Methods, systems, electronic devices, and vehicles for assessing the hazard of obstacles.

Abstract

This invention provides a method, system, electronic device, and vehicle for determining the hazard of an obstacle. The method includes: acquiring observation information of the obstacle within a predetermined time period; classifying the obstacle based on the observation information and obtaining a classification result; if the classification result belongs to an unknown category, then, based on the observation information, performing a first determination of whether the obstacle is stationary within the predetermined time period; if the first determination yields a positive result, the obstacle is judged to be more hazardous than if the first determination yields a negative result. By using the observation information of the obstacle, the movement state of the obstacle is determined, including its trajectory, whether it is stationary or deformed, etc., thereby further determining the hazard of the obstacle.

Description

Technical Field

[0001] This invention relates to the field of target detection technology, and in particular to a method, system, electronic device, and vehicle for determining the hazard of an obstacle. Background Technology

[0002] In the many technical fields of computer vision, object detection is a very fundamental task. Image segmentation, object tracking, key point detection, and other tasks usually rely on object detection.

[0003] In autonomous or assisted driving of vehicles, obstacles can be identified through target detection. Existing technologies have methods for automatically detecting obstacles such as stationary vehicles and pedestrians, but lack methods for assessing the danger based on the different types of obstacles.

[0004] While a vehicle is in motion, it may encounter moving obstacles, but different obstacles pose significantly different risks. For example, a plastic bag flying towards the vehicle and a rock will cause drastically different damage. If the same avoidance measures are taken for all obstacles without differentiation, it may result in unexpected and unnecessary damage to the vehicle.

[0005] The information disclosed in this background section is intended only to enhance the understanding of the general background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] In view of the problems existing in the prior art, the present invention provides a method, system, electronic device, and vehicle for judging the danger of obstacles.

[0007] This invention provides a method for determining the hazard of an obstacle, the method comprising:

[0008] Obtain observation information of obstacles within a predetermined time period;

[0009] Based on the observation information, the obstacles are classified, and the classification results are obtained;

[0010] If the classification result belongs to an unknown category, then based on the observation information, a first judgment is made as to whether the obstacle is stationary during the predetermined time period, and / or a second judgment is made as to whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or a third judgment is made as to whether the obstacle maintains its shape during the predetermined time period.

[0011] If the first judgment yields an affirmative result, the obstacle is deemed more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields an affirmative result, the obstacle is deemed more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields an affirmative result, the obstacle is deemed more dangerous than if the third judgment yields a negative result.

[0012] According to a method for determining the hazard of an obstacle provided by the present invention, the method further includes:

[0013] If any one of the first, second, or third judgments yields a positive result, then the obstacle is determined to be a high-risk obstacle.

[0014] According to the present invention, a method for determining the hazard of an obstacle, wherein the obstacle is determined to be a high-risk obstacle, includes:

[0015] Issue a high-risk warning and / or issue control commands to avoid the obstacle.

[0016] According to a method for determining the hazard of an obstacle provided by the present invention, performing a first determination of whether the obstacle is stationary during a predetermined time period includes:

[0017] Obtain the first distance between the obstacle and the observer at the first moment;

[0018] Obtain the second distance between the obstacle and the observer at a second moment;

[0019] Assuming the obstacle is stationary, based on the first distance and the observer's velocity information, predict the third distance between the obstacle and the observer at a second moment;

[0020] If the third distance matches the second distance, the obstacle is determined to be stationary; otherwise, if the third distance does not match the second distance, the obstacle is determined to be moving.

[0021] According to the present invention, a method for determining the hazard of an obstacle is provided, comprising obtaining observation information of the obstacle within a predetermined time period, including:

[0022] Based on the camera, acquire two-dimensional image information of the obstacle within the predetermined time period;

[0023] Based on lidar, the three-dimensional point cloud information of the obstacle is acquired within the predetermined time period.

[0024] According to a method for determining the hazard of an obstacle provided by the present invention, a second determination is made as to whether the trajectory of the obstacle within a predetermined time period is a straight line or a parabola, including:

[0025] Based on the two-dimensional image information, the first motion trajectory is obtained;

[0026] Based on the three-dimensional point cloud information, a three-dimensional motion trajectory is obtained;

[0027] The three-dimensional motion trajectory is projected onto the two-dimensional plane of the camera to obtain a second motion trajectory;

[0028] The first motion trajectory and the second motion trajectory are fitted together to form a third motion trajectory;

[0029] Determine whether the third motion trajectory is a straight line or a parabola.

