Vehicle abnormal behavior early warning method, device and equipment

Abstract

The invention discloses a vehicle abnormal behavior early warning method, device and equipment, and relates to the technical field of traffic. The vehicle abnormal behavior early warning method disclosed by the invention comprises the following steps: according to vehicle real-time operation information and real-time signal lamp information, determining whether a vehicle at an intersection is not started after a green light is turned on; under the condition that the vehicle is not started after the green light is turned on, the road condition in front of the vehicle is determined according to the vehicle real-time video stream; and responding to a road condition in front of the vehicle to trigger an early warning condition, and sending an early warning prompt to the vehicle. According to the scheme, intersection congestion can be relieved, the traffic fluency of the intersection, namely the traffic fluency near the intersection, can be improved, a driver can be reminded to concentrate attention, traffic potential safety hazards are reduced, and the possibility of accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a vehicle abnormal behavior early warning method, device and equipment. Background Art

[0002] At traffic intersections, vehicles often fail to start in time after the green light comes on, which may lead to a backlog of subsequent vehicles, increasing the risk of traffic delays and congestion at the intersection. One of the reasons for this phenomenon is the driver's distracted driving behavior. At present, there is no effective means to analyze the reasons why the driver fails to start the vehicle in time after the green light comes on. On this basis, no warning reminder can be issued for vehicles that fail to start in time after the green light comes on due to driver distraction, which can easily lead to a backlog of subsequent vehicles, increasing the risk of traffic delays and congestion at the intersection. Summary of the invention

[0003] In view of this, the present invention proposes a vehicle abnormal behavior warning method, device and equipment, which solves the problem that there is no effective means in the prior art to analyze the reason why the driver fails to start the vehicle in time after the green light comes on, and the problem that a warning reminder cannot be issued for the vehicle that fails to start in time after the green light comes on due to the driver's distraction.

[0004] On the one hand, an embodiment of the present invention provides a vehicle abnormal behavior warning method, the vehicle abnormal behavior warning method comprising: According to the real-time vehicle operation information and real-time traffic light information, determine whether the vehicle at the intersection has not started after the green light comes on; If the vehicle does not start after the green light comes on, determine the road condition in front of the vehicle based on the real-time video stream of the vehicle; In response to the road conditions ahead of the vehicle triggering a warning condition, a warning reminder is sent to the vehicle.

[0005] In some embodiments of the present invention, when a vehicle does not start after the green light comes on, the road condition ahead of the vehicle is obtained based on the real-time video stream of the vehicle, including: When the vehicle does not start after the green light comes on, obtain the duration of the green light, and determine whether the duration is greater than a threshold; When the lighting duration is greater than the threshold, the road condition in front of the vehicle is determined based on the vehicle's real-time video stream.

[0006] In some embodiments of the present invention, obtaining the recognition result of the target to be detected in front of the vehicle and the recognition result of the lane traffic line according to the real-time video stream of the vehicle includes: extracting a plurality of frames of images from the real-time video stream of the vehicle; recognizing each frame of the image to obtain the recognition result of the target to be detected; In response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to the vehicle includes: in response to the recognition result of the target to be detected identified according to a plurality of frames of images triggering a warning condition, sending a warning reminder to the vehicle.

[0007] In some embodiments of the present invention, each frame of the image is recognized to obtain a recognition result of the target to be detected, including: The target area in each frame of the image is identified according to the target detection model to obtain the recognition result of the target to be detected.

[0008] In some embodiments of the present invention, the warning condition includes that there is no target to be detected in front of the vehicle.

[0009] In response to the road conditions ahead of the vehicle triggering a warning condition, a warning reminder is sent to the vehicle, including: In response to there being no target to be detected in front of the vehicle, a warning reminder is sent to the vehicle.

[0010] In some embodiments of the present invention, the method further includes: in response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to a vehicle behind the vehicle.

[0011] In some embodiments of the present invention, the method also includes: obtaining real-time vehicle operation information, real-time vehicle video stream and real-time signal light information, aligning the real-time vehicle operation information, real-time vehicle video stream and real-time signal light information to obtain aligned real-time vehicle operation information, real-time vehicle video stream and real-time signal light information.

