Dangerous driving identification method, device and equipment and storage medium
Analyze driving data and video data through the Internet of Vehicles platform, combine the types of emergency accidents to accurately determine whether the driver has dangerous driving behavior, solve the problem of low identification accuracy in the existing technology, and detect fatigue through monitoring data, improving identification accuracy sex.
Patent Information
- Application Number
- CN202411041289.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art fails to effectively consider emergency risk avoidance when identifying drivers’ dangerous driving behaviors, resulting in low identification accuracy.
The Internet of Vehicles platform receives and analyzes driving data in real time, obtains dash recorder video data, determines whether an emergency accident occurred in front of the vehicle, and compares emergency driving measures to determine whether there are dangerous driving behaviors.
It improves the accuracy of identification of dangerous driving behaviors, can accurately judge in emergency risk avoidance, reduce the rate of misjudgment, and detects driver fatigue in real time through monitoring data, further improving identification accuracy.
Smart Images

Figure CN119068684A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a dangerous driving identification method, device, equipment and storage medium. Background Art
[0002] At present, for public vehicles such as taxis, buses and long-distance coaches, safe driving by drivers is particularly important because it involves the safety of many passengers. The traditional technical solution for monitoring the driver's dangerous driving behavior is generally to install a vehicle-mounted monitoring camera on the vehicle, use the monitoring camera to capture images of the driver during driving, and then determine whether the driver has dangerous driving behavior by analyzing the vehicle's driving data and the images captured by the monitoring camera.
[0003] However, in some cases, when a driver performs dangerous driving behavior, it may be due to the need for emergency avoidance. In the process of judging the driver's dangerous driving behavior, the existing technology does not consider the driver's emergency avoidance, resulting in low accuracy in identifying the driver's dangerous driving behavior. Summary of the invention
[0004] The embodiments of the present invention provide a dangerous driving identification method, device, equipment and storage medium. The embodiments of the present invention can identify situations where a driver engages in dangerous driving behavior due to the need for emergency risk avoidance, improve the accuracy of identifying dangerous driving behavior, and solve the technical problem of low accuracy in identifying a driver's dangerous driving behavior in the prior art.
[0005] In a first aspect, an embodiment of the present invention provides a dangerous driving identification method, the method is applicable to a vehicle networking platform, the vehicle networking platform is communicatively connected with a vehicle-mounted terminal on a vehicle, and the method includes:
[0006] Receiving driving data uploaded by the vehicle-mounted terminal in real time;
[0007] In the case where it is determined according to the driving data that there is a suspected dangerous driving behavior, determining a first moment when the suspected dangerous driving behavior occurs;
[0008] Acquiring, through the vehicle terminal, video data captured by the driving recorder within a preset time length before the first moment;
[0009] In the case where it is determined according to the video data that an emergency accident occurs in front of the vehicle, determining the accident type of the emergency accident;
[0010] In the driving data, first driving data corresponding to the suspected dangerous driving behavior is determined, and whether there is a dangerous driving behavior is determined according to the accident type and the first driving data.
[0011] Wherein, determining whether there is a dangerous driving behavior according to the accident type and the first driving data includes:
[0012] Determining all emergency driving measures corresponding to the accident type, and determining emergency driving data corresponding to each of the emergency driving measures;
[0013] The first driving data is compared with each of the emergency driving data, and whether there is a dangerous driving behavior is determined based on the comparison result.
[0014] The step of comparing the first driving data with each of the emergency driving data and determining whether there is a dangerous driving behavior according to the comparison result includes:
[0015] Determine the actual steering and actual acceleration change of the vehicle according to the first driving data;
[0016] Determining emergency steering and emergency acceleration changes of the vehicle according to the emergency driving data;
[0017] The actual steering is compared with the emergency steering, the actual acceleration change is compared with the emergency acceleration change, and whether there is a dangerous driving behavior is determined based on the comparison result.
[0018] The step of comparing the actual steering with the emergency steering, comparing the actual acceleration change with the emergency acceleration change, and determining whether there is a dangerous driving behavior based on the comparison results includes:
[0019] Determine whether there is target emergency driving data in which the emergency steering is consistent with the actual steering and the deviation between the emergency acceleration change and the actual acceleration change is within a preset value range;
[0020] In the presence of the target emergency driving data, it is determined that there is no dangerous driving behavior.