[0030] According to a method for determining the hazard of an obstacle provided by the present invention, a third determination is made regarding whether the obstacle maintains its shape unchanged during a predetermined time period, including:

[0031] Based on the two-dimensional image information, a first sub-determination is performed to determine whether the obstacle maintains its shape within the predetermined time period;

[0032] Based on the three-dimensional point cloud information, a second sub-determination is performed to determine whether the obstacle maintains its shape within the predetermined time period;

[0033] If the result of either the first sub-judgment or the second sub-judgment is positive, then the third judgment outputs a positive result; otherwise, if the results of both the first and second sub-judgments are negative, then the third judgment outputs a negative result.

[0034] According to a method for determining the hazard of an obstacle provided by the present invention, a third determination is made regarding whether the obstacle maintains its shape unchanged during a predetermined time period, including:

[0035] Determine whether the multiple distances between various feature points of the obstacle and the ratios of these distances have changed;

[0036] If any of the plurality of distances or the ratio of the plurality of distances changes, it is determined that the obstacle has failed to maintain its shape within the predetermined time period.

[0037] This invention also provides a system for determining the hazard of an obstacle, the system comprising:

[0038] The acquisition module is used to acquire observation information of obstacles within a predetermined time period;

[0039] The classification module is used to classify the obstacles based on the observation information and obtain the classification results;

[0040] The intermediate judgment module is used to perform the following judgments: if the classification result belongs to an unknown category, then based on the observation information, it performs a first judgment on whether the obstacle is stationary during the predetermined time period, and / or performs a second judgment on whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or performs a third judgment on whether the obstacle maintains its shape during the predetermined time period.

[0041] The hazard assessment module is used to perform the following assessments: if the first assessment yields a positive result, the obstacle is assessed as being more dangerous than if the first assessment yields a negative result; and / or, if the second assessment yields a positive result, the obstacle is assessed as being more dangerous than if the second assessment yields a negative result; and / or, if the third assessment yields a positive result, the obstacle is assessed as being more dangerous than if the third assessment yields a negative result.

[0042] The present invention also 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 executes the program to implement the steps of the method for determining the hazard of an obstacle as described in any of the preceding claims.

[0043] The present invention also provides a vehicle having autonomous driving and / or assisted driving functions, the vehicle including the aforementioned electronic equipment.

[0044] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for determining the hazard of an obstacle as described in any of the preceding claims.

[0045] The present invention provides a method, system, electronic device, and vehicle for judging the danger of obstacles. By observing the obstacle's information, the method determines the obstacle's motion state, including its trajectory, whether it is stationary or deformed, thereby further judging the danger of the obstacle. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0047] Figure 1A flowchart illustrating a method for determining the hazard of an obstacle provided by the present invention;

[0048] Figure 2 A flowchart illustrating another method for determining the hazard of an obstacle provided by the present invention;

[0049] Figure 3 This invention also provides a schematic diagram of a system structure for determining the hazard of obstacles;

[0050] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided by the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0052] The method for determining the hazard of obstacles provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0053] Figure 1 A flowchart illustrating a method for determining the hazard of an obstacle provided by the present invention is shown below. Figure 1 As shown, the present invention provides a method for determining the hazard of an obstacle, which may include the following steps.

[0054] Preferably, this method is applicable to vehicles equipped with cameras and lidar, which detect obstacles while in motion. Further, the vehicle includes aircraft and vehicles.

[0055] S100: Obtain observation information of obstacles within a predetermined time period.

[0056] Optionally, obtain observation information of the obstacle within a predetermined time period, including:

[0057] Based on the camera, acquire two-dimensional image information of obstacles within a predetermined time period;

[0058] Based on LiDAR, three-dimensional point cloud information of obstacles is acquired within a predetermined time period.

[0059] It should be noted that the camera's operating wavelength is not necessarily limited to the visible light band. The vehicle detects obstacles in real time and acquires observation information during its movement.

[0060] S200. Based on the observation information, classify the obstacles and obtain the classification results.

