Vehicle accident detection method, device and equipment and storage medium

Abstract

The invention discloses a vehicle accident detection method, a vehicle accident detection device, vehicle accident detection equipment and a storage medium. Obtaining a vehicle video in a time period when the distance between the moving object and the vehicle is within a preset threshold value, a time point when the distance between the moving object and the vehicle is shortest, and the distance; detecting a relative position area of the moving object and the vehicle at the target time point; determining a vehicle accident risk level according to the vibration condition of the vehicle and the target distance; acquiring an image of a moving object, performing feature extraction on the image, determining an object type of the moving object, and identifying object features of the moving object according to the object type; and obtaining a current parking place of the vehicle, generating a corresponding vehicle accident report, and sending the vehicle accident report and the target video to a corresponding client. According to the invention, the event backtracking efficiency of the vehicle owner when the accident occurs can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle accident detection, and in particular to a vehicle accident detection method, device, equipment and storage medium. Background Art

[0002] In order to monitor scratches, collisions, and thefts after parking, many vehicles are equipped with a sentinel (accident detection) mode. After most sentinel modes are triggered, the owner can only understand the process of the incident by viewing the recorded video. The video recorded during the sentinel mode is as short as tens of seconds or as long as more than ten minutes. The owner cannot quickly understand the time, process, and consequences of the incident. In addition, the recorded video may not clearly show the specific license plate and facial information of the person who caused the accident, resulting in the inability to trace the accident. Summary of the invention

[0003] The present invention provides a vehicle accident detection method, device, equipment and storage medium to solve the technical problems that the existing vehicle accident detection mode cannot allow the car owner to quickly understand the time, process and consequences of the incident, and the recorded video may not clearly show the specific license plate and facial information of the person who caused the accident, resulting in the inability to trace the accident.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a vehicle accident detection method, comprising:

[0005] When a moving object is detected around the vehicle, the distance between the moving object and the vehicle is detected;

[0006] When the distance between the moving object and the vehicle is less than a preset threshold, a vehicle video of a time period in which the distance between the moving object and the vehicle is within the preset threshold is obtained, the vehicle video is used as a target video, and a time point when the distance between the moving object and the vehicle is the shortest is used as a target time point, and a distance when the distance between the moving object and the vehicle is the shortest is used as a target distance;

[0007] According to the target time point, the relative position area between the moving object and the vehicle at the target time point is detected, and the relative position area is used as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle;

[0008] Acquiring a vibration condition of the vehicle according to a preset vehicle vibration sensor, and determining a vehicle accident risk level according to the vibration condition and the target distance;

[0009] Acquire an image of the moving object, perform feature extraction on the image, determine the object type of the moving object according to the extracted image features, and identify the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face;

[0010] The current parking location of the vehicle is obtained, and a corresponding vehicle accident report is generated according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and the vehicle accident report and the target video are sent to the corresponding client.

[0011] As a preferred solution, the vibration condition of the vehicle includes: vibration occurs or no vibration occurs;

[0012] Determining the vehicle accident risk level according to the vibration condition and the target distance includes:

[0013] According to the vibration condition and the target distance, when the vehicle vibrates, determining that the vehicle accident risk level is a high risk level;

[0014] When the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, the vehicle accident risk level is determined to be a medium risk level;

[0015] When the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, the vehicle accident risk level is determined to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

[0016] As a preferred solution, extracting features from the image and then determining the object type of the moving object according to the extracted image features includes:

[0017] Extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches;

[0018] The extracted image features are compared with image features in a preset image feature library, and then the object type of the moving object is determined according to the comparison result; wherein the object type includes: a motor vehicle, a non-motor vehicle or a pedestrian.

[0019] As a preferred solution, the identifying the object feature of the moving object according to the object type includes:

[0020] When the object type is a motor vehicle or a non-motor vehicle, extracting texture, color and shape from the image, performing feature analysis on the extracted texture, color and shape, locating a license plate area where a vehicle license plate is located, performing character recognition on the license plate area, obtaining a license plate number of the moving object, and using the extracted license plate number as an object feature of the moving object;

[0021] When the object type is a pedestrian, facial information of the moving object is extracted from the image according to a preset face detection algorithm, and the extracted facial information is used as the object feature of the moving object.

