Automobile data recorder video processing method and device, electronic equipment and target vehicle

Abstract

The invention relates to the technical field of automobiles, in particular to an automobile data recorder video processing method and device, electronic equipment and a target vehicle. The method comprises a video acquisition module, a target identification module, a scene identification module, a terminal control module, a recording module, a playing module and the like. Wherein the sensor comprises a foresight camera and an all-round camera which are arranged on a front windshield. Obtaining target driving data corresponding to the target vehicle; analyzing the target driving data, and determining whether the target driving data meets a preset triggering condition or not; if the target driving data meets the preset triggering condition, determining a triggering moment meeting the preset triggering condition; and based on the triggering moment, extracting the target video clip from the automobile data recorder, storing the target video clip, and generating the video clip abstract, thereby solving the problem that the backtracking check of the key event is not efficient and convenient enough. And safer and more convenient driving recording experience is provided for a driver.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a driving recorder video processing method, device, electronic equipment and a target vehicle. Background Art

[0002] Traditional driving recorders usually use a loop recording method to record the entire process of the vehicle's driving. This method can ensure that the vehicle can review the event when a traffic accident or related incident occurs, but the review process is relatively cumbersome. In order to solve this problem, an intelligent driving recorder system is introduced, which combines event-triggered recording, intelligent storage management, remote real-time uploading and driving behavior monitoring. Through the event-triggered recording mechanism, the system can automatically start the recording function when the vehicle encounters an emergency and retain key video clips; the intelligent storage management technology optimizes storage according to the importance and time of the video to save storage space; the remote real-time uploading function uploads the video to the cloud storage in real time, which is convenient for remote viewing and management, and accurately restores the accident process; driving behavior monitoring combines AI technology to monitor driving behavior and improve driving safety. This intelligent driving recorder system provides drivers with a safer and more convenient driving record experience, making event review easier and more efficient.

[0003] Therefore, how to extract and save important video clips from the driving recorder has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present invention provides a driving recorder video processing method, device, electronic equipment and target vehicle to solve the problem of how to record and save important video clips in the driving recorder.

[0005] In a first aspect, the present invention provides a driving recorder video processing method, the method comprising:

[0006] Obtain target driving data corresponding to the target vehicle;

[0007] Analyze the target driving data to determine whether the target driving data meets the preset trigger conditions;

[0008] If the target driving data meets the preset trigger condition, then determining the trigger time when the preset trigger condition is met;

[0009] Based on the triggering moment, the target video segment is extracted from the driving recorder and saved.

[0010] The driving recorder video processing method provided in the embodiment of the present application obtains the target driving data corresponding to the target vehicle, analyzes the target driving data, determines whether the target driving data meets the preset trigger condition, and ensures the accuracy of the result of determining whether the target driving data meets the preset trigger condition. If the target driving data meets the preset trigger condition, the triggering time that meets the preset trigger condition is determined, and based on the triggering time, the target video segment is extracted from the driving recorder, and the target video segment is saved, ensuring the accuracy of the extracted target video segment.

[0011] In an optional implementation, the target driving data includes the self-vehicle driving data corresponding to the target vehicle, and analyzing the target driving data to determine whether the target driving data meets a preset trigger condition includes:

[0012] Analyze the self-vehicle driving data to determine whether the target vehicle has emergency driving behavior; emergency driving behavior includes sudden braking driving behavior, sudden deceleration driving behavior, sudden acceleration driving behavior, and sharp turning driving behavior;

[0013] If there is emergency driving behavior, it is determined that the target driving data meets the preset trigger conditions;

[0014] If there is no emergency driving behavior, it is determined that the target driving data does not meet the preset trigger condition.

[0015] The dashcam video processing method provided in the embodiment of the present application analyzes the driving data of the vehicle to determine whether the target vehicle has emergency driving behavior; emergency driving behavior includes sudden braking driving behavior, sudden deceleration driving behavior, sudden acceleration driving behavior, and sharp turning driving behavior; if there is emergency driving behavior, it is determined that the target driving data meets the preset trigger conditions, thereby ensuring the accuracy of the result of whether the determined target driving data meets the preset trigger conditions. If there is no emergency driving behavior, it is determined that the target driving data does not meet the preset trigger conditions, thereby ensuring the accuracy of the result of whether the determined target driving data does not meet the preset trigger conditions. Furthermore, when the target vehicle has emergency driving behavior, the target video clip corresponding to the emergency driving behavior can be extracted and saved.

[0016] In an optional implementation, the target driving data includes target image data corresponding to multiple sensors of the target vehicle, and analyzing the target driving data to determine whether the target driving data meets a preset trigger condition includes:

[0017] Performing target detection on each target image data, determining other target bodies from the target image data, and determining position information and category information corresponding to the other target bodies;

[0018] According to the continuous position information corresponding to other target bodies, the speed and movement direction information corresponding to other target bodies are determined;

[0019] According to the speed, direction and category information of other target objects, it is determined whether the target driving data meets the preset trigger conditions.

[0020] The dashcam video processing method provided in the embodiment of the present application obtains continuous target image data corresponding to the target vehicle; performs target detection on each target image data, determines other target bodies from the target image data, and determines the position information and category information corresponding to the other target bodies. According to the continuous position information corresponding to the other target bodies, the speed and movement direction information corresponding to the other target bodies are determined, and according to the speed, direction information and category information of the other target bodies, it is determined whether the target driving data meets the preset trigger condition, thereby ensuring the accuracy of the result of determining whether the target driving data meets the preset trigger condition.