[0061] Preferably, after an obstacle is detected, it is initially classified using a conventional algorithm, such as traffic cones, pedestrians, and bicycles. After the initial classification, there are usually still unidentifiable categories, which will be classified into the "unknown category". In this case, the following additional obstacle detection steps are performed.

[0062] S300. If the classification result belongs to an unknown category, then based on the observation information, perform the first judgment on whether the obstacle is stationary within a predetermined time period, and / or, perform the second judgment on whether the obstacle's trajectory within the predetermined time period is a straight line or a parabola, and / or, perform the third judgment on whether the obstacle maintains its shape within the predetermined time period. The risk of the obstacle is quantified from three dimensions: motion state, trajectory, and deformation.

[0063] Optionally, the first determination of whether the obstacle is stationary within a predetermined time period includes:

[0064] Obtain the initial distance between the obstacle and the observer at the first moment;

[0065] Obtain the second distance between the obstacle and the observer at the second moment;

[0066] Assuming the obstacle is stationary, based on the first distance and the observer's velocity information, predict the third distance between the obstacle and the observer at the second moment;

[0067] If the third distance matches the second distance, the obstacle is determined to be stationary; otherwise, if the third distance does not match the second distance, the obstacle is determined to be moving.

[0068] Preferably, for an autonomous vehicle, the method for determining whether an obstacle is moving or stationary includes: when an obstacle is detected during vehicle travel, obtaining a first distance between the vehicle and the obstacle, and predicting a third distance between the vehicle and the obstacle after a certain period of time (e.g., 1 second) based on the vehicle's current travel speed; after 1 second, detecting the distance between the vehicle and the obstacle again; if the detected distance matches the third distance (not necessarily exactly equal), the obstacle is considered stationary; otherwise, the obstacle is considered moving.

[0069] Optionally, a second determination is made regarding whether the obstacle's trajectory within a predetermined time period is a straight line or a parabola, including:

[0070] Based on the two-dimensional image information, the first motion trajectory is obtained;

[0071] Based on 3D point cloud information, obtain 3D motion trajectory;

[0072] The three-dimensional motion trajectory is projected onto the two-dimensional plane of the camera to obtain the second motion trajectory;

[0073] The first and second motion trajectories are fitted together to form the third motion trajectory;

[0074] Determine whether the third trajectory is a straight line or a parabola.

[0075] Preferably, the method for obtaining the obstacle's motion trajectory through the camera's photo stream includes: taking the front-facing camera as an example, establishing a Cartesian coordinate system with the lower left corner of the photo taken by the front-facing camera as the origin, and performing rasterization processing on the image containing the obstacle, and then obtaining the grid where the obstacle is located; obtaining the grid where the obstacle is located again at certain intervals (e.g., 30ms); continuously detecting a certain number of times, such as 50 times, and connecting the center point of the grid where the obstacle is located to obtain a trajectory of the obstacle.

[0076] Preferably, the method for obtaining the obstacle's trajectory using the point cloud detection information of the lidar includes: using the lidar point cloud coordinate system, connecting the center points of the object at regular intervals (e.g., 30ms) over a period of time to obtain the object's trajectory in the three-dimensional world.

[0077] Preferably, the trajectory fitting method obtained by the camera and lidar includes: using the plane where the camera is located as the projection plane, mapping the three-dimensional motion trajectory to the two-dimensional plane where the camera is located; for each point (x1, y1) and (x2, y2) on the two curves at the same time, calculating the fitting point (x, y) respectively, the calculation method is x = (x1 + x2) / 2, y = (y1 + y2) / 2.

[0078] Optionally, a third determination is made regarding whether the obstacle maintains its shape within a predetermined time period, including:

[0079] Based on two-dimensional image information, perform the first sub-judgment on whether the obstacle maintains its shape within a predetermined time period;

[0080] Based on 3D point cloud information, a second sub-judgment is performed to determine whether the obstacle maintains its shape within a predetermined time period.

[0081] If the result of either the first or second sub-judgment is positive, then the third judgment outputs a positive result; conversely, if the results of both the first and second sub-judgments are negative, then the third judgment outputs a negative result.