[0012] In some embodiments of the present invention, determining whether a vehicle at an intersection has not started after the green light comes on, based on the real-time vehicle operation information and the real-time signal light information, includes: Determine whether the vehicle is parked based on the real-time operation information of the vehicle; When the vehicle is parked, determine whether the vehicle is at an intersection based on high-precision maps and real-time vehicle operation information; When the vehicle is at an intersection, the phase of the lane the vehicle is in is determined based on the high-precision map and the vehicle's real-time operation information; Real-time traffic light information is obtained, and based on the phase of the lane where the vehicle is located and the real-time traffic light information, it is determined whether the vehicle at the intersection has not started after the green light comes on.

[0013] On the other hand, an embodiment of the present invention further provides an early warning device, the early warning device comprising: A determination module configured to determine whether a vehicle at an intersection has not started after the green light comes on, based on the real-time vehicle operation information and the real-time signal light information; The recognition module is configured to obtain the road condition in front of the vehicle according to the real-time video stream of the vehicle when the vehicle does not start after the green light comes on; The warning module is configured to send a warning reminder to the vehicle in response to the road conditions in front of the vehicle triggering the warning condition.

[0014] On the other hand, an embodiment of the present invention further provides an electronic device, comprising: at least one processor; and a memory, the memory storing a computer program that can be run on the processor, characterized in that when the processor executes the program, the steps of the method of any of the above embodiments are performed.

[0015] On the other hand, an embodiment of the present invention further provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of any of the above embodiments are executed.

[0016] The present invention has at least the following beneficial effects: The present invention provides a method, device and equipment for warning of abnormal vehicle behavior. The method, device and equipment for warning of abnormal vehicle behavior provided by the present invention can determine whether a vehicle at an intersection has not started after the green light comes on based on the real-time operation information of the vehicle and the real-time signal light information; if the vehicle has indeed not started after the green light comes on, the road condition in front of the vehicle is obtained based on the real-time video stream of the vehicle, and then it can be determined whether to send a warning reminder to the vehicle based on whether the road condition in front of the vehicle triggers the warning condition. The scheme of the present invention can send a warning reminder to the vehicle in a timely manner when the road condition in front of the vehicle triggers the warning condition. By sending a warning reminder to the vehicle, it can not only improve the traffic efficiency and avoid wasting the green light time, but also alleviate the congestion at the intersection, improve the traffic flow at the intersection, and remind the driver to concentrate, reduce traffic safety hazards, and reduce the possibility of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a vehicle abnormal behavior warning method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a vehicle located at an intersection provided by an embodiment of the present invention; Figure 3A flow chart for determining whether a vehicle at an intersection has not started after the green light comes on, provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an early warning device provided by an embodiment of the present invention; Figure 5 A schematic diagram of an application scenario of the early warning device provided by an embodiment of the present invention; Figure 6 A flowchart of a vehicle abnormal behavior warning method provided by an embodiment of the present invention; Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention; Figure 8 A schematic diagram of the structure of a computer storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0020] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0021] At traffic intersections, vehicles often fail to start in time after the green light comes on. One of the reasons for this is the driver's distracted driving behavior. However, there is currently no effective means to analyze the reasons why the driver fails to start the vehicle in time after the green light comes on. On this basis, no warning reminder can be issued for vehicles that fail to start in time after the green light comes on due to driver distraction, which can easily lead to the accumulation of subsequent vehicles, reduce vehicle communication efficiency, increase the risk of intersection congestion, and easily bring traffic safety hazards and increase the possibility of traffic accidents.

[0022] In view of this, in order to solve at least one of the above technical problems, an embodiment of the present invention provides a vehicle abnormal behavior warning method. The present invention is described in detail below in conjunction with the embodiments and drawings.

[0023] A first aspect of an embodiment of the present invention provides a vehicle abnormal behavior warning method, such as Figure 1 As shown, the vehicle abnormal behavior warning method may include steps S10 to S12.

