images reaches a preset number, it can be determined that the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard.

[0042] S106: Determine that there is no risk in the automatic driving operation of the vehicle corresponding to the real-time driving video, and continue to obtain the real-time driving video captured by the in-vehicle camera until the automatic driving detection task of the vehicle is completed.

[0043] In one or more embodiments of the present specification, when the automatic driving operation of the car corresponding to the real-time driving video meets the preset standards, the terminal device can determine that there is no risk in the automatic driving operation of the car corresponding to the real-time driving video. After that, the terminal device can continue to obtain the real-time driving video taken by the camera inside the car until the automatic driving detection task of the car is completed.

[0044] S108: Determine that there is a risk in the automatic driving operation of the vehicle corresponding to the real-time driving video, and end the automatic driving detection task of the vehicle.

[0045] In one or more embodiments of the present specification, when the automatic driving operation of the car corresponding to the real-time driving video does not meet the preset standards, the terminal device can determine that the automatic driving operation of the car corresponding to the real-time driving video is risky. Based on the principle of safety as the top priority, the terminal device can then end the automatic driving detection task of the car. Of course, after ending the automatic driving detection task of the car, the terminal device can issue an alarm through a connected microphone device, etc., to prompt that the automatic driving detection task of the car has ended.

[0046] based on Figure 1The risk detection method for the car's autonomous driving shown in the figure uses an in-car camera that is independent of the car's autonomous driving system to shoot real-time driving videos during the car's autonomous driving process. Then, by analyzing the real-time driving videos, it is determined whether there is a problem with the car's autonomous driving process. When the on-board sensors connected to the autonomous driving system are affected by extreme weather (heavy rain / dense fog) or hardware failures, it is no longer solely dependent on the on-board autonomous driving system to determine whether there is a problem. The images shot by the in-car camera can still be used for image comparison, providing dual protection for driving safety and autonomous driving detection.

[0047] Moreover, in actual use, people will inevitably rely on the vehicle's intelligent driving when the vehicle is driving automatically, which may cause distraction (such as playing with mobile phones, deep chatting, etc.), and they cannot pay full attention to the situation of automatic driving at all times. Therefore, the risk detection method for automatic driving of a car provided in this manual can assist the driver to pay attention to the situation of automatic driving anytime and anywhere through the installed in-car camera, thereby increasing safety.

[0048] In addition, in one or more embodiments of the present specification, each frame image of the real-time driving video includes at least the dashboard, that is, the driving scene captured by the in-car camera installed on the top of the car during the automatic driving process includes the dashboard and the steering wheel.

[0049] Therefore, when the terminal device calculates the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, it can determine the target object in the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, and the target object is one of the dashboard and the steering wheel.

[0050] When the target object is a dashboard, the Nth frame image in the real-time driving image sequence is segmented to determine the first dashboard image, and the Nth frame image in the reference driving image sequence is segmented to determine the second dashboard image. The similarity between the first dashboard image and the second dashboard image is then calculated as the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence. When the terminal device performs image segmentation, a segmentation algorithm such as region growing can be used for image segmentation.

[0051] In one or more embodiments of the present specification, when the target object is a steering wheel, the terminal device may further perform image segmentation on the Nth frame image in the real-time driving image sequence to determine a first steering wheel image, and perform image segmentation on the Nth frame image in the reference driving image sequence to determine a second steering wheel image. The similarity between the first steering wheel image and the second steering wheel image is then calculated as the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence.

[0052] In one or more embodiments of the present specification, the terminal device may also obtain data collected by various vibration sensors pre-set on the seat cushion, seat back and floor in the vehicle. According to the data collected by each vibration sensor, the total weighted RMS value of the seat cushion, seat back and floor is determined. The method for calculating the total weighted RMS value of the acceleration may refer to the standard document of the vehicle ride comfort test method (GB / T 4970-2009).