[0082] Optionally, a third determination is made regarding whether the obstacle maintains its shape within a predetermined time period, including:

[0083] Determine whether the multiple distances between various feature points of the obstacle and the ratios of these distances have changed;

[0084] If any of the multiple distances or the ratio of multiple distances changes, it is determined that the obstacle has failed to maintain its shape within the predetermined time period.

[0085] S400. If the first judgment yields an affirmative result, the obstacle is judged to be more dangerous than if the first judgment yields a negative result. And / or, if the second judgment yields an affirmative result, the obstacle is judged to be more dangerous than if the second judgment yields a negative result. And / or, if the third judgment yields an affirmative result, the obstacle is judged to be more dangerous than if the third judgment yields a negative result.

[0086] It should be noted that if an obstacle's trajectory is straight or parabolic, it is considered to have a large mass and may cause significant damage to the vehicle; in this case, the obstacle should be avoided immediately. If the obstacle's trajectory is irregular, it is considered to have a small mass and may cause minor or no damage to the vehicle; in this case, no avoidance measures are necessary. If the obstacle does not deform during its movement, it is considered to have a high rigidity and will cause significant damage to the vehicle; if it deforms, it is considered to have a low rigidity and will cause less damage to the vehicle. Stationary obstacles are always considered to pose a higher risk.

[0087] This embodiment uses observation information of obstacles to determine the movement state of obstacles, including movement trajectory, whether they are stationary or deformed, etc., thereby further judging the danger of obstacles and taking corresponding countermeasures.

[0088] Optionally, Figure 2 A flowchart illustrating another method for determining the hazard of an obstacle provided by the present invention is shown below. Figure 2 As shown, the method includes:

[0089] If any one of the first, second, or third judgments yields a positive result, then the obstacle is judged as a high-risk obstacle.

[0090] Optionally, an obstacle is determined to be a high-risk obstacle, including:

[0091] Issue a high-risk warning and / or issue control commands to avoid obstacles.

[0092] Furthermore, the method's judgment logic includes:

[0093] First, if the obstacle is detected to be stationary, the motion state score is 1.

[0094] Secondly, if obstacle movement is detected: further, if the obstacle's trajectory is detected to be approximately a straight line or a parabola, the trajectory score is 1; otherwise, the trajectory score is 0. Further, if the obstacle has a shape change, the shape change score is 0; otherwise, the shape change score is 1.

[0095] Finally, the scores are summed. If the total score is 0, the obstacle risk is considered low; otherwise, the obstacle risk is considered high. A risk warning is immediately issued to the safety officer, or an obstacle avoidance control command is issued to automatically control the vehicle to avoid the obstacle.

[0096] The system for determining the hazard of obstacles provided by the present invention will be described below. The system for determining the hazard of obstacles described below can be referred to in correspondence with the method for determining the hazard of obstacles described above.

[0097] Figure 3 This invention also provides a schematic diagram of a system structure for determining the hazard of obstacles, such as... Figure 3 As shown, the present invention also provides a system for determining the hazard of an obstacle, the system comprising:

[0098] The acquisition module is used to acquire observation information of obstacles within a predetermined time period;

[0099] The classification module is used to classify obstacles based on observation information and obtain classification results;

[0100] The intermediate judgment module is used to perform the following judgments: if the classification result belongs to an unknown category, then based on the observation information, it performs the first judgment of whether the obstacle is stationary within a predetermined time period, and / or performs the second judgment of whether the obstacle's trajectory within the predetermined time period is a straight line or a parabola, and / or performs the third judgment of whether the obstacle maintains its shape within the predetermined time period.

[0101] The hazard assessment module is used to perform the following judgments: if the first judgment results in a positive result, the obstacle is judged to be more dangerous than if the first judgment results in a negative result; and / or, if the second judgment results in a positive result, the obstacle is judged to be more dangerous than if the second judgment results in a negative result; and / or, if the third judgment results in a positive result, the obstacle is judged to be more dangerous than if the third judgment results in a negative result.

[0102] This embodiment uses observation information of obstacles to determine the movement state of obstacles, including movement trajectory, whether they are stationary or deformed, and thus further determines the danger of obstacles.