[0021] The step of comparing the first driving data with each of the emergency driving data and determining whether there is a dangerous driving behavior according to the comparison result includes:
[0022] generating an actual movement trajectory according to the first driving data;
[0023] generating a theoretical moving trajectory according to each of the emergency driving data;
[0024] Determining whether there is a target theoretical movement trajectory in the theoretical movement trajectory whose similarity with the actual movement trajectory is greater than a preset similarity threshold;
[0025] In the case where the target theoretical movement trajectory exists, it is determined that there is no dangerous driving behavior.
[0026] Wherein, when it is determined according to the video data that an emergency accident occurs in front of the vehicle, determining the type of the emergency accident includes:
[0027] identifying a first object appearing in the video data and an object type of the first object;
[0028] determining a movement trajectory of the first object according to the video data;
[0029] Determining whether there is a matching emergency event in a preset emergency event database according to the first object, the object type, and the movement trajectory, wherein the emergency event database includes movement trajectories of objects of different object types under different emergency events;
[0030] In the case where it is determined that a matching emergency exists, determining that an emergency has occurred;
[0031] The accident type corresponding to the emergency accident that occurs is determined according to the movement trajectory.
[0032] Among them, it also includes:
[0033] Acquiring the driver's monitoring data in real time through the vehicle-mounted terminal;
[0034] When it is determined according to the monitoring data that the driver is driving fatigued, it is determined that there is dangerous driving behavior.
[0035] In a second aspect, an embodiment of the present invention provides a dangerous driving identification device, which is applicable to a vehicle networking platform, and the vehicle networking platform is communicatively connected with a vehicle-mounted terminal on a vehicle, and the device includes:
[0036] A data receiving module, used for receiving driving data uploaded by the vehicle-mounted terminal in real time;
[0037] a time determination module, for determining a first time when the suspected dangerous driving behavior occurs, when it is determined according to the driving data that there is a suspected dangerous driving behavior;
[0038] A data acquisition module, used to acquire, through the vehicle-mounted terminal, video data captured by the driving recorder within a preset time length before the first moment;
[0039] A type determination module, configured to determine the type of the emergency accident when it is determined according to the video data that an emergency accident occurs in front of the vehicle;
[0040] The dangerous driving determination module is used to determine the first driving data corresponding to the suspected dangerous driving behavior in the driving data, and determine whether there is a dangerous driving behavior according to the accident type and the first driving data.
[0041] In a third aspect, an embodiment of the present invention provides a dangerous driving identification device, the dangerous driving identification device comprising a processor and a memory;
[0042] The memory is used to store a computer program and transmit the computer program to the processor;
[0043] The processor is used to execute the dangerous driving identification method as described in the first aspect according to the instructions in the computer program.
[0044] In a fourth aspect, an embodiment of the present invention provides a storage medium storing computer executable instructions, which, when executed by a computer processor, are used to execute the dangerous driving identification method as described in the first aspect.
[0045] The embodiment of the present invention provides a dangerous driving identification method, device, equipment and storage medium. In the embodiment of the present invention, when the vehicle networking platform determines that the driver has suspected dangerous driving behavior according to the driving data of the vehicle, it will obtain the video data of the driving recorder through the vehicle terminal, and when it is determined that an emergency accident has occurred in front of the vehicle according to the video data, it will determine whether the first driving data is an emergency driving measure corresponding to the accident type according to the first driving data corresponding to the suspected dangerous driving behavior and the accident type of the emergency accident, thereby determining whether the suspected dangerous driving behavior is a dangerous driving behavior. The embodiment of the present invention can identify the situation where the driver has dangerous driving behavior due to the need for emergency avoidance, improve the accuracy of identifying dangerous driving behavior, and solve the technical problem of low accuracy in identifying the driver's dangerous driving behavior in the prior art. In addition, the vehicle networking platform of the embodiment of the present invention will obtain the driver's monitoring data in real time during the driver's driving process, and when it is determined that the driver is fatigued according to the monitoring data, it is determined that the driver has dangerous driving behavior, further improving the accuracy of identifying dangerous driving behavior. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 A flowchart of a dangerous driving identification method provided by an embodiment of the present invention.
[0047] Figure 2 A specific process for determining dangerous driving behavior is provided in an embodiment of the present invention.
[0048] Figure 3 A schematic diagram of the structure of a dangerous driving identification device provided in an embodiment of the present invention.