[0053] At the same time, the terminal device can also determine the navigation distance recorded by the terminal device for navigation pre-set in the car, and determine the driving distance corresponding to the reference driving video. Then, the distance difference is determined based on the navigation distance and the driving distance. After that, the score corresponding to the real-time driving video is determined according to the preset scoring rule text, the total weighted acceleration root mean square value and the distance difference. The scoring rule text records the scoring rules for scoring the real-time driving video.

[0054] Furthermore, when the score corresponding to the real-time driving video does not reach the preset score, and the automatic driving system of the car corresponding to the real-time driving video is in the minimum risk maneuver (MRM) state, a prompt message is issued to prompt the user in the car to perform manual driving.

[0055] Among them, according to the preset scoring rule text, the total weighted acceleration root mean square value and the distance difference value, the process of determining the score corresponding to the real-time driving video can be: the terminal device determines whether the automatic driving operation of the car corresponding to the real-time driving video is risky. If so, it is determined that the automatic driving operation of the car corresponding to the real-time driving video obtains a safety compliance score that accounts for 50% of the preset total score. According to the preset interval ranges, the interval range corresponding to the total weighted acceleration root mean square value is determined, and the smoothness score is determined according to the interval range corresponding to the total weighted acceleration root mean square value. According to the preset difference range and the distance difference value, the efficiency score is determined. According to the safety compliance score, the smoothness score and the efficiency score, the score corresponding to the real-time driving video is determined. If not, the safety compliance score is not obtained, and the score corresponding to the real-time driving video is determined to be 0. In this case, it can be considered that the safety compliance does not meet the standard, and the smoothness and efficiency are no longer considered, with safety compliance as the first priority.

[0056] The following is an example of a preset scoring rule text: 1. The safety compliance score accounts for 50% of the total score. Whether the car's autonomous driving operation corresponding to the real-time driving video is risky is used as the standard for safety compliance scoring. If the autonomous driving operation is risk-free, it is considered to be a safety compliance score, otherwise it is considered not to be a safety compliance score.

[0057] 2. The smoothness score accounts for 30% of the total score. The total weighted acceleration root mean square value is used as the standard for smoothness scoring. If the calculated total weighted acceleration root mean square value is less than 0.3, it is full marks, 0.3-0.4 (excluding 0.4) accounts for 60% of the smoothness score, (3) 0.4-0.5 (excluding 0.5) accounts for 30% of the smoothness score, (4) greater than or equal to 0.5, no points are given. Among them, the total weighted acceleration root mean square value is less than 0.3, 0.3-0.4, 0.4-0.5, and the total weighted acceleration root mean square value is greater than or equal to 0.5, which are the preset ranges. The premise of the smoothness test of this scheme is that the vehicle hardware has met the smoothness requirements, that is, the factors affecting the smoothness of non-automatic driving systems such as the active control suspension system of the vehicle have been excluded.

[0058] 3. The efficiency score accounts for 20% of the total score. If the preset time for shooting the real-time driving video is 15 minutes, and the navigation distance recorded by the terminal device for navigation in the car is one-third less than the driving distance corresponding to the reference driving video, the efficiency score will not be counted. If the navigation distance recorded by the terminal device for navigation in the car is one-quarter less than the driving distance corresponding to the reference driving video, the efficiency score will be 30%; if the navigation distance recorded by the terminal device for navigation in the car is one-fifth less than the driving distance corresponding to the reference driving video, the efficiency score will be 60%; if the navigation distance recorded by the terminal device for navigation in the car is consistent with the driving distance corresponding to the reference driving video, the full score will be given. Among them, the difference between the above one-third, one-quarter, one-fifth and the same distance is 0, which is the preset difference range.

[0059] 4. The total score can be based on a percentage system. If the sum of the safety compliance score, efficiency score and smoothness score is less than 80 points, it is considered that the minimum risk strategy of the vehicle's autonomous driving system should be triggered.