[0103] Figure 4 A schematic diagram of the physical structure of an electronic device provided by the present invention, such as... Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a method for determining the hazard of an obstacle, the method including:

[0104] Obtain observation information of obstacles within a predetermined time period;

[0105] Based on the observation information, the obstacles are classified, and the classification results are obtained;

[0106] If the classification result belongs to an unknown category, then based on the observation information, a first judgment is made as to whether the obstacle is stationary during the predetermined time period, and / or a second judgment is made as to whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or a third judgment is made as to whether the obstacle maintains its shape during the predetermined time period.

[0107] If the first judgment yields an affirmative result, the obstacle is deemed more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields an affirmative result, the obstacle is deemed more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields an affirmative result, the obstacle is deemed more dangerous than if the third judgment yields a negative result.

[0108] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] The present invention also provides a vehicle having autonomous driving and / or assisted driving functions, the vehicle including electronic devices.

[0110] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to perform the methods provided above for determining the hazard of obstacles, the methods comprising:

[0111] Obtain observation information of obstacles within a predetermined time period;

[0112] Based on the observation information, the obstacles are classified, and the classification results are obtained;

[0113] If the classification result belongs to an unknown category, then based on the observation information, a first judgment is made as to whether the obstacle is stationary during the predetermined time period, and / or a second judgment is made as to whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or a third judgment is made as to whether the obstacle maintains its shape during the predetermined time period.

[0114] If the first judgment yields an affirmative result, the obstacle is deemed more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields an affirmative result, the obstacle is deemed more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields an affirmative result, the obstacle is deemed more dangerous than if the third judgment yields a negative result.

[0115] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the methods for determining the hazard of obstacles provided above, the methods comprising:

[0116] Obtain observation information of obstacles within a predetermined time period;

[0117] Based on the observation information, the obstacles are classified, and the classification results are obtained;

[0118] If the classification result belongs to an unknown category, then based on the observation information, a first judgment is made as to whether the obstacle is stationary during the predetermined time period, and / or a second judgment is made as to whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or a third judgment is made as to whether the obstacle maintains its shape during the predetermined time period.

[0119] If the first judgment yields an affirmative result, the obstacle is deemed more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields an affirmative result, the obstacle is deemed more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields an affirmative result, the obstacle is deemed more dangerous than if the third judgment yields a negative result.

[0120] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, 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 can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the hazard of an obstacle, characterized in that, The method includes: Obtain observation information of obstacles within a predetermined time period; Based on the observation information, the obstacles are classified, and the classification results are obtained; If the classification result belongs to an unknown category, then based on the observation information, a first judgment is made as to whether the obstacle is stationary during the predetermined time period, and / or a second judgment is made as to whether the trajectory of the obstacle during the predetermined time period is a straight line or a parabola, and / or a third judgment is made as to whether the obstacle maintains its shape during the predetermined time period. Performing a third determination on whether the obstacle maintains its shape during the predetermined time period includes: Determine whether the multiple distances between various feature points of the obstacle and the ratios of these distances have changed; If any of the plurality of distances or the ratio of the plurality of distances changes, it is determined that the obstacle has failed to maintain its shape within the predetermined time period; If the first judgment yields an affirmative result, then the obstacle is judged to be more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields an affirmative result, then the obstacle is judged to be more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields an affirmative result, then the obstacle is judged to be more dangerous than if the third judgment yields a negative result. The method's judgment logic includes: First, if the obstacle is detected to be stationary, the motion state score is 1; Secondly, if obstacle movement is detected: further, if the obstacle's trajectory is detected to be approximately a straight line or a parabola, the trajectory score is 1; otherwise, the trajectory score is 0. Further, if the obstacle has a shape change, the shape change score is 0; otherwise, the shape change score is 1. Finally, the scores are summed. If the total score is 0, the obstacle risk is considered low; otherwise, the obstacle risk is considered high, and a risk warning is immediately issued to the safety officer, or an obstacle avoidance control command is issued to automatically control the vehicle to avoid the obstacle.

2. The method for determining the hazard of an obstacle according to claim 1, characterized in that, The method further includes: If any one of the first, second, or third judgments yields a positive result, then the obstacle is determined to be a high-risk obstacle.

3. The method for determining the hazard of an obstacle according to claim 2, characterized in that, The following criteria are used to determine if an obstacle is a high-risk obstacle: Issue a high-risk warning and / or issue control commands to avoid the obstacle.