[0049] Figure 4 A schematic diagram of the structure of a dangerous driving identification device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0050] The following description and accompanying drawings fully illustrate the specific embodiments of the present application so that those skilled in the art can practice them. The examples represent possible variations only. Unless explicitly required, separate components and functions are optional, and the order of operation can vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. The scope of the embodiments of the present application includes the entire scope of the claims, and all available equivalents of the claims. In this article, each embodiment may be represented individually or generally by the term "invention", which is only for convenience, and if more than one invention is disclosed in fact, it is not intended to automatically limit the scope of the application to any single invention or inventive concept. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, without requiring or implying any actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed. The various embodiments are described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. As for the structures, products, etc. disclosed in the embodiments, since they correspond to the parts disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0051] like Figure 1 As shown, Figure 1 A flowchart of a dangerous driving identification method provided by an embodiment of the present invention. The dangerous driving identification method provided by an embodiment of the present invention is applicable to a vehicle networking platform, which is connected to a vehicle-mounted terminal on a vehicle. The vehicle networking platform can obtain the vehicle's status information from the vehicle-mounted terminal and effectively use the status information to provide different functional services for the vehicle during the vehicle operation. The dangerous driving identification method provided by an embodiment of the present invention includes:
[0052] Step 101: Receive driving data uploaded by the vehicle terminal in real time.
[0053] In this embodiment, the vehicle terminal on the vehicle will collect the driving data of the vehicle in real time, wherein the driving data is relevant data during the vehicle driving process, such as the vehicle speed data, acceleration data, braking data, and steering data, etc. After collecting the driving data, the vehicle terminal will upload the driving data to the Internet of Vehicles platform in real time, and the Internet of Vehicles platform needs to receive the driving data uploaded by each vehicle terminal in real time.
[0054] Step 102: When it is determined based on the driving data that there is a suspected dangerous driving behavior, determine the first moment when the suspected dangerous driving behavior occurs.
[0055] After receiving the driving data uploaded by the vehicle terminal, the Internet of Vehicles platform needs to analyze the driving data to determine whether the driver has suspected dangerous driving behavior, where suspected dangerous driving behavior refers to possible dangerous driving behavior. Specifically, the Internet of Vehicles platform can analyze the vehicle's speed change, acceleration change and steering situation based on the driving data, and evaluate whether the vehicle frequently exceeds the speed or changes dramatically according to the speed change, determine whether the vehicle accelerates or brakes suddenly according to the acceleration change, and analyze whether the vehicle's steering operation is frequent or sudden according to the steering situation. Finally, according to the analysis results, if the vehicle's speed exceeds the speed threshold, the acceleration change exceeds the preset change range, or the steering operation within the preset time exceeds the preset number of times, it can be determined that the vehicle is in a dangerous driving state at this time and the driver of the vehicle has suspected dangerous driving behavior. The reason for not directly determining whether the driver has dangerous driving behavior at this time is that there may be an emergency in the vehicle during the driving process, and the driver has to accelerate, brake suddenly or frequently turn in order to avoid danger in an emergency. At this time, it should not be directly considered that the driver has dangerous driving behavior. If the Internet of Vehicles platform determines that the driver has suspected dangerous driving behavior based on the driving data, it needs to further determine the first moment when the suspected dangerous driving behavior occurs.
[0056] Step 103: Obtain, through the vehicle-mounted terminal, video data captured by the driving recorder within a preset time length before the first moment.
[0057] After determining the first moment, the Internet of Vehicles platform needs to further obtain the video data captured by the driving recorder within a preset time length before the first moment from the vehicle-mounted terminal of the vehicle. In this embodiment, the vehicle-mounted terminal is in communication connection with the driving recorder, and the driving recorder is used to capture the video data in front of the front of the vehicle. In addition, the preset time length can be set according to actual needs. For example, in this embodiment, the preset time length can be set to 10 seconds or 15 seconds, that is, the video data within 10 seconds or 15 seconds before the first moment when the suspected dangerous driving behavior occurs is obtained from the driving recorder.
[0058] Step 104: When it is determined based on the video data that an emergency accident occurs in front of the vehicle, determine the type of the emergency accident.