[0060] The safety compliance score, efficiency score, and smoothness score comprehensively cover the evaluation dimensions. The scores in these three aspects can provide a comprehensive perspective to evaluate the performance of the autonomous driving system. Safety compliance ensures that the operation of the vehicle complies with traffic rules and legal requirements. Efficiency focuses on whether the system can complete the task or reach the destination as quickly as possible while optimizing resource use, while smoothness examines the comfort of passengers and avoids sudden braking or sudden acceleration. In addition, through the safety compliance score, the ability of the autonomous driving system to comply with traffic rules and safe driving guidelines can be directly measured, thereby reducing the possibility of accidents and improving the safety of other users on public roads. It can also optimize the user experience. The smoothness score helps to ensure the comfort of the riding experience and reduce passenger discomfort caused by unstable driving. This is crucial to enhancing users' trust and acceptance of autonomous driving technology.

[0061] It is worth noting that the core steps are listed here as an example, referring to the method for calculating the total weighted RMS value of acceleration in the standard document of the automobile ride comfort test method (GB / T 4970-2009). The data collected by the vibration sensors installed on the seat cushion, seat back and floor in the vehicle can be summarized as data in three directions, that is, vibration sensors are installed in the three directions of the X-axis (seat back), Y-axis (seat cushion) and Z-axis (floor) to collect data in these three directions. Taking the calculation of the weighted RMS value of acceleration in one direction as an example, through the formula A.3 in A.2.1 of the standard document of the automobile ride comfort test method (GB / T 4970-2009):

[0062] in, is the root mean square value of the acceleration in the 1 / 3 octave band, ——The center frequency is f j The root mean square value of the acceleration in the jth (j=1, 2, 3...23) 1 / 3 octave band, in meters per second squared (m / s 2 ). , ——The center frequency of the 1 / 3 octave band is f j The upper and lower limit frequencies (details are in Table A.2 of the standard document of Vehicle Ride Comfort Test Method (GB / T 4970-2009)), in Hertz (Hz). ——Acceleration rate spectral density function, in square meters per second cubed (m 2 / s 3 ).

[0063] After that, the weighted acceleration root mean square value is calculated according to the following formula (Formula A.4 in A.2.1 of the standard document of the vehicle ride comfort test method (GB / T 4970-2009)):

[0064] in, ——Root mean square value of one-way weighted acceleration, in meters per second squared (m / s 2 ). ——The weighting coefficient of the jth 1 / 3 octave band is determined according to the direction and position of the measuring point to which the one-way direction belongs. For specific values, see Table A.4 in the standard document of the vehicle ride comfort test method (GB / T 4970-2009).

[0065] Therefore, the above method for calculating the unidirectional weighted acceleration root mean square value can be used to calculate the unidirectional weighted acceleration root mean square value in three directions, and then the total weighted acceleration root mean square value can be calculated according to the preset weighting coefficient and the formula recorded in A.6 of the standard document of the vehicle ride comfort test method (GB / T 4970-2009).

[0066] In one or more embodiments of the present specification, when determining that the automatic driving operation of the car corresponding to the real-time driving video is at risk, the terminal device may determine whether the automatic driving system of the car corresponding to the real-time driving video is already in the minimum risk strategy state. If so, it is determined that the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time. The target time may be the difference between the time when the minimum risk strategy is triggered and the time when the terminal device determines that the automatic driving operation is at risk. The target time may be set to 1 minute to determine whether the triggering of the minimum risk strategy is a timely response. If not, an alarm message is issued, and the alarm message is used to prompt that the minimum risk strategy is not triggered within the target time.

[0067] In one or more embodiments of this specification, when there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time, the terminal device sends a prompt message, and the prompt message is used to prompt the user in the car to perform manual driving. After a period of manual driving, the terminal device receives the instruction information to continue to perform the automatic driving detection task of the car, and continues to obtain the real-time driving video captured by the camera in the car according to the instruction information until the automatic driving detection task of the car is completed.