4. The method for determining the hazard of an obstacle according to claim 1, characterized in that, Performing a first determination of whether the obstacle is stationary during the predetermined time period includes: Obtain the first distance between the obstacle and the observer at the first moment; Obtain the second distance between the obstacle and the observer at a second moment; Assuming the obstacle is stationary, based on the first distance and the observer's velocity information, predict the third distance between the obstacle and the observer at a second moment; If the third distance matches the second distance, the obstacle is determined to be stationary; otherwise, if the third distance does not match the second distance, the obstacle is determined to be moving.

5. The method for determining the hazard of an obstacle according to claim 1, characterized in that, Obtain observation information of obstacles within a predetermined time period, including: Based on the camera, acquire two-dimensional image information of the obstacle within the predetermined time period; Based on lidar, the three-dimensional point cloud information of the obstacle is acquired within the predetermined time period.

6. The method for determining the hazard of an obstacle according to claim 5, characterized in that, The second determination of whether the trajectory of the obstacle within the predetermined time period is a straight line or a parabola includes: Based on the two-dimensional image information, the first motion trajectory is obtained; Based on the three-dimensional point cloud information, a three-dimensional motion trajectory is obtained; The three-dimensional motion trajectory is projected onto the two-dimensional plane of the camera to obtain the second motion trajectory; The first motion trajectory and the second motion trajectory are fitted together to form a third motion trajectory; Determine whether the third motion trajectory is a straight line or a parabola.

7. The method for determining the hazard of an obstacle according to claim 5, characterized in that, Performing a third determination on whether the obstacle maintains its shape during the predetermined time period includes: Based on the two-dimensional image information, a first sub-determination is performed to determine whether the obstacle maintains its shape within the predetermined time period; Based on the three-dimensional point cloud information, a second sub-determination is performed to determine whether the obstacle maintains its shape within the predetermined time period; If the result of either the first sub-judgment or the second sub-judgment is positive, then the third judgment outputs a positive result; otherwise, if the results of both the first and second sub-judgments are negative, then the third judgment outputs a negative result.

8. A system for determining the hazard of an obstacle, characterized in that, The system includes: The acquisition module is used to acquire observation information of obstacles within a predetermined time period; The classification module is used to classify the obstacles based on the observation information and obtain the classification results; The intermediate judgment module is used to perform the following judgments: if the classification result belongs to an unknown category, then based on the observation information, it performs a first judgment on whether the obstacle is stationary within the predetermined time period, and / or performs a second judgment on whether the obstacle's trajectory within the predetermined time period is a straight line or a parabola, and / or performs a third judgment on whether the obstacle maintains its shape within the predetermined time period; the third judgment on whether the obstacle maintains its shape within the predetermined time period includes: judging whether multiple distances between various feature points of the obstacle and the ratio of these multiple distances have changed; if any of the multiple distances or the ratio of the multiple distances has changed, it is judged that the obstacle has failed to maintain its shape within the predetermined time period; The hazard assessment module performs the following judgments: if the first judgment yields a positive result, the obstacle is considered more dangerous than if the first judgment yields a negative result; and / or, if the second judgment yields a positive result, the obstacle is considered more dangerous than if the second judgment yields a negative result; and / or, if the third judgment yields a positive result, the obstacle is considered more dangerous than if the third judgment yields a negative result. The judgment logic of the method includes: first, if the obstacle is detected to be stationary, the motion state score is 1; second, if the obstacle is detected to be moving: further, if the obstacle's trajectory is detected to be approximately a straight line or a parabola, the trajectory score is 1; otherwise, the trajectory score is 0; further, if the obstacle is detected to have a shape change, the deformation score is 0; otherwise, the deformation score is 1; finally, the scores are summed. If the total score equals 0, the obstacle is considered to have a low risk; otherwise, the obstacle is considered to have a high risk, and a risk warning is immediately issued to the safety officer, or a control command to avoid the obstacle is issued to automatically control the vehicle to avoid it.

9. 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, it implements the steps of the method for determining the danger of an obstacle as described in any one of claims 1-7.

10. A vehicle, characterized in that, The vehicle has autonomous driving and / or driver assistance functions, and the vehicle includes the electronic device as described in claim 9.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for determining the danger of an obstacle as described in any one of claims 1-7.

Images