[0022] Based on the above embodiment, another embodiment of the present invention provides a vehicle accident detection device, including: a vehicle real-time monitoring module, a vehicle video acquisition module, a vehicle area detection module, a vehicle accident risk level determination module, an object feature recognition module and a vehicle accident report generation module;

[0023] The vehicle real-time monitoring module is used to detect the distance between the moving object and the vehicle when a moving object is detected around the vehicle;

[0024] The vehicle video acquisition module is used to, when the distance between the moving object and the vehicle is less than a preset threshold, acquire the vehicle video of the time period when the distance between the moving object and the vehicle is within the preset threshold, use the vehicle video as the target video, and use the time point when the distance between the moving object and the vehicle is the shortest as the target time point, and use the distance when the distance between the moving object and the vehicle is the shortest as the target distance;

[0025] The vehicle area detection module is used to detect the relative position area between the moving object and the vehicle at the target time point according to the target time point, and use the relative position area as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle;

[0026] The vehicle accident risk level determination module is used to obtain the vibration condition of the vehicle according to a preset vehicle vibration sensor, and determine the vehicle accident risk level according to the vibration condition and the target distance;

[0027] The object feature recognition module is used to obtain an image of the moving object, perform feature extraction on the image, determine the object type of the moving object according to the extracted image features, and recognize the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face;

[0028] The vehicle accident report generation module is used to obtain the current parking location of the vehicle, generate a corresponding vehicle accident report according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and send the vehicle accident report and the target video to the corresponding client.

[0029] As a preferred solution, the vibration condition of the vehicle includes: vibration occurs or no vibration occurs;

[0030] Determining the vehicle accident risk level according to the vibration condition and the target distance includes:

[0031] According to the vibration condition and the target distance, when the vehicle vibrates, determining that the vehicle accident risk level is a high risk level;

[0032] When the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, the vehicle accident risk level is determined to be a medium risk level;

[0033] When the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, the vehicle accident risk level is determined to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

[0034] As a preferred solution, extracting features from the image and then determining the object type of the moving object according to the extracted image features includes:

[0035] Extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches;

[0036] The extracted image features are compared with image features in a preset image feature library, and then the object type of the moving object is determined according to the comparison result; wherein the object type includes: a motor vehicle, a non-motor vehicle or a pedestrian.

[0037] As a preferred solution, the identifying the object feature of the moving object according to the object type includes:

[0038] When the object type is a motor vehicle or a non-motor vehicle, extracting texture, color and shape from the image, performing feature analysis on the extracted texture, color and shape, locating a license plate area where a vehicle license plate is located, performing character recognition on the license plate area, obtaining a license plate number of the moving object, and using the extracted license plate number as an object feature of the moving object;

[0039] When the object type is a pedestrian, facial information of the moving object is extracted from the image according to a preset face detection algorithm, and the extracted facial information is used as the object feature of the moving object.

[0040] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the vehicle accident detection method described in the above invention embodiments is implemented.

[0041] Based on the above embodiment, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the vehicle accident detection method described in the above invention embodiment.

[0042] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0043] The present invention provides a vehicle accident detection method. When the distance between a moving object around a vehicle and the vehicle is less than a preset threshold, a vehicle video of a time period in which the distance between the moving object and the vehicle is within the preset threshold is obtained, the vehicle video is used as a target video, and the time point when the distance between the moving object and the vehicle is the shortest is used as a target time point, and the distance when the distance between the moving object and the vehicle is the shortest is used as a target distance; according to the target time point, the relative position area between the moving object and the vehicle at the target time point is detected, and the relative position is used as a target area; the vibration of the vehicle is obtained according to a preset vehicle vibration sensor, and the vehicle accident risk level is determined according to the vibration and the target distance; the image of the moving object is obtained, and features are extracted from the image, and then the object type of the moving object is determined according to the extracted image features, and the object features of the moving object are identified according to the object type. The current parking location of the vehicle is obtained, and a corresponding vehicle accident report is generated according to the parking location, target time point, target area, vehicle accident risk level, object type and object features, and the vehicle accident report and the target video are sent to the corresponding client.