[0068] Figure 2 This is a flow chart of a car automatic driving test provided in this manual. Figure 2As shown, when the automatic driving test begins, the terminal device obtains the real-time driving video shot by the in-car camera and the pre-shot reference driving video for comparative analysis to determine whether the car's automatic driving capability meets the preset standard. If so, the automatic driving test continues. Otherwise, the terminal device also needs to determine whether the automatic driving system triggers MRM within the target time. If so, the car is switched to manual driving, and after the terminal device receives the instruction to continue the automatic driving test, the automatic driving test continues. If not, the automatic driving test ends directly.

[0069] The above is a risk detection method for automatic driving of a vehicle provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding risk detection device for automatic driving of a vehicle, such as Figure 3 shown.

[0070] Figure 3 A schematic diagram of a risk detection device for automatic driving of a vehicle provided in this specification, specifically including: An acquisition module 300 is used to acquire a real-time driving video shot by an in-vehicle camera at a preset time and a reference driving video shot in advance, wherein the preset time is the same as the shooting time of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle and is used to shoot a video including a driving scene and a windshield during the automatic driving process; A determination module 302 is used to determine a real-time driving image sequence according to each frame of the real-time driving video, and to determine a reference driving image sequence according to each frame of the reference driving video; The judgment module 304 is used to judge whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard based on the real-time driving image sequence and the reference driving image sequence; if so, it is determined that there is no risk in the automatic driving operation of the car corresponding to the real-time driving video, and the real-time driving video captured by the in-vehicle camera is continuously obtained until the automatic driving detection task of the car is completed; if not, it is determined that there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and the automatic driving detection task of the car is terminated.

[0071] Optionally, the judgment module 304 is used to determine the number of image comparison rounds according to the number of images in the real-time driving image sequence, and perform image comparison operations corresponding to the number of image comparison rounds according to the number of image comparison rounds, the shooting order of each frame image in the real-time driving image sequence and the reference driving image sequence, to determine the similarity between the images in the real-time driving image sequence and the reference driving image sequence, wherein, for the Nth round of image comparison operation, the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence are determined according to the shooting order, and the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence is calculated, where N is a positive integer not less than 1, and the similarity between the real-time driving image sequence and the reference driving image sequence is determined according to each similarity, and it is judged whether the similarity between the real-time driving image sequence and the reference driving image sequence meets a preset similarity value.

[0072] Optionally, each frame image of the real-time driving video includes at least a dashboard and a steering wheel; The judgment module 304 is used to determine the target object in the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, where the target object is one of the instrument panel and the steering wheel, perform image segmentation on the Nth frame image in the real-time driving image sequence to determine the first target object image, and perform image segmentation on the Nth frame image in the reference driving image sequence to determine the second target object image, and calculate the similarity between the first target object image and the second target object image as the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence.

[0073] Optionally, the judgment module 304 is used to obtain data collected by vibration sensors pre-installed on the seat cushion, seat back and floor in the vehicle, determine the total weighted acceleration root mean square value of the seat cushion, the seat back and the floor according to the data collected by the vibration sensors, determine the navigation distance recorded by the terminal device for navigation pre-installed in the vehicle, and determine the driving distance corresponding to the reference driving video, determine the distance difference according to the navigation distance and the driving distance, and determine the score corresponding to the real-time driving video according to a preset scoring rule text, the total weighted acceleration root mean square value and the distance difference, the scoring rule text records the scoring rules for scoring the real-time driving video, and when the score corresponding to the real-time driving video does not reach the preset score and the automatic driving system of the car corresponding to the real-time driving video is in the minimum risk strategy state, a prompt message is issued, and the prompt message is used to prompt the user in the car to perform manual driving.