[0024] S10. Determine whether a vehicle at an intersection has not started after the green light comes on, based on the real-time vehicle operation information and the real-time traffic light information.

[0025] The vehicle may be a connected vehicle, for example, a vehicle with an autonomous driving function or a vehicle that can be connected to a cloud server, so that the cloud server can obtain the operating information of the vehicle.

[0026] Vehicle real-time operation information refers to the vehicle operation information collected in real time, such as speed, acceleration, braking, position, etc.

[0027] Real-time traffic light information refers to traffic light information collected in real time, such as the color of the traffic light, the time when the traffic light turns on a certain color, the location of the traffic light, and other information.

[0028] The vehicle at the intersection refers to the vehicle closest to the intersection on each lane connected by the traffic intersection. For example, in one example, Figure 2 As shown, at a T-junction, there are four vehicles, namely vehicle 1_1, vehicle 1_1, vehicle 2_1, and vehicle 2_2, wherein vehicle 1_1 and vehicle 2_1 are vehicles located at the intersection.

[0029] S11. When the vehicle does not start after the green light comes on, determine the road condition ahead of the vehicle based on the real-time video stream of the vehicle.

[0030] The real-time vehicle video stream refers to the video stream of the vehicle's surrounding environment collected by the vehicle, such as the video in front of the vehicle, the video behind the vehicle, etc.

[0031] Based on the video stream in front of the vehicle in the real-time video stream of the vehicle, the road occupancy situation in front of the vehicle can be obtained, and based on this, it is judged whether the warning condition is triggered when the vehicle does not start after the green light comes on.

[0032] S12: In response to the road condition in front of the vehicle triggering a warning condition, a warning reminder is sent to the vehicle.

[0033] The warning condition may be that there is no target to be detected in front of the vehicle that may affect the vehicle's starting. The target to be detected may be a person, a vehicle, an obstacle, a lane sign, etc., which is not specifically limited here.

[0034] In some examples, if the road conditions in front of the vehicle do not trigger a warning condition, for example, if there is a pedestrian in front of the vehicle that affects the vehicle's start, no action is required.

[0035] In some examples, if the road conditions in front of the vehicle trigger a warning condition, it means that the vehicle has abnormal behavior. The cause of the abnormal behavior may be driver distraction, abnormal vehicle start-up, etc. At this time, a warning can be issued by sending a prompt voice or prompt information to the vehicle.

[0036] The solution of the present invention can determine whether a vehicle at an intersection has not started after the green light comes on based on the real-time operation information of the vehicle and the real-time signal light information; if the vehicle has indeed not started after the green light comes on, the road conditions in front of the vehicle can be obtained based on the real-time video stream of the vehicle, and then it can be determined whether to send a warning reminder to the vehicle based on whether the road conditions in front of the vehicle trigger the warning conditions, and in the case where the road conditions in front of the vehicle trigger the warning conditions, a warning reminder is sent to the vehicle in a timely manner. By sending warning reminders to vehicles, it is possible to improve traffic efficiency and avoid wasting green light time, and to alleviate intersection congestion, improve traffic flow at intersections or near intersections, and remind drivers to concentrate, reduce traffic safety hazards, and reduce the possibility of accidents.

[0037] In some embodiments of the present invention, Figure 1 The step S11 shown, when the vehicle does not start after the green light comes on, obtaining the road condition in front of the vehicle according to the real-time video stream of the vehicle, can include: when the vehicle does not start after the green light comes on, obtaining the lighting time of the green light and determining whether the lighting time is greater than a threshold; when the lighting time is greater than the threshold, obtaining the road condition in front of the vehicle according to the real-time video stream of the vehicle.

[0038] The threshold is a preset duration. For example, the preset duration may be 1s, 2s, 3s, 4s, 5s, etc., which is not specifically limited here.

[0039] In a specific implementation, the duration of the green light is obtained and compared with a preset threshold. When the duration is greater than the threshold, the real-time video stream of the vehicle at the current moment is obtained. The road condition ahead of the vehicle is analyzed based on the real-time video stream of the vehicle at the current moment. This can eliminate the reaction time of the driver and the impact on the vehicle's start, thereby improving the accuracy of subsequent vehicle warnings.