[0044] Through the present invention, the car owner can quickly understand the location of the vehicle at the time of the accident, the time of the accident, the course of the accident and the risk level of the accident through the parking location, target time point, target area and vehicle accident risk level in the vehicle accident report, and can also hold the perpetrator or the vehicle involved in the accident accountable through the object type and object characteristics in the vehicle accident report, and can also view the vehicle video of the time period when the distance between the moving object and the vehicle is within a preset threshold through the target video, so as to understand the entire process of the accident, thereby greatly improving the event backtracking efficiency of the car owner when an accident occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a vehicle accident detection method provided by one embodiment of the present invention;

[0046] Figure 2 This is the interface diagram of the vehicle accident report;

[0047] Figure 3 It is a structural schematic diagram of a vehicle accident detection device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0050] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0053] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0054] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , is a flow chart of a vehicle accident detection method provided by an embodiment of the present invention, comprising the following specific steps:

[0057] S1. When a moving object is detected around the vehicle, the distance between the moving object and the vehicle is detected;

[0058] Specifically, in view of the problem that the existing technology cannot allow the car owner to quickly understand the time, process and consequences of the incident, and the recorded video may not clearly show the specific license plate and facial information of the person who caused the accident, resulting in the inability to trace the accident, the present invention proposes a sentinel mode accident report generation method based on image recognition, which integrates image recognition and target tracking technology in the domain controller. After the sentinel mode (i.e., accident detection mode) is turned on, the surround camera continues to work. When the domain controller detects a risk event, the image processing module is activated to track and identify key information such as license plates and faces. When the risk video is locked, the system generates a vehicle accident report. The report should include: the time, location, event level, damage location, suspected accident vehicle, person or object image, etc., which are saved together with the video to the vehicle computer for the convenience of the car owner to view. The specific process is as follows:

[0059] (1) After the sentry mode (i.e., accident detection mode) is turned on, the sensors (camera, ultrasonic wave, vibration sensor, etc.) arranged on the vehicle continuously detect the environment around the vehicle and cyclically record the images around the vehicle through the camera. When the on-board sensor detects the information of moving objects around the vehicle, the distance between the moving object and the vehicle is detected in real time to determine whether the sentry mode locking condition is met; wherein, the sentry mode locking condition is: the distance D between the sensor and the vehicle is detected to be less than a preset threshold value D1.

[0060] S2. When the distance between the moving object and the vehicle is less than a preset threshold, obtain a vehicle video of a time period in which the distance between the moving object and the vehicle is within the preset threshold, use the vehicle video as a target video, and use the time point when the distance between the moving object and the vehicle is the shortest as a target time point, and use the distance when the distance between the moving object and the vehicle is the shortest as a target distance;

[0061] (2) When the distance D between the moving object and the vehicle is less than a preset threshold value D1, the video of X minutes before and after the time period from when the sentinel mode latching condition is met to when the sentinel mode latching condition is not met (D>D1) is latched, and the vehicle video is stored as the target video in the corresponding storage module.

[0062] The time point at which the distance between the detected moving object and the vehicle is the shortest in the latching time period is recorded as the target time point T1, and the shortest distance is recorded as the target distance Dmin.

[0063] S3, according to the target time point, detecting the relative position area between the moving object and the vehicle at the target time point, and taking the relative position area as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle;

[0064] (3) The area around the vehicle is divided into six areas, namely, the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle. The area where the system determines the relative position of the moving object and the vehicle detected by the sensor at T1 is recorded as the target area F.