[0021] In an optional implementation, determining whether the target driving data meets a preset trigger condition based on the speed, direction information, and category information of other target objects includes:

[0022] Determine the acceleration of other target objects according to the velocity information of other target objects;

[0023] According to the category information corresponding to the target object, the acceleration thresholds corresponding to other target objects are determined;

[0024] If the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition.

[0025] The dash cam video processing method provided in the embodiment of the present application determines the acceleration of other target objects based on the speed information of other target objects; determines the acceleration threshold corresponding to other target objects based on the category information corresponding to the target objects; if the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition, thereby ensuring the accuracy of the determined target driving data meeting the preset trigger condition.

[0026] In an optional implementation, determining whether the target driving data meets a preset trigger condition based on the speed, direction information, and category information of other target objects includes:

[0027] According to the speed and direction information of other targets, determine the changing trend of the movement direction of other targets;

[0028] According to the category information corresponding to other targets, the motion direction change threshold corresponding to other targets is determined;

[0029] If the change in motion direction is greater than the motion direction change threshold, it is determined that the target driving data meets the preset trigger condition.

[0030] The dash cam video processing method provided in the embodiment of the present application determines the change in the motion direction of other target objects based on the speed and direction information of other target objects, and determines the motion direction change threshold corresponding to other target objects based on the category information corresponding to other target objects. If the motion direction change is greater than the motion direction change threshold, it is determined that the target driving data meets the preset trigger condition, and then the target video clip in which the motion direction of other target objects suddenly changes can be saved.

[0031] In an optional implementation, the target driving data includes target image data corresponding to the target vehicle, and analyzing the target driving data to determine whether the target driving data meets a preset trigger condition includes:

[0032] Identify the target image data and determine the driving environment corresponding to the target vehicle; the driving environment includes road conditions, weather conditions, congestion conditions, and accident conditions;

[0033] If the driving environment meets the preset environmental conditions, determining that the target driving data meets the preset trigger conditions;

[0034] If the driving environment does not meet the preset environmental conditions, it is determined that the target driving data does not meet the preset trigger conditions.

[0035] The dash cam video processing method provided in the embodiment of the present application identifies the target image data and determines the driving environment corresponding to the target vehicle; the driving environment includes road conditions, weather conditions, congestion conditions and accident conditions; if the driving environment meets the preset environmental conditions, it is determined that the target driving data meets the preset trigger conditions; if the driving environment does not meet the preset environmental conditions, it is determined that the target driving data does not meet the preset trigger conditions, and the target video clip corresponding to the complex driving environment can be saved.

[0036] In an optional implementation, based on the triggering moment, extracting a target video segment from the driving recorder and saving the target video segment include:

[0037] Based on the triggering moment, determining a first preset time length before the triggering moment as the start time of the target video segment, and determining a second preset time length after the triggering moment as the end time of the target video segment;

[0038] Extract the target video clip from the driving recorder according to the start time and the end time;

[0039] Determine at least one of weather information, time information, road information, location information, and event information corresponding to the target video clip;

[0040] generating summary information based on at least one of weather information, time information, road information, location information, and event information;

[0041] The target video clip and summary information are stored correspondingly.

[0042] The dash cam video processing method provided in the embodiment of the present application determines, based on the trigger moment, the first preset time length before the trigger moment as the start moment of the target video segment, and determines the second preset time length after the trigger moment as the end moment of the target video segment, thereby ensuring the accuracy of the determined start moment and end moment of the target video segment. According to the start moment and the end moment, the target video segment is extracted from the dash cam. At least one of the weather information, time information, road information, location information, and event information corresponding to the target video segment is determined; based on at least one of the weather information, time information, road information, location information, and event information, summary information is generated, so that it can be conveniently used to determine the content of the target video segment based on the summary information. The target video segment and the summary information are stored correspondingly to facilitate searching for the target video segment. The user does not need to search for the target video segment data from all the video data.

[0043] In a second aspect, the present invention provides a driving recorder video processing device, comprising:

[0044] An acquisition module, used to acquire target driving data corresponding to a target vehicle;

[0045] A first determination module is used to analyze the target driving data to determine whether the target driving data meets a preset trigger condition;

[0046] A second determination module is used to determine a triggering time that satisfies a preset triggering condition if the target driving data satisfies a preset triggering condition;

[0047] The extraction module is used to extract the target video segment from the driving recorder based on the triggering moment and save the target video segment.

[0048] The dashcam video processing device provided in the embodiment of the present application obtains the target driving data corresponding to the target vehicle, analyzes the target driving data, determines whether the target driving data satisfies the preset trigger condition, and ensures the accuracy of the result of determining whether the target driving data satisfies the preset trigger condition. If the target driving data satisfies the preset trigger condition, the trigger moment that satisfies the preset trigger condition is determined, and based on the trigger moment, the target video clip is extracted from the dashcam and the target video clip is saved, ensuring the accuracy of the extracted target video clip, realizing the saving of the target video clip, and solving the problem that the target video clip misses the key moment and is difficult to review.

[0049] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the dash cam video processing method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0050] In a fourth aspect, the present invention provides a target vehicle, including an electronic device, a vehicle body and a driving recorder, wherein the electronic device and the driving recorder are communicatively connected, and the electronic device is used to execute the driving recorder video processing method of the first aspect or any corresponding embodiment thereof.

[0051] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the dash cam video processing method of the first aspect or any corresponding embodiment thereof.