[0040] In some embodiments of the present invention, Figure 1 In step S11 shown, determining the road condition in front of the vehicle according to the real-time video stream of the vehicle may include: extracting a number of frames of images from the real-time video stream of the vehicle; and identifying each frame of image to obtain a recognition result of the target to be detected.

[0041] Specifically, in order to reduce the amount of calculation, increase the calculation speed, and improve the real-time nature of the early warning, several frames of images can be extracted from the video stream according to the preset sampling time. For example, if the preset sampling time is 100ms, then for the real-time video stream of 1s, 10 frames of images can be collected for processing, but it is not limited to this, and the preset sampling time can be set according to the needs.

[0042] On this basis, if Figure 1In step S11 shown, in response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to the vehicle may include: in response to the recognition result of the target to be detected identified according to several frames of images triggering the warning condition, sending a warning reminder to the vehicle.

[0043] Specifically, the recognition results of the target to be detected obtained by comprehensively considering several frames of image recognition are used to determine whether the vehicle triggers the warning condition, so that the situation of triggering the warning condition can be judged more accurately, thereby improving the accuracy of issuing warning reminders.

[0044] For example, 15 frames of images are extracted based on a video stream per unit time. Among the 15 frames of images, one or more frames detect the target to be detected. It can be considered that the vehicle does not start after the green light comes on because there is a target to be detected in front of the vehicle.

[0045] The targets to be detected can be traffic participants and objects, such as pedestrians, vehicles, obstacles, traffic signs, signal lights, etc.

[0046] In some embodiments of the present invention, identifying each frame of image to obtain a recognition result of the target to be detected may include: identifying a target area in each frame of image according to a target detection model to obtain a recognition result of the target to be detected.

[0047] The target detection model can use models such as Sort, UpdateNet, and CFNet.

[0048] The target area can be defined as needed to exclude information irrelevant to the vehicle's driving. For example, the target area can be defined as a certain distance range in front of the vehicle in the lane where the vehicle is located.

[0049] In some examples, embodiments of the present invention can identify the target area in each frame of the image according to the Sort model to obtain a recognition result of the target to be detected.

[0050] In a specific implementation of the present invention, on the basis of determining the road condition ahead of the vehicle through the recognition result of the target to be detected, the road condition ahead can also be determined in combination with the traffic line condition of the lane.

[0051] Specifically, the target area in each frame of the image can be identified according to the lane detection model to obtain the lane traffic line recognition result.

[0052] The lane detection model can adopt models such as LaneNet or SCNN.

[0053] Lane traffic lines can be traffic signs, left turn lane lines, straight lane lines, no parking lane lines, zebra crossings, etc. The lane detection model can identify the position and shape of lane traffic lines in the target area to determine the type of lane traffic lines and whether it affects the start of the current vehicle.

[0054] By determining whether the warning conditions are triggered through the identification results of the target to be detected and the lane traffic line identification results, it is possible to more accurately determine whether the road conditions ahead of the vehicle trigger the warning conditions, further improving the accuracy of issuing warning reminders.

[0055] In some embodiments of the present invention, Figure 1 In step S12 shown, in response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to the vehicle may include: in response to there being no target to be detected in front of the vehicle, sending a warning reminder to the vehicle.

[0056] According to the road conditions in front of the vehicle, determine whether the vehicle triggers the warning condition. The warning condition can be that there is no target to be detected in front of the vehicle. If there is a target to be detected in front of the vehicle, such as pedestrians, vehicles, obstacles, etc., it can be determined that the vehicle has not started when the green light is on and the warning condition has not been triggered, and there is no need to send a warning reminder to the vehicle. If there is no target to be detected in front of the vehicle, it is determined that the vehicle has not started when the green light is on and it is not caused by the target to be detected, which means that the vehicle has abnormal behavior. The cause of the abnormal behavior may be the driver's distraction, the vehicle starts abnormally, etc., that is, the warning condition is triggered. At this time, it is necessary to send a warning reminder to the vehicle. In this way, it can not only improve traffic efficiency and avoid wasting green light time, but also alleviate intersection congestion, improve the traffic flow at the intersection or near the intersection, but also remind drivers to concentrate, reduce traffic safety hazards, and reduce the possibility of accidents.