[0065] S4. Acquire the vibration condition of the vehicle according to a preset vehicle vibration sensor, and determine the vehicle accident risk level according to the vibration condition and the target distance;

[0066] Preferably, the vibration condition of the vehicle includes: vibration occurs or no vibration occurs; determining the vehicle accident risk level according to the vibration condition and the target distance includes: according to the vibration condition and the target distance, when the vehicle vibrates, determining the vehicle accident risk level to be a high risk level; when the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, determining the vehicle accident risk level to be a medium risk level; when the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, determining the vehicle accident risk level to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

[0067] (4) The system classifies the vehicle accident risk level according to the distance of the object (i.e., the target distance Dmin) and the vibration of the vehicle obtained by the vehicle vibration sensor. The vehicle accident risk level is recorded as C:

[0068] ① High-risk event: The vehicle vibration sensor senses that the vehicle is vibrating;

[0069] ② Medium risk event: the vehicle vibration sensor does not detect the vehicle vibration, and the minimum value Dmin≤D2 of the distance between the moving object and the vehicle detected by the sensor; wherein D2 is the preset medium risk threshold, i.e., the first distance threshold;

[0070] ③ Low-risk event: the vehicle vibration sensor does not detect any vibration of the vehicle, and the minimum distance between the sensor-detected object and the vehicle is D2<Dmin≤D1; wherein D1 is a preset low-risk threshold, i.e., the second distance threshold, D2<D1.

[0071] S5, acquiring an image of the moving object, performing feature extraction on the image, then determining the object type of the moving object according to the extracted image features, and identifying the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face;

[0072] Preferably, the extracting features from the image and then determining the object type of the moving object based on the extracted image features includes: extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches; comparing the extracted image features with image features in a preset image feature library, and then determining the object type of the moving object based on the comparison results; wherein the object types include: motor vehicles, non-motor vehicles, or pedestrians.

[0073] Preferably, the identifying the object features of the moving object according to the object type includes: when the object type is a motor vehicle or a non-motor vehicle, extracting the texture, color and shape in the image, performing feature analysis on the extracted texture, color and shape, locating the license plate area where the vehicle license plate is located, and performing character recognition on the license plate area to obtain the license plate number of the moving object, and using the extracted license plate number as the object feature of the moving object; when the object type is a pedestrian, according to a preset face detection algorithm, extracting the facial information of the moving object from the image, and using the extracted facial information as the object feature of the moving object.

[0074] (5) After the sentinel mode latching condition is met, the object type E of the moving object detected by the sensor (camera) is identified, and image features such as key pixels, edges or patches in the image of the moving object taken by the camera are extracted, and compared with the image features in the preset image feature library to determine the object type; wherein the object type is divided into: motor vehicle, non-motor vehicle, pedestrian or others.

[0075] The object feature Y of the object type E detected by the sensor is identified: ① When detected as a motor vehicle or non-motor vehicle, feature analysis is performed through texture, color and shape to locate the license plate area, and then the segmented characters are recognized through optical character recognition technology and converted into numbers and letters to complete the vehicle license plate number extraction; ② When detected as a pedestrian, a face detection algorithm (Haar feature-based cascade classifier, neural network-based method, etc.) is used to separate the face from the background; others are not processed.

[0076] S6. Obtain the current parking location of the vehicle, generate a corresponding vehicle accident report according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and send the vehicle accident report and the target video to the corresponding client.

[0077] (6) Obtain the GNSS positioning information of the vehicle when it is parked, and record the parking location as L.

[0078] Please refer to Figure 2, which is the interface diagram of the vehicle accident report. After the video is locked, the vehicle accident report is automatically generated, showing the target time (T1) of the risk event, the parking location (L), the vehicle accident risk level (C), the vehicle area (F), the suspected vehicle or person (object type E), the person or object image (object feature Y), etc., and then the vehicle accident report and the target video are sent to the corresponding client.

[0079] Embodiment 2

[0080] Please refer to Figure 3 , is a schematic diagram of the structure of a vehicle accident detection device provided by an embodiment of the present invention, the device comprising: a vehicle real-time monitoring module, a vehicle video acquisition module, a vehicle area detection module, a vehicle accident risk level determination module, an object feature recognition module and a vehicle accident report generation module;

[0081] The vehicle real-time monitoring module is used to detect the distance between the moving object and the vehicle when a moving object is detected around the vehicle;

[0082] The vehicle video acquisition module is used to, when the distance between the moving object and the vehicle is less than a preset threshold, acquire the vehicle video of the time period when the distance between the moving object and the vehicle is within the preset threshold, use the vehicle video as the target video, and use the time point when the distance between the moving object and the vehicle is the shortest as the target time point, and use the distance when the distance between the moving object and the vehicle is the shortest as the target distance;