[0052] In a sixth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the dash cam video processing method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a first driving recorder video processing method according to an embodiment of the present invention;

[0055] Figure 2 is a flow chart of a second driving recorder video processing method according to an embodiment of the present invention;

[0056] Figure 3 is a schematic diagram of a process of generating a target video segment and summary information corresponding to the target video segment according to an embodiment of the present invention;

[0057] Figure 4 is a schematic diagram of a target video segment to be saved according to an embodiment of the present invention;

[0058] Figure 5 is a schematic diagram of playing a target video segment according to an embodiment of the present invention;

[0059] Figure 6is a flow chart of a third driving recorder video processing method according to an embodiment of the present invention;

[0060] Figure 7 is a schematic flow chart of a fourth driving recorder video processing method according to an embodiment of the present invention;

[0061] Figure 8 is a flowchart of a fifth driving recorder video processing method according to an embodiment of the present invention;

[0062] Fig. 9 is a structural block diagram of a driving recorder video processing device according to an embodiment of the present invention;

[0063] Fig.10 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0065] Traditional driving recorders usually use a loop recording method to record the entire driving process of the vehicle. This method can ensure that the vehicle can review the event when a traffic accident or related incident occurs, but the review process is relatively cumbersome.

[0066] Therefore, how to save the important videos in the driving recorder has become an urgent problem to be solved.

[0067] Based on this, the embodiment of the present application provides a driving recorder video processing method, which obtains the target driving data corresponding to the target vehicle, analyzes the target driving data, determines whether the target driving data meets the preset trigger condition, and ensures the accuracy of the result of whether the target driving data meets the preset trigger condition. If the target driving data meets the preset trigger condition, the triggering moment that meets the preset trigger condition is determined, and based on the triggering moment, the target video clip is extracted from the driving recorder, and the target video clip is saved, so that the key target video clip is saved, and the problem of inconvenient retrospective viewing of key event points is solved.

[0068] It should be noted that the execution subject of the method for processing dashcam video provided in the embodiment of the present application may be a dashcam video processing device, and the dashcam video processing device may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device may be a control device in the dashcam, or may be an electronic device in a target vehicle that is independent of the dashcam but is communicatively connected to the dashcam. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0069] According to an embodiment of the present invention, an embodiment of a dash cam video processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0070] In this embodiment, a driving recorder video processing method is provided, which can be used in the above-mentioned electronic device. Figure 1 is a flow chart of a method for processing a driving recorder video according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0071] Step S101, obtaining target driving data corresponding to a target vehicle.

[0072] Specifically, the electronic device may detect target driving data corresponding to the target vehicle based on a sensor installed in the target vehicle.

[0073] Among them, the sensors installed in the target vehicle include but are not limited to GPS, lidar sensors, millimeter-wave radar sensors, cameras, etc. The embodiments of the present application do not specifically limit the sensors installed in the target vehicle.

[0074] Among them, the target driving data may include at least one of the self-vehicle driving data, the motion data of other target objects that can be collected by the target vehicle, and the surrounding environment data. Among them, the self-vehicle driving data may include the self-vehicle speed, vehicle acceleration, vehicle heading angle, vehicle foot brake, vehicle hand brake, target throttle and other data; the motion data of other target objects may include the position, speed, direction of other target objects at each moment, and the calculated acceleration data of other target objects, as well as the driving trajectory statistical data of other target objects, etc.; the surrounding environment data may include road conditions, weather conditions, congestion conditions, accident conditions and other data.

[0075] The embodiment of the present application does not specifically limit the target driving data.

[0076] Step S102: Analyze the target driving data to determine whether the target driving data meets a preset trigger condition.

[0077] Specifically, the electronic device may input the driving image data in the target driving data into a preset trigger condition recognition model, and the preset trigger condition recognition model analyzes the target driving data to determine whether the target driving data satisfies the preset trigger condition.

[0078] The preset trigger condition related recognition model may be any one or more of BEV, YOLO series, FasterR-CNN, EfficientDet, VILT model, etc. The embodiment of the present application does not limit the preset trigger condition recognition model.

[0079] Step S103: if the target driving data meets the preset trigger condition, then determine the trigger time that meets the preset trigger condition.

[0080] Specifically, if the target driving data meets the preset trigger condition, the electronic device determines the moment when the preset trigger condition is met as the trigger moment.

[0081] Step S104: extracting a target video segment from the driving recorder based on the triggering moment, and saving the target video segment.

[0082] Specifically, the electronic device can determine the start time and end time corresponding to the target video segment based on the event triggering time, thereby determining the target video segment, extracting the target video segment from the driving recorder, and saving the target video segment.

[0083] The dashcam video processing method provided in the embodiment of the present application obtains the target driving data corresponding to the target vehicle, analyzes the target driving data, determines whether the target driving data meets the preset trigger condition, and ensures the accuracy of the result of determining whether the target driving data meets the preset trigger condition. If the target driving data meets the preset trigger condition, the triggering moment that meets the preset trigger condition is determined, and based on the triggering moment, the target video clip is extracted from the dashcam and the target video clip is saved, thereby realizing the saving of key target video clips and solving the problem of inconvenient retrospective viewing of key event points.

[0084] In this embodiment, a driving recorder video processing method is provided, which can be used in the above-mentioned electronic device. Figure 2 is a flow chart of a method for processing a driving recorder video according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0085] Step S201, obtaining target driving data corresponding to the target vehicle.

[0086] For details about this step, please refer to the above description of step S101, which will not be elaborated here.

[0087] Step S202: Analyze the target driving data to determine whether the target driving data meets a preset trigger condition.

[0088] Specifically, the target driving data includes the self-vehicle driving data corresponding to the target vehicle. The above step S202 may include the following steps:

[0089] Step S2021, analyzing the self-vehicle driving data to determine whether the target vehicle has emergency driving behavior.

[0090] Among them, emergency driving behaviors include sudden braking, sudden deceleration, sudden acceleration, and sudden turning.