[0074] Optionally, the judgment module 304 is used to judge whether there is a risk in the automatic driving operation of the car corresponding to the real-time driving video. If so, it is determined that the automatic driving operation of the car corresponding to the real-time driving video obtains a safety compliance score that accounts for 50% of the preset total score; according to the preset interval ranges, the interval range corresponding to the total weighted acceleration root mean square value is determined, and the smoothness score is determined according to the interval range corresponding to the total weighted acceleration root mean square value; according to the preset difference ranges and the distance difference, the efficiency score is determined; according to the safety compliance score, the smoothness score and the efficiency score, the score corresponding to the real-time driving video is determined, if not, no safety compliance score is obtained, and the score corresponding to the real-time driving video is determined to be 0.

[0075] Optionally, the judgment module 304 is used to determine whether the automatic driving system of the car corresponding to the real-time driving video is in a minimum risk strategy state. If so, it is determined that the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time. If not, an alarm message is issued, and the alarm message is used to prompt that the minimum risk strategy is not triggered within the target time.

[0076] Optionally, the judgment module 304 is used to issue a prompt message when there is a risk in the automatic driving operation of the car corresponding to the real-time driving video and the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time. The prompt message is used to prompt the user in the car to perform manual driving, receive instruction information to continue to execute the automatic driving detection task of the car, and continue to obtain the real-time driving video taken by the camera in the car according to the instruction information until the automatic driving detection task of the car is completed.

[0077] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A risk detection method for automatic driving of a vehicle is provided.

[0078] This manual also provides Figure 4 The schematic structure diagram of the electronic device shown in FIG. Figure 4 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The risk detection method for automatic driving of a car.

[0079] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0080] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0081] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0082] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0083] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0084] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0089] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0090] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0091] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0092] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0094] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0095] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A risk detection method for automatic driving of a vehicle, characterized in that: include: Acquire a real-time driving video captured by an in-vehicle camera at a preset time and a reference driving video captured in advance, wherein the preset time is the same as the shooting duration of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle and is used to capture a video including a driving scene and a windshield during the automatic driving process; Determine a real-time driving image sequence according to each frame of the real-time driving video, and determine a reference driving image sequence according to each frame of the reference driving video; According to the real-time driving image sequence and the reference driving image sequence, determining whether the automatic driving operation of the vehicle corresponding to the real-time driving video meets a preset standard; If yes, it is determined that there is no risk in the automatic driving operation of the vehicle corresponding to the real-time driving video, and the real-time driving video captured by the in-vehicle camera is continuously obtained until the automatic driving detection task of the vehicle is completed; If not, it is determined that the automatic driving operation of the car corresponding to the real-time driving video is risky, and the automatic driving detection task of the car is terminated.

2. The risk detection method for automatic driving of a vehicle according to claim 1, characterized in that: Judging whether the automatic driving operation of the vehicle corresponding to the real-time driving video meets a preset standard according to the real-time driving image sequence and the reference driving image sequence, specifically includes: Determining the number of image comparison rounds according to the number of images in the real-time driving image sequence; According to the image comparison round number and the shooting order of each frame image in the real-time driving image sequence and the reference driving image sequence, perform the image comparison operation corresponding to the image comparison round number, and determine the similarity between the images in the real-time driving image sequence and the reference driving image sequence, wherein for the Nth round of image comparison operation, according to the shooting order, determine the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, and calculate the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, where N is a positive integer not less than 1; Determining, according to each similarity, a similarity between the real-time driving image sequence and the reference driving image sequence; It is determined whether the similarity between the real-time driving image sequence and the reference driving image sequence meets a preset similarity value.

3. A risk detection method for automatic driving of a vehicle as claimed in claim 2, characterized in that: Each frame image of the real-time driving video at least includes a dashboard and a steering wheel; For the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence, calculating the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence specifically includes: Determine a target object in an N-th frame image in the real-time driving image sequence and an N-th frame image in the reference driving image sequence, wherein the target object is one of the instrument panel and the steering wheel; Performing image segmentation on the Nth frame image in the real-time driving image sequence to determine a first target object image, and performing image segmentation on the Nth frame image in the reference driving image sequence to determine a second target object image; The similarity between the first target object image and the second target object image is calculated as the similarity between the Nth frame image in the real-time driving image sequence and the Nth frame image in the reference driving image sequence.