[0057] In some embodiments of the present invention, the method further includes: in response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to a vehicle behind the vehicle.

[0058] Specifically, in response to a vehicle at an intersection not starting after the green light comes on and there is no target to be detected in front of the vehicle, a warning reminder is sent to the vehicle behind the vehicle. By sending a warning reminder to the vehicle behind the vehicle that has not started after the green light comes on, the vehicle behind can be reminded that "the vehicle in front has not started after the green light comes on", thereby reminding the driver of the vehicle behind to drive carefully to avoid rear-ending the vehicle in front, further reducing the possibility of accidents.

[0059] In some embodiments of the present invention, the method also includes: obtaining real-time vehicle operation information, real-time vehicle video stream and real-time signal light information, aligning the real-time vehicle operation information, real-time vehicle video stream and real-time signal light information to obtain aligned real-time vehicle operation information, real-time vehicle video stream and real-time signal light information.

[0060] Aligning the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information may include: temporal alignment and spatial alignment of the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information.

[0061] Specifically, the time of the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information is synchronized through the timestamps of the three, and the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information after time synchronization are obtained. Afterwards, the position information in the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information is aligned to the same coordinate system, thereby ensuring the spatial consistency of the real-time vehicle operation information, the real-time vehicle video stream and the real-time traffic light information.

[0062] In some embodiments of the present invention, the acquired real-time vehicle operation information, real-time vehicle video stream and real-time traffic light information can also be filtered, thereby reducing noise interference. When the filtered real-time vehicle operation information, real-time vehicle video stream and real-time traffic light information are used for subsequent abnormal behavior analysis of the vehicle not starting after the green light comes on, the analysis accuracy can be improved and misjudgment can be avoided. In some embodiments of the present invention, Figure 1 Step S10 shown in the figure, based on the real-time vehicle operation information and the real-time signal light information, determines whether the vehicle at the intersection has not started after the green light comes on, which may include the following steps: Figure 3 Steps S30~S34 are shown.

[0063] S30, obtaining real-time vehicle operation information, real-time vehicle video stream and real-time traffic light information.

[0064] S31. Determine whether the vehicle is parked according to the real-time operation information of the vehicle.

[0065] Whether the vehicle is in a parked state can be determined based on whether the vehicle speed in the real-time vehicle operation information is 0. If the vehicle speed is 0, the vehicle is in a parked state. If the vehicle speed is not 0, the vehicle is not in a parked state.

[0066] S32. When the vehicle is parked, determine whether the vehicle is located at an intersection based on a high-precision map and real-time vehicle operation information.

[0067] An HD map is a high-precision map that covers map elements such as roads, lanes, intersections, roadside traffic signs and ground signs. The map accuracy can reach the centimeter level.

[0068] The vehicle location information in the real-time vehicle operation information can be mapped to a high-precision map to determine whether the vehicle is at an intersection.

[0069] S33. When the vehicle is at an intersection, determine the phase of the lane in which the vehicle is located based on the high-precision map and the real-time operation information of the vehicle.

[0070] When the vehicle is at an intersection, the lane the vehicle is in and the phase of the lane the vehicle is in are determined based on the vehicle's position information in the high-precision map.

[0071] The phase of the lane can be left turn, right turn or straight ahead, that is, when the vehicle is at the intersection, the vehicle's position information in the high-precision map is used to determine whether the lane the vehicle is in is a left turn lane, a right turn lane or a straight ahead lane. This allows the corresponding traffic light information to be matched.

[0072] S34, obtaining real-time traffic light information, and determining whether the vehicle at the intersection has not started after the green light comes on, based on the phase of the lane where the vehicle is located and the real-time traffic light information.