[0091] Among them, the self-vehicle driving data may include target vehicle speed, target vehicle acceleration, target vehicle steering angle, target vehicle foot brake, target vehicle hand brake, target vehicle throttle and other data.

[0092] Specifically, the electronic device can analyze the self-vehicle driving data to determine whether the target vehicle has emergency driving behavior.

[0093] (1) For rapid braking driving behavior: Optionally, the electronic device can judge by the rate of change of the target vehicle speed. The rate of change of the target vehicle speed at time t is defined as v'(t). If v'(t) exceeds a set acceleration threshold, it can be considered that the target vehicle has experienced rapid braking driving behavior.

[0094] If |v'(t)|>Threshold_{braking}, it is judged as an emergency braking behavior.

[0095] Optionally, the electronic device can also judge by detecting the hand brake signal and / or foot brake signal of the target vehicle. When the hand brake and / or foot brake signal of the target vehicle is triggered, it can be considered that the target vehicle has a situation of emergency braking driving behavior.

[0096] Optionally, when the target vehicle triggers the automatic emergency braking (AEB) function, it can be considered that the vehicle has performed an emergency braking driving behavior.

[0097] (2) Rapid Deceleration: Optionally, the electronic device can also judge by the rate of change of the target vehicle speed. The deceleration of the target vehicle speed at time t is defined as v'(t). If v'(t) exceeds a set deceleration threshold, it can be considered that the target vehicle has experienced rapid deceleration.

[0098] If |v'(t)|>Threshold_{deceleration}, it is judged as a sudden deceleration driving behavior.

[0099] (3) Rapid Deceleration: Optionally, the electronic device can also judge by the rate of change of the target vehicle speed. The acceleration of the target vehicle speed at time t is defined as a(t) = v'(t). If a(t) exceeds a set acceleration threshold, it can be considered that the target vehicle has experienced rapid acceleration.

[0100] If a(t)>Threshold_{acceleration}, it is judged as a sudden acceleration driving behavior.

[0101] Optionally, the electronic device can also make a judgment by detecting a throttle signal of the target vehicle. When the throttle signal of the target vehicle is greater than a preset throttle threshold, it can be considered that the target vehicle has a situation of sudden acceleration driving behavior.

[0102] (4) Sharp Turn: The electronic device can judge by monitoring the angular acceleration or steering angle change rate of the target vehicle. The steering angular velocity of the vehicle at time t is defined as omega(t). If omega(t) exceeds a set steering angle threshold, it can be considered that the target vehicle has made a sharp turn.

[0103] Angular acceleration: When a vehicle turns, it will generate angular acceleration, which is the rotational acceleration of the vehicle around the vertical axis. By monitoring the angular acceleration omega1(t) of the vehicle, it can be determined whether the vehicle has made a sharp turn. If the angular acceleration exceeds a certain threshold, it can be considered that the vehicle has made a sharp turn.

[0104] If |omega1(t)|>Threshold1_{turning}, it is judged as a sharp turning driving behavior.

[0105] Optionally, steering angle change rate: Another method is to monitor the rate of change of the vehicle's steering angle. When the vehicle makes a sharp turn, the steering angle changes dramatically. By monitoring the rate of change of the steering angle omega2(t), it can be determined whether the vehicle is making a sharp turn. If the rate of change of the steering angle exceeds a certain threshold, it can be considered that the vehicle is making a sharp turn.

[0106] If |omega2(t)|>Threshold2_{turning}, it is judged as a sharp turning driving behavior.

[0107] Step S2022: If there is emergency driving behavior, determine whether the target driving data meets the preset trigger condition.

[0108] Specifically, if there is an emergency driving behavior, the electronic device determines that the target driving data meets a preset trigger condition.

[0109] Step S2023: If there is no emergency driving behavior, it is determined that the target driving data does not meet the preset trigger condition.

[0110] Specifically, if there is no emergency driving behavior, the electronic device determines that the target driving data does not meet the preset trigger condition.

[0111] Step S203: if the target driving data meets the preset trigger condition, determine the trigger time that meets the preset trigger condition.

[0112] For details about this step, please refer to the above description of step S103, which will not be elaborated here.

[0113] Step S204: extracting a target video segment from the driving recorder based on the triggering moment, and saving the target video segment.

[0114] Specifically, the above step S204 may include the following steps:

[0115] Step S2041, based on the triggering moment, determining a first preset time length before the triggering moment as the start time of the target video segment, and determining a second preset time length after the triggering moment as the end time of the target video segment.

[0116] Specifically, the electronic device can receive the first preset time length and the second preset time length set by the user; the electronic device can also receive the first preset time length and the second preset time length sent by other devices. The electronic device can also set different first preset time lengths and second preset time lengths according to different trigger conditions met.

[0117] Exemplarily, if there is emergency driving behavior, it is determined that the target driving data meets the preset trigger conditions, and the first duration can be set according to the start time of the emergency driving behavior, and the second duration can be set according to the end time of the emergency driving behavior of the target vehicle.

[0118] If the target driving data satisfies the preset trigger condition based on the trajectory information and category information corresponding to other target objects, the first duration can be determined based on the time when the other target objects are detected, and the second duration can be determined based on the time when the other target objects cannot be detected.

[0119] If the driving environment meets the preset environmental conditions and it is determined that the target driving data meets the preset trigger conditions, the first preset duration can be set according to the start time when the driving environment meets the preset environmental conditions, and the first preset duration can be set according to the end time when the driving environment meets the preset environmental conditions.

[0120] Step S2042: extract the target video clip from the driving recorder according to the start time and the end time.

[0121] Specifically, the electronic device can determine the target video segment from the driving recorder according to the start time and the end time, and extract the target video segment.