[0059] After acquiring the video data, the Internet of Vehicles platform needs to further analyze whether an emergency accident has occurred in front of the vehicle based on the video data. For example, the Internet of Vehicles platform first needs to detect the target that appears in the picture from the video data. After that, the Internet of Vehicles platform can track the detected target, obtain its trajectory, and identify whether the target has abnormal behavior based on its trajectory, such as suddenly stopping moving, suddenly invading the current lane, etc. When it is determined that the target has abnormal behavior, it is determined that an emergency accident has occurred in front of the vehicle, and the accident type corresponding to the emergency accident needs to be determined.
[0060] Based on the above embodiment, in step 104, when it is determined according to the video data that an emergency accident occurs in front of the vehicle, determining the type of the emergency accident includes:
[0061] Step 1041, identify the first object appearing in the video data and the object type of the first object. In this embodiment, the Internet of Vehicles platform first needs to identify the first object appearing in the video data by calling a pre-trained target recognition model, and after identifying the first object, determine the object type of the first object, for example, the object type of the first object can be a vehicle, a pedestrian, an animal, etc. The target recognition model can be obtained by training a neural network. The specific process can refer to the prior art and will not be repeated in this embodiment.
[0062] Step 1042: Determine the movement trajectory of the first object according to the video data.
[0063] After identifying the first object from the video data, the Internet of Vehicles platform needs to further extract the movement trajectory of the first object from the video data, wherein the movement trajectory of the first object can be extracted by using algorithms such as background difference, frame difference or optical flow method, or by using a machine learning algorithm.
[0064] Step 1043: Determine whether there is a matching emergency event in a preset emergency event database according to the first object, the object type, and the movement trajectory. The emergency event database includes the movement trajectories of objects of different object types under different emergency events.
[0065] After determining the first object in the video data, the object type and the moving trajectory of the first object, the Internet of Vehicles platform needs to determine whether there is a matching emergency accident in the preset emergency accident database based on the object type and moving trajectory of the first object, wherein the emergency accident database includes the moving trajectories of objects of different object types under different emergency accidents. For example, when the emergency accident is a pedestrian intruding into a lane, the moving trajectory of the pedestrian is from outside the lane where the vehicle is currently traveling to inside the lane where the vehicle is currently traveling; when the emergency accident is an emergency brake of the vehicle in front, the moving trajectory of the vehicle in front is from moving to stopping, etc. The Internet of Vehicles platform can match whether there is an emergency accident with the same object type and the same moving trajectory in the emergency accidents in the emergency accident database based on the object type and moving trajectory of the first object, and if so, the emergency accident is determined as a matching emergency accident.
[0066] Step 1044: When it is determined that a matching emergency exists, determine that an emergency has occurred.
[0067] When the Internet of Vehicles platform determines that a matching emergency accident exists, it determines that an emergency accident has occurred in front of the vehicle.
[0068] Step 1045: Determine the accident type corresponding to the emergency accident that occurs according to the movement trajectory.
[0069] After determining that an emergency has occurred in front of the vehicle, the Internet of Vehicles platform needs to further determine the type of accident corresponding to the emergency based on the movement trajectory of the first object causing the emergency, where the accident type is used to characterize the type of accident. When determining the type of accident, the type of accident can be determined based on the direction of the danger source compared to the current vehicle based on the movement trajectory. For example, the accident type may include sudden braking of the vehicle in front, foreign objects intruding from the left side of the lane, and foreign objects intruding from the right side of the lane.
[0070] Step 105: Determine in the driving data the first driving data corresponding to the suspected dangerous driving behavior, and determine whether there is any dangerous driving behavior based on the accident type and the first driving data.
[0071] After the Internet of Vehicles platform determines the occurrence of an emergency accident and the type of emergency accident based on the video data, it needs to further obtain the first driving data corresponding to the suspected dangerous driving behavior from the driving data, that is, the relevant driving data that can determine the suspected dangerous driving behavior. It can be understood that the first driving data is driving data over a period of time, not driving data at a certain moment.
[0072] After obtaining the first driving data, the Internet of Vehicles platform needs to determine whether the driver of the vehicle actually has dangerous driving behavior based on the accident type and the first driving data. Exemplarily, the Internet of Vehicles platform can obtain the corresponding emergency driving measures based on the accident type, and determine whether the control result of the first driving data is consistent with the emergency driving measures. In the case of consistency, it means that the suspected dangerous driving behavior is an emergency driving measure taken by the driver for emergency avoidance, and there is no dangerous driving behavior at this time. In the case of inconsistency, it can be determined that the driver did not take correct emergency driving measures when encountering an emergency accident, and