4. The risk detection method for automatic driving of a vehicle according to claim 1, characterized in that: Before continuing to obtain the real-time driving video captured by the in-vehicle camera, the method further includes: Acquire data collected by various vibration sensors pre-installed on the seat cushion, seat back and floor of the vehicle; Determining a total weighted root mean square value of acceleration on the seat cushion, the seat back, and the floor according to the data collected by the vibration sensors; Determining a navigation distance recorded by a terminal device for navigation pre-installed in the vehicle, and determining a driving distance corresponding to the reference driving video; Determining a distance difference according to the navigation distance and the driving distance; Determine a score corresponding to the real-time driving video according to a preset scoring rule text, the total weighted acceleration root mean square value, and the distance difference value, wherein the scoring rule text records a scoring rule for scoring the real-time driving video; When the score corresponding to the real-time driving video does not reach the preset score and the automatic driving system of the car corresponding to the real-time driving video is in the minimum risk strategy state, a prompt message is issued, and the prompt message is used to prompt the user in the car to perform manual driving.

5. A risk detection method for automatic driving of a vehicle as claimed in claim 4, characterized in that: Determining a score corresponding to the real-time driving video according to a preset scoring rule text, the total weighted acceleration root mean square value, and the distance difference value, specifically includes: Determine whether there is a risk in the automatic driving operation of the vehicle corresponding to the real-time driving video; If so, it is determined that the automatic driving operation of the automobile corresponding to the real-time driving video obtains a safety compliance score that accounts for 50% of the preset total score; according to the preset interval ranges, the interval range corresponding to the total weighted acceleration root mean square value is determined, and the smoothness score is determined according to the interval range corresponding to the total weighted acceleration root mean square value; according to the preset difference ranges and the distance difference, the efficiency score is determined; according to the safety compliance score, the smoothness score and the efficiency score, the score corresponding to the real-time driving video is determined; If not, no safety compliance score is obtained, and the scoring score corresponding to the real-time driving video is determined to be 0.

6. The risk detection method for automatic driving of a vehicle according to claim 1, characterized in that: Before completing the vehicle automatic driving detection task, the method further includes: Determining whether the automatic driving system of the vehicle corresponding to the real-time driving video is in a minimum risk strategy state; If so, determining that the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time; If not, an alarm message is issued, wherein the alarm message is used to prompt that the minimum risk strategy is not triggered within the target time.

7. A risk detection method for automatic driving of a vehicle as claimed in claim 6, characterized in that: The method further comprises: When there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and when the car corresponding to the real-time driving video triggers the minimum risk strategy within the target time, a prompt message is issued, and the prompt message is used to prompt the user in the car to perform manual driving; Receive instruction information for continuing to execute the vehicle automatic driving detection task, and continue to obtain the real-time driving video captured by the in-vehicle camera according to the instruction information until the vehicle automatic driving detection task is completed.

8. A risk detection device for automatic driving of a car, characterized in that: include: an acquisition module, used to acquire a real-time driving video shot by an in-vehicle camera at a preset time and a reference driving video shot in advance, wherein the preset time is the same as the shooting time of the reference driving video, and the in-vehicle camera is installed on the top of the vehicle and is used to shoot a video including a driving scene and a windshield during the automatic driving process; A determination module, configured to determine a real-time driving image sequence according to each frame of the real-time driving video, and to determine a reference driving image sequence according to each frame of the reference driving video; The judgment module is used to judge whether the automatic driving operation of the car corresponding to the real-time driving video meets the preset standard according to the real-time driving image sequence and the reference driving image sequence; if so, it is determined that there is no risk in the automatic driving operation of the car corresponding to the real-time driving video, and the real-time driving video captured by the in-vehicle camera is continuously obtained until the automatic driving detection task of the car is completed; if not, it is determined that there is a risk in the automatic driving operation of the car corresponding to the real-time driving video, and the automatic driving detection task of the car is terminated.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images