[0122] Step S2043, determining at least one of weather information, time information, road information, location information and event information corresponding to the target video clip.

[0123] Specifically, the electronic device can decode the target video clip, obtain a video frame sequence, and then perform image preprocessing, such as denoising, contrast enhancement, etc., to improve the accuracy of subsequent processing. The electronic device can use image recognition technology to analyze features such as sky, clouds, precipitation, etc. in the video frame to determine weather conditions, such as sunny, cloudy, rainy, etc.

[0124] Then, the electronic device can analyze the metadata of the target video clip, such as shooting time, frame rate, etc., to obtain time information. Optionally, the electronic device can also determine the time through elements such as a clock and a calendar in the video.

[0125] Optionally, the electronic device may also use a deep learning model, such as a semantic segmentation network, to achieve automatic recognition of road information.

[0126] If the target video clip contains geographic location information, such as GPS data, the electronic device can directly extract the geographic location information corresponding to the target video clip. If the target video clip does not contain geographic location information, the electronic device can infer the shooting location of the video through features such as landmarks and buildings in the video combined with map data.

[0127] Electronic devices can also use object detection technology to detect and classify objects such as vehicles, pedestrians, traffic lights, etc. in the video frames of the target video clips. The behavior and interaction of the objects can be analyzed to determine whether a specific event has occurred, such as a traffic accident, traffic congestion, etc.

[0128] Optionally, the electronic device can use scene recognition visual large models (ViLT, DriveVLM) to achieve automatic detection of event information.

[0129] Step S2044, generating summary information based on at least one of weather information, time information, road information, location information and event information.

[0130] Specifically, the electronic device generates summary information based on at least one of weather information, time information, road information, location information, and event information.

[0131] Step S2045: store the target video clip and summary information in correspondence.

[0132] Specifically, the electronic device can store the target video clip and summary information in correspondence, and mark them as timestamps of when the event occurred, so as to facilitate subsequent viewing and management by the user.

[0133] For example, Figure 3 , which is a schematic diagram of a process of generating a target video segment and summary information corresponding to the target video segment.

[0134] For example, Figure 4 The following is a schematic diagram of the target video clip being saved. Figure 5 , which is a schematic diagram of playing a target video clip.

[0135] The dashcam video processing method provided in the embodiment of the present application analyzes the driving data of the vehicle to determine whether the target vehicle has emergency driving behavior; emergency driving behavior includes sudden braking driving behavior, sudden deceleration driving behavior, sudden acceleration driving behavior, and sharp turning driving behavior; if there is emergency driving behavior, it is determined that the target driving data meets the preset trigger conditions, thereby ensuring the accuracy of the result of whether the determined target driving data meets the preset trigger conditions. If there is no emergency driving behavior, it is determined that the target driving data does not meet the preset trigger conditions, thereby ensuring the accuracy of the result of whether the determined target driving data does not meet the preset trigger conditions. Furthermore, when the target vehicle has emergency driving behavior, the target video clip corresponding to the emergency driving behavior can be saved, thereby avoiding problems such as untimely saving of the target video clip and missing of key moments.

[0136] In addition, based on the trigger moment, the first preset duration before the trigger moment is determined as the start moment of the target video segment, and the second preset duration after the trigger moment is determined as the end moment of the target video segment, thereby ensuring the accuracy of the start moment and the end moment of the determined target video segment. According to the start moment and the end moment, the target video segment is extracted from the driving recorder, thereby ensuring the accuracy of the extracted target video segment. At least one of the weather information, time information, road information, location information and event information corresponding to the target video segment is determined; based on at least one of the weather information, time information, road information, location information and event information, summary information is generated, thereby ensuring the accuracy of the generated summary information, so that it can be conveniently used to determine the content of the target video segment according to the summary information. The target video segment and the summary information are stored correspondingly, so as to facilitate the search of the target video segment. The user does not need to search for the target video segment data from all the video data.

[0137] In this embodiment, a driving recorder video processing method is provided, which can be used in the above-mentioned electronic device. Figure 6 is a flow chart of a method for processing a driving recorder video according to an embodiment of the present invention. Figure 6 As shown, the process includes the following steps:

[0138] Step S301, obtaining target driving data corresponding to the target vehicle.

[0139] For details about this step, please refer to the above description of step S201, which will not be elaborated here.

[0140] Step S302: Analyze the target driving data to determine whether the target driving data meets a preset trigger condition.

[0141] Specifically, the target driving data includes target image data corresponding to multiple sensors of the target vehicle. The above step S302 may include the following steps:

[0142] Step S3021, performing target detection on each target image data, determining other target bodies from the target image data, and determining position information and category information corresponding to the other target bodies.

[0143] Specifically, the electronic device may collect at least two frames of target image data corresponding to the target vehicle based on a camera in the target vehicle.

[0144] The target detection algorithm may be BEV, YOLO series, FasterR-CNN, EfficientDet, VILT model, etc. The embodiment of the present application does not specifically limit the target detection algorithm.

[0145] It should be noted that the other target objects may be target objects around the target vehicle, such as surrounding vehicles, non-motor vehicles, pedestrians, and small animals, etc. The embodiments of the present application do not specifically limit the other target objects.

[0146] Step S3022: Determine the speed and movement direction information corresponding to the other target objects based on the continuous position information corresponding to the other target objects.

[0147] Specifically, the electronic device can use a target tracking algorithm (such as Kalman filtering, particle filtering, optical flow method, etc.) to track the motion trajectory of other target objects and obtain the corresponding speed and motion direction information of other target objects in different frames.

[0148] Step S3023, determining whether the target driving data meets the preset trigger condition based on the speed, direction information and category information of other target objects.