[0083] The vehicle area detection module is used to detect the relative position area between the moving object and the vehicle at the target time point according to the target time point, and use the relative position area as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle;

[0084] The vehicle accident risk level determination module is used to obtain the vibration condition of the vehicle according to a preset vehicle vibration sensor, and determine the vehicle accident risk level according to the vibration condition and the target distance;

[0085] The object feature recognition module is used to obtain an image of the moving object, perform feature extraction on the image, determine the object type of the moving object according to the extracted image features, and recognize the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face;

[0086] The vehicle accident report generation module is used to obtain the current parking location of the vehicle, generate a corresponding vehicle accident report according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and send the vehicle accident report and the target video to the corresponding client.

[0087] Preferably, the vibration condition of the vehicle includes: vibration occurs or no vibration occurs; determining the vehicle accident risk level according to the vibration condition and the target distance includes: according to the vibration condition and the target distance, when the vehicle vibrates, determining the vehicle accident risk level to be a high risk level; when the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, determining the vehicle accident risk level to be a medium risk level; when the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, determining the vehicle accident risk level to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

[0088] Preferably, the extracting features from the image and then determining the object type of the moving object based on the extracted image features includes: extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches; comparing the extracted image features with image features in a preset image feature library, and then determining the object type of the moving object based on the comparison results; wherein the object types include: motor vehicles, non-motor vehicles, or pedestrians.

[0089] Preferably, the identifying the object features of the moving object according to the object type includes: when the object type is a motor vehicle or a non-motor vehicle, extracting the texture, color and shape in the image, performing feature analysis on the extracted texture, color and shape, locating the license plate area where the vehicle license plate is located, and performing character recognition on the license plate area to obtain the license plate number of the moving object, and using the extracted license plate number as the object feature of the moving object; when the object type is a pedestrian, according to a preset face detection algorithm, extracting the facial information of the moving object from the image, and using the extracted facial information as the object feature of the moving object.

[0090] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0091] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0092] Embodiment 3

[0093] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the vehicle accident detection method described in the above-mentioned embodiment of the invention when executing the computer program.

[0094] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0095] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0096] Embodiment 4

[0097] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the vehicle accident detection method described in the above-mentioned embodiment of the invention.

[0098] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0099] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0100] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A vehicle accident detection method, characterized in that: include: When a moving object is detected around the vehicle, the distance between the moving object and the vehicle is detected; When the distance between the moving object and the vehicle is less than a preset threshold, a vehicle video of a time period in which the distance between the moving object and the vehicle is within the preset threshold is obtained, the vehicle video is used as a target video, and a time point when the distance between the moving object and the vehicle is the shortest is used as a target time point, and a distance when the distance between the moving object and the vehicle is the shortest is used as a target distance; According to the target time point, the relative position area between the moving object and the vehicle at the target time point is detected, and the relative position area is used as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle; Acquiring a vibration condition of the vehicle according to a preset vehicle vibration sensor, and determining a vehicle accident risk level according to the vibration condition and the target distance; Acquire an image of the moving object, perform feature extraction on the image, determine the object type of the moving object according to the extracted image features, and identify the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face; The current parking location of the vehicle is obtained, and a corresponding vehicle accident report is generated according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and the vehicle accident report and the target video are sent to the corresponding client.

2. The vehicle accident detection method according to claim 1, characterized in that: The vibration condition of the vehicle includes: vibration occurs or no vibration occurs; Determining the vehicle accident risk level according to the vibration condition and the target distance includes: According to the vibration condition and the target distance, when the vehicle vibrates, determining that the vehicle accident risk level is a high risk level; When the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, the vehicle accident risk level is determined to be a medium risk level; When the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, the vehicle accident risk level is determined to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

3. The vehicle accident detection method according to claim 1, characterized in that: The extracting features from the image and then determining the object type of the moving object according to the extracted image features includes: Extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches; The extracted image features are compared with image features in a preset image feature library, and then the object type of the moving object is determined according to the comparison result; wherein the object type includes: a motor vehicle, a non-motor vehicle or a pedestrian.