[0073] Through the phase of the lane where the vehicle is located and the corresponding real-time traffic light information of the lane, it can be determined whether the vehicle at the intersection has not started after the green light comes on. If the vehicle does not start after the green light comes on, the road conditions in front of the vehicle will be analyzed in combination with the real-time video stream to determine whether to send an early warning reminder to the vehicle.

[0074] Based on the same inventive concept, the embodiment of the present invention also provides an early warning device, such as Figure 4 As shown, the early warning device 40 may include: A determination module 41 is configured to determine whether a vehicle at an intersection has not started after the green light comes on, based on the real-time vehicle operation information and the real-time signal light information; The recognition module 42 is configured to obtain the road condition ahead of the vehicle according to the real-time video stream of the vehicle when the vehicle does not start after the green light comes on; The warning module 43 is configured to send a warning reminder to the vehicle in response to the road condition in front of the vehicle triggering the warning condition.

[0075] The specific embodiments of the present invention are described below by means of specific examples.

[0076] Reference Figure 5 and Figure 6 .

[0077] Figure 5An application scenario of an embodiment of the present invention is shown. In this application scenario, the early warning device is located in a cloud server, and the cloud server collects real-time vehicle operation data and real-time vehicle video stream data from the connected vehicle in real time through a data acquisition unit, and collects real-time signal light data from the traffic signal system in real time, and sends all collected real-time data to the early warning device.

[0078] The warning device performs the following operations based on the vehicle's real-time operation data, vehicle real-time video stream data, and real-time traffic light data: Figure 6 Steps shown.

[0079] S61. Receive the vehicle real-time operation data, vehicle real-time video stream data and real-time traffic light data sent by the data acquisition unit, and perform multi-source data fusion and analysis on the vehicle real-time operation data, vehicle real-time video stream data and real-time traffic light data to determine whether the connected vehicle at the intersection has not started after the green light comes on.

[0080] S62, the green light turns on and the test starts When the green light signal comes on, the system enters the detection mode, records the green light time, and starts collecting the vehicle's starting conditions.

[0081] S63. Determine whether the green light is blocked.

[0082] The system determines whether the vehicle starts or accelerates within the set time after the green light comes on. If the vehicle does not start within the set time, the system analyzes the road conditions ahead of the vehicle to further determine whether the warning conditions are triggered.

[0083] S64: Analyze the road conditions ahead, determine whether a warning condition is triggered, and generate a detection result.

[0084] The video stream artificial intelligence model analyzes the road conditions ahead to determine whether the warning condition is triggered. If there is no target to be detected in front of the vehicle, the warning condition is triggered, otherwise the warning condition is not triggered. The detection result is generated based on whether the warning condition is triggered and sent to the data feedback module.

[0085] S65. If the detection result is a triggering warning condition, a reminder is generated and fed back to the connected vehicle that is blocking the green light.

[0086] When the detection result triggers a warning condition, the data feedback module generates a reminder and feeds it back to the connected vehicle that is blocking the green light, thereby reminding the driver of the connected vehicle to concentrate and start.

[0087] S66. If the detection result is a triggering warning condition, a reminder is generated and fed back to the connected vehicle behind the connected vehicle blocking the green light.

[0088] When the detection result is a condition that triggers an early warning, the data feedback module generates a reminder and sends it to the connected vehicle behind the connected vehicle that is blocking the green light, thereby sending a reminder message or an early warning signal to the vehicle behind.

[0089] Based on the same inventive concept, according to another aspect of the present invention, Figure 7 As shown, an embodiment of the present invention further provides an electronic device 70, which includes a processor 710 and a memory 720. The memory 720 stores a computer program 721 that can be run on the processor. When the processor 710 executes the program, the steps of the above method are performed.

[0090] Among them, the memory, as a non-volatile storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the compression method in the embodiment of the present application. The processor executes various functional applications and data processing of the device by running the non-volatile software programs, instructions and modules stored in the memory, that is, realizing the compression method of the above method embodiment.