[0149] In another case, the above step S3023 may include the following steps:

[0150] Step b1, determining the acceleration of other target objects according to the velocity information of other target objects.

[0151] Specifically, the electronic device can calculate the speed of the target at different time points based on the speed and direction information of other target objects. The speed can be determined by calculating the displacement and time interval between adjacent position coordinates. A common method is to use numerical differentiation or other speed calculation algorithms. Then, the electronic device can calculate the rate of change of the speed based on the speed of the target at different time points. Acceleration represents the change of speed over time. Numerical differentiation or other rate of change calculation methods can be used to determine the acceleration.

[0152] Step b2: determining the acceleration thresholds corresponding to the other targets based on the category information corresponding to the other targets.

[0153] Optionally, the electronic device may determine the acceleration threshold corresponding to the other target objects according to the correspondence between the category information corresponding to the other target objects and the acceleration threshold.

[0154] Optionally, the electronic device may also set acceleration thresholds corresponding to other target objects according to category information corresponding to other target objects.

[0155] For example, if the category information corresponding to the other target object is a vehicle, the acceleration threshold may be 4 m / s 2 ; If the category information corresponding to other targets is pedestrians, the acceleration threshold of pedestrians can be 1m / s 2 .

[0156] Step b3: If the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition.

[0157] Specifically, the electronic device may compare the acceleration with an acceleration threshold, and if the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets a preset trigger condition.

[0158] In another case, the above step S3023 may include the following steps:

[0159] Step c1, determining the movement direction change trend of other target objects according to the speed and direction information of other target objects.

[0160] Specifically, the electronic device can calculate the movement direction of other target bodies based on the speed and direction information of other target bodies. Optionally, the electronic device can use vectors or angles to represent the direction. For example, the displacement vector of the target body between adjacent time points can be calculated, and then the direction of the vector can be determined. Then, the electronic device compares the movement directions at different time points to detect changes in direction. The change trend of the movement direction of other target bodies can be determined by calculating the difference between the directions or using other statistical methods to determine whether the direction has changed significantly.

[0161] Step c2: determining the motion direction change threshold corresponding to other targets based on the category information corresponding to other targets.

[0162] Specifically, the electronic device may determine the motion direction change threshold corresponding to the other target objects according to the correspondence between the category information corresponding to the other target objects and the motion direction change threshold.

[0163] Optionally, the electronic device may also set a motion direction change threshold corresponding to other target objects according to category information corresponding to other target objects.

[0164] Step c3: if the movement direction change is greater than the movement direction change threshold, it is determined that the target driving data meets the preset trigger condition.

[0165] Specifically, the electronic device may compare the change in motion direction with a motion direction change threshold, and if the change in motion direction is greater than the motion direction change threshold, it is determined that the target driving data meets a preset trigger condition.

[0166] Step S303: If the target driving data meets the preset trigger condition, a trigger time that meets the preset trigger condition is determined.

[0167] For details about this step, please refer to the above description of step S203, which will not be elaborated here.

[0168] Step S304: extracting a target video segment from the driving recorder based on the triggering moment, and saving the target video segment.

[0169] For details about this step, please refer to the above description of step S204, which will not be elaborated here.

[0170] The dashcam video processing method provided in the embodiment of the present application performs target detection on each target image data, determines other target objects from the target image data, and determines the position information and category information corresponding to the other target objects, thereby ensuring the accuracy of the position information and category information corresponding to the determined other target objects. According to the continuous position information corresponding to the other target objects, the speed and movement direction information corresponding to the other target objects are determined, thereby ensuring the accuracy of the trajectory information corresponding to the determined other target objects.

[0171] According to the speed information of other target bodies, the acceleration of other target bodies is determined, and according to the category information corresponding to other target bodies, the acceleration threshold corresponding to other target bodies is determined, thereby ensuring the accuracy of the acceleration threshold corresponding to other target bodies. If the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition, and then the target video clip in which the acceleration of other target bodies is greater than the acceleration threshold, that is, the acceleration of other target bodies suddenly changes, can be saved.

[0172] According to the speed and direction information of other targets, the change in the direction of motion of other targets is determined, ensuring the accuracy of the change in the direction of motion of other targets. According to the category information corresponding to other targets, the change threshold of the direction of motion of other targets is determined, ensuring the accuracy of the change threshold of the direction of motion of other targets. If the change in the direction of motion is greater than the change threshold of the direction of motion, it is determined that the target driving data meets the preset trigger condition, and then the target video clip with a sudden change in the direction of motion of other targets can be saved.

[0173] In this embodiment, a driving recorder video processing method is provided, which can be used in the above-mentioned electronic device. Figure 7 is a flow chart of a method for processing a driving recorder video according to an embodiment of the present invention. Figure 7 As shown, the process includes the following steps:

[0174] Step S401, obtaining target driving data corresponding to the target vehicle.

[0175] For details about this step, please refer to the above description of step S301, which will not be elaborated here.

[0176] Step S402: Analyze the target driving data to determine whether the target driving data meets a preset trigger condition.

[0177] Specifically, the target driving data includes target image data corresponding to the target vehicle. The above step S402 may include the following steps:

[0178] Step S4021, identifying the target image data and determining the driving environment corresponding to the target vehicle.

[0179] The target image data may include road conditions, weather conditions, congestion conditions, and accident conditions.