4. The vehicle accident detection method according to claim 3, characterized in that: The identifying the object feature of the moving object according to the object type includes: When the object type is a motor vehicle or a non-motor vehicle, extracting texture, color and shape from the image, performing feature analysis on the extracted texture, color and shape, locating a license plate area where a vehicle license plate is located, performing character recognition on the license plate area, obtaining a license plate number of the moving object, and using the extracted license plate number as an object feature of the moving object; When the object type is a pedestrian, facial information of the moving object is extracted from the image according to a preset face detection algorithm, and the extracted facial information is used as the object feature of the moving object.

5. A vehicle accident detection device, characterized in that: include: Vehicle real-time monitoring module, vehicle video acquisition module, vehicle area detection module, vehicle accident risk level determination module, object feature recognition module and vehicle accident report generation module; The vehicle real-time monitoring module is used to detect the distance between the moving object and the vehicle when a moving object is detected around the vehicle; The vehicle video acquisition module is used to, when the distance between the moving object and the vehicle is less than a preset threshold, acquire the vehicle video of the time period when the distance between the moving object and the vehicle is within the preset threshold, use the vehicle video as the target video, and use the time point when the distance between the moving object and the vehicle is the shortest as the target time point, and use the distance when the distance between the moving object and the vehicle is the shortest as the target distance; The vehicle area detection module is used to detect the relative position area between the moving object and the vehicle at the target time point according to the target time point, and use the relative position area as the target area; wherein the relative position area includes: the left front of the vehicle, the right front of the vehicle, the left side of the vehicle, the right side of the vehicle, the left rear of the vehicle, and the right rear of the vehicle; The vehicle accident risk level determination module is used to obtain the vibration condition of the vehicle according to a preset vehicle vibration sensor, and determine the vehicle accident risk level according to the vibration condition and the target distance; The object feature recognition module is used to obtain an image of the moving object, perform feature extraction on the image, determine the object type of the moving object according to the extracted image features, and recognize the object features of the moving object according to the object type; wherein the object features include: a license plate number or a human face; The vehicle accident report generation module is used to obtain the current parking location of the vehicle, generate a corresponding vehicle accident report according to the parking location, target time point, target area, vehicle accident risk level, object type and object characteristics, and send the vehicle accident report and the target video to the corresponding client.

6. The vehicle accident detection device according to claim 5, characterized in that: The vibration condition of the vehicle includes: vibration occurs or no vibration occurs; Determining the vehicle accident risk level according to the vibration condition and the target distance includes: According to the vibration condition and the target distance, when the vehicle vibrates, determining that the vehicle accident risk level is a high risk level; When the vehicle does not vibrate and the target distance does not exceed a preset first distance threshold, the vehicle accident risk level is determined to be a medium risk level; When the vehicle does not vibrate and the target distance is greater than the first distance threshold and does not exceed a preset second distance threshold, the vehicle accident risk level is determined to be a low risk level; wherein the first distance threshold is less than the second distance threshold.

7. The vehicle accident detection device according to claim 5, characterized in that: The extracting features from the image and then determining the object type of the moving object according to the extracted image features includes: Extracting image features from the image; wherein the image features include: key pixels, image edges, and image patches; The extracted image features are compared with image features in a preset image feature library, and then the object type of the moving object is determined according to the comparison result; wherein the object type includes: a motor vehicle, a non-motor vehicle or a pedestrian.

8. The vehicle accident detection device according to claim 7, characterized in that: The identifying the object feature of the moving object according to the object type includes: When the object type is a motor vehicle or a non-motor vehicle, extracting texture, color and shape from the image, performing feature analysis on the extracted texture, color and shape, locating a license plate area where a vehicle license plate is located, performing character recognition on the license plate area, obtaining a license plate number of the moving object, and using the extracted license plate number as an object feature of the moving object; When the object type is a pedestrian, facial information of the moving object is extracted from the image according to a preset face detection algorithm, and the extracted facial information is used as the object feature of the moving object.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the vehicle accident detection method according to any one of claims 1 to 4 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the vehicle accident detection method according to any one of claims 1 to 4.

Images