[0091] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments of the present invention, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0092] Based on the same inventive concept, according to another aspect of the present invention, Figure 8 As shown, an embodiment of the present invention further provides a computer storage medium 80, which stores a computer program 81 that performs the above method when executed by a processor.

[0093] Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiments can achieve the same or similar effects as the corresponding above-mentioned any method embodiments.

[0094] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0095] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope of the embodiments disclosed in the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0096] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.

[0097] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A vehicle abnormal behavior warning method, characterized in that: include: According to the real-time vehicle operation information and real-time traffic light information, determine whether the vehicle at the intersection has not started after the green light comes on; In the case where the vehicle does not start after the green light comes on, determining the road condition ahead of the vehicle based on the real-time video stream of the vehicle; In response to the road condition in front of the vehicle triggering a warning condition, a warning reminder is sent to the vehicle.

2. The method according to claim 1, characterized in that In the case that the vehicle does not start after the green light comes on, determining the road condition ahead of the vehicle according to the real-time video stream of the vehicle includes: In the case that the vehicle does not start after the green light turns on, obtaining the duration of the green light turning on, and determining whether the duration of the green light turning on is greater than a threshold; When the lighting duration is greater than a threshold, the road condition in front of the vehicle is determined based on the real-time video stream of the vehicle.

3. The method according to claim 1, characterized in that Determining the road condition ahead of the vehicle according to the real-time video stream of the vehicle includes: Extracting a number of frames of images from the real-time video stream of the vehicle shown; Identify each frame of the image to obtain the recognition result of the target to be detected; In response to the road condition in front of the vehicle triggering a warning condition, sending a warning reminder to the vehicle includes: in response to the recognition result of the target to be detected identified according to the plurality of frames of images triggering a warning condition, sending a warning reminder to the vehicle.

4. The method according to claim 3, characterized in that Recognize each frame of the image to obtain the recognition result of the target to be detected, including: The target area in each frame of the image is identified according to the target detection model to obtain the recognition result of the target to be detected.

5. The method according to claim 1, characterized in that The warning condition includes that there is no target to be detected in front of the vehicle; In response to the road condition in front of the vehicle triggering the warning condition, sending a warning reminder to the vehicle includes: In response to there being no target to be detected in front of the vehicle, sending a warning reminder to the vehicle.

6. The method according to claim 1, characterized in that The method further comprises: In response to the road condition in front of the vehicle triggering a warning condition, a warning reminder is sent to the vehicle behind the vehicle.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The real-time operation information of the vehicle, the real-time video stream of the vehicle and the real-time signal light information are obtained, and the real-time operation information of the vehicle, the real-time video stream of the vehicle and the real-time signal light information are aligned to obtain the aligned real-time operation information of the vehicle, the real-time video stream of the vehicle and the real-time signal light information.

8. The method according to any one of claims 1 to 6, characterized in that: Based on the real-time vehicle operation information and real-time traffic light information, determine whether the vehicle at the intersection has not started after the green light comes on, including: Determining whether the vehicle is parked according to the real-time operation information of the vehicle; When the vehicle is parked, determining whether the vehicle is located at an intersection based on a high-precision map and the real-time operation information of the vehicle; When the vehicle is at an intersection, determining the phase of the lane in which the vehicle is located according to the high-precision map and the real-time operation information of the vehicle; Real-time traffic light information is obtained, and according to the phase of the lane where the vehicle is located and the real-time traffic light information, it is determined whether the vehicle at the intersection has not started after the green light is on.

9. An early warning device, characterized in that: include: A determination module configured to determine whether a vehicle at an intersection has not started after the green light comes on, based on the real-time vehicle operation information and the real-time signal light information; an identification module configured to determine the road condition ahead of the vehicle according to the real-time video stream of the vehicle when the vehicle does not start after the green light comes on; The warning module is configured to send a warning reminder to the vehicle in response to the road condition in front of the vehicle triggering a warning condition.

10. An electronic device, comprising: at least one processor; as well as A memory storing a computer program executable on the processor, wherein the processor executes the steps of the method according to any one of claims 1 to 8 when executing the program.

Images