[0180] Specifically, the electronic device can pre-process the collected target image data, such as denoising, enhancing, cropping, etc., to improve the image quality and the accuracy of subsequent recognition. Then, features related to road conditions, weather conditions, congestion conditions, and accident conditions are extracted from the processed target image data. These features may include road signs, markings, traffic lights, vehicle density, weather conditions (such as sunny days, rainy days, foggy days, etc.), accident signs (such as collision marks, vehicle damage, etc.), etc. Then, a large amount of annotated data is used to train a machine learning or deep learning model to learn how to identify different road conditions, weather conditions, congestion conditions, and accident conditions based on the extracted features. Then, the electronic device inputs the target image data to be identified into the trained model, performs reasoning and prediction, and obtains the classification or description of the road conditions, weather conditions, congestion conditions, and accident conditions corresponding to the target vehicle.

[0181] Step S4022: If the driving environment meets the preset environmental conditions, it is determined that the target driving data meets the preset trigger conditions.

[0182] Specifically, if the road condition is any one of an viaduct, a fork intersection, an intersection and a roundabout, and / or the weather condition is any one of a cloudy day, a rainy day, a snowy day and a haze day, and / or the congestion situation is congestion, and / or the accident situation is an accident, then it is determined that the target driving data meets the preset trigger conditions.

[0183] Step S4023: if the driving environment does not satisfy the preset environmental condition, it is determined that the target driving data does not satisfy the preset trigger condition.

[0184] Specifically, if the driving environment does not meet the preset environmental condition, it is determined that the target driving data does not meet the preset trigger condition.

[0185] Step S403: if the target driving data meets the preset trigger condition, determine the trigger time that meets the preset trigger condition.

[0186] For details about this step, please refer to the above description of step S303.

[0187] Step S404: extracting a target video segment from the driving recorder based on the triggering moment, and saving the target video segment.

[0188] For details about this step, please refer to the above description of step S304.

[0189] The dash cam video processing method provided in the embodiment of the present application identifies the target image data and determines the driving environment corresponding to the target vehicle; the driving environment includes road conditions, weather conditions, congestion conditions and accident conditions; if the driving environment meets the preset environmental conditions, it is determined that the target driving data meets the preset trigger conditions; if the driving environment does not meet the preset environmental conditions, it is determined that the target driving data does not meet the preset trigger conditions, and the target video clip corresponding to the complex driving environment can be saved.

[0190] For better description, the driving recorder video processing method provided in the embodiment of the present application is as follows: Figure 8 As shown, an embodiment of the present application provides a flow chart of a driving recorder video processing method.

[0191] XPU (autonomous driving controller chip) receives the vehicle status data transmitted by MCU based on the CAN bus, and receives the target image data collected by the surround view camera and the front view camera after serializer encoding, decodes the target image data through the deserializer, performs image data transcoding, downsampling and other preprocessing, and then inputs the preprocessed target image data into the preset recognition model for target detection, and determines the position information and category information corresponding to other target bodies in the target image data. In addition, XPU performs scene recognition on the preprocessed target image data to determine the driving road condition scene corresponding to the target vehicle. Then, based on the vehicle status data of the vehicle, the position and category information corresponding to other target bodies, and the driving road condition scene, it is determined that the target driving data meets the preset trigger conditions. Finally, based on the above preset trigger conditions and camera image data, the target video clip is extracted, the target video clip is saved to local storage, and the target video clip is uploaded to cloud storage.

[0192] In this embodiment, a driving recorder video processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0193] This embodiment provides a driving recorder video processing device, such as Fig. 9 As shown, including:

[0194] An acquisition module 501 is used to acquire target driving data corresponding to a target vehicle;

[0195] A first determination module 502 is used to analyze the target driving data to determine whether the target driving data meets a preset trigger condition;

[0196] A second determination module 503 is used to determine a triggering time that satisfies a preset triggering condition if the target driving data satisfies a preset triggering condition;

[0197] The extraction module 504 is used to extract the target video segment from the driving recorder based on the triggering moment and save the target video segment.

[0198] In some optional embodiments, the target driving data includes the self-vehicle driving data corresponding to the target vehicle. The first determination module 502 is specifically used to analyze the self-vehicle driving data to determine whether the target vehicle has emergency driving behavior; emergency driving behavior includes sudden braking driving behavior, sudden deceleration driving behavior, sudden acceleration driving behavior, and sharp turn driving behavior; if there is emergency driving behavior, it is determined that the target driving data meets the preset trigger condition; if there is no emergency driving behavior, it is determined that the target driving data does not meet the preset trigger condition.

[0199] In some optional embodiments, the target driving data includes target image data corresponding to multiple sensors of the target vehicle. The first determination module 502 is specifically used to: perform target detection on each target image data, determine other target objects from the target image data, and determine the position information and category information corresponding to the other target objects; determine the speed and movement direction information corresponding to the other target objects based on the continuous position information corresponding to the other target objects; and determine whether the target driving data meets the preset trigger conditions based on the speed, direction information and category information of the other target objects.

[0200] In some optional embodiments, the first determination module 502 is specifically used to determine the acceleration of other target objects based on the speed information of other target objects; determine the acceleration threshold corresponding to other target objects based on the category information corresponding to other target objects; if the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition.

[0201] In some optional embodiments, the first determination module 502 is specifically used to determine the change in motion direction of other target objects based on the speed and direction information of other target objects; determine the motion direction change threshold corresponding to other target objects based on the category information corresponding to other target objects; if the motion direction change is greater than the motion direction change threshold, it is determined that the target driving data meets the preset trigger condition.

[0202] In some optional embodiments, the target driving data includes target image data corresponding to multiple sensors of the target vehicle. The first determination module 502 is specifically used to identify the target image data and determine the driving environment corresponding to the target vehicle; the driving environment includes road conditions, weather conditions, congestion conditions and accident conditions; if the driving environment meets the preset environmental conditions, it is determined that the target driving data meets the preset trigger conditions; if the driving environment does not meet the preset environmental conditions, it is determined that the target driving data does not meet the preset trigger conditions.

[0203] In some optional embodiments, the extraction module 504 is specifically used to determine, based on the trigger moment, a first preset time length before the trigger moment as the start moment of the target video segment, and determine a second preset time length after the trigger moment as the end moment of the target video segment; extract the target video segment from the driving recorder according to the start moment and the end moment; determine at least one of the weather information, time information, road information, location information and event information corresponding to the target video segment; generate summary information based on at least one of the weather information, time information, road information, location information and event information; and store the target video segment and the summary information accordingly.

[0204] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0205] The dash cam video processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0206] The embodiment of the present invention also provides an electronic device having the above Fig. 9 The video processing device of the driving recorder is shown.

[0207] See also Fig.10 , Fig.10 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Fig.10As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.10 A processor 10 is taken as an example.

[0208] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0209] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0210] The memory 20 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 electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device 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.

[0211] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0212] The electronic device further comprises a communication interface 30 for the electronic device to communicate with other devices or a communication network.

[0213] An embodiment of the present invention also provides a target vehicle, including an electronic device, a vehicle body and a driving recorder, wherein the electronic device and the driving recorder are communicatively connected, and the electronic device is used to execute the driving recorder video processing method of any one of the above-mentioned implementation modes.

[0214] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0215] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0216] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A driving recorder video processing method, characterized in that: The method comprises: Obtain target driving data corresponding to the target vehicle; Analyzing the target driving data to determine whether the target driving data meets a preset trigger condition; If the target driving data satisfies the preset trigger condition, determining a trigger time at which the preset trigger condition is satisfied; Based on the triggering moment, a target video segment is extracted from the driving recorder, and the target video segment is saved.

2. The method according to claim 1, characterized in that The target driving data includes the self-vehicle driving data corresponding to the target vehicle, and the analyzing the target driving data to determine whether the target driving data meets a preset trigger condition includes: Analyze the self-vehicle driving data to determine whether the target vehicle has emergency driving behavior; the emergency driving behavior includes sudden braking driving behavior, sudden deceleration driving behavior, sudden acceleration driving behavior, and sharp turning driving behavior; If the emergency driving behavior exists, determining that the target driving data meets the preset trigger condition; If the emergency driving behavior does not exist, it is determined that the target driving data does not meet the preset trigger condition.

3. The method according to claim 1, characterized in that The target driving data includes target image data corresponding to a plurality of sensors of the target vehicle, and the identifying the target driving data to determine whether the target driving data meets a preset trigger condition includes: Performing target detection on each of the target image data, determining other target objects from the target image data, and determining position information and category information corresponding to the other target objects; Determine the speed and movement direction information corresponding to the other target according to the continuous position information corresponding to the other target; According to the speed and direction information of the other target objects and the category information, it is determined whether the target driving data meets a preset trigger condition.

4. The method according to claim 3, characterized in that The determining, based on the speed and direction information of the other target objects and the category information, whether the target driving data meets a preset trigger condition includes: Determining the acceleration of the other target object according to the velocity information of the other target object; Determining the acceleration threshold corresponding to the other target object according to the category information corresponding to the other target object; If the acceleration is greater than the acceleration threshold, it is determined that the target driving data meets the preset trigger condition.

5. The method according to claim 3, characterized in that: The determining, based on the speed and direction information of the other target objects and the category information, whether the target driving data meets a preset trigger condition includes: Determine the change trend of the movement direction of the other target according to the speed and direction information of the other target; Determining a motion direction change threshold corresponding to the other target according to the category information corresponding to the other target; If the movement direction change is greater than the movement direction change threshold, it is determined that the target driving data meets the preset trigger condition.

6. The method according to claim 1, characterized in that The target driving data includes target image data corresponding to the target vehicle, and the analyzing the target driving data to determine whether the target driving data meets a preset trigger condition includes: Identify the target image data to determine the driving environment corresponding to the target vehicle; the driving environment includes road conditions, weather conditions, congestion conditions, and accident conditions; If the driving environment satisfies a preset environmental condition, determining that the target driving data satisfies a preset trigger condition; If the driving environment does not meet the preset environmental condition, it is determined that the target driving data does not meet the preset trigger condition.

7. The method according to claim 1, characterized in that The step of extracting a target video segment from the driving recorder based on the triggering moment and saving the target video segment includes: Based on the triggering moment, determining a first preset time length before the triggering moment as the start time of the target video segment, and determining a second preset time length after the triggering moment as the end time of the target video segment; Extracting the target video clip from the driving recorder according to the start time and the end time; Determine at least one of weather information, time information, road information, location information, and event information corresponding to the target video clip; generating summary information based on at least one of the weather information, the time information, the road information, the location information, and the event information; The target video segment and the summary information are stored correspondingly.

8. A driving recorder video processing device, characterized in that: The device comprises: An acquisition module, used to acquire target driving data corresponding to a target vehicle; A first determination module, configured to analyze the target driving data to determine whether the target driving data meets a preset trigger condition; A second determination module, configured to determine a triggering time when the preset triggering condition is met if the target driving data meets the preset triggering condition; The extraction module is used to extract the target video segment from the driving recorder based on the triggering moment and save the target video segment.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the dash cam video processing method according to any one of claims 1 to 7 by executing the computer instructions.

10. A target vehicle, characterized in that: The invention comprises an electronic device, a vehicle body and a driving recorder, wherein the electronic device is communicatively connected with the driving recorder, and the electronic device is used to execute the driving recorder video processing method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the dashcam video processing method according to any one of claims 1 to 7.

12. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the driving recorder video processing method according to any one of claims 1 to 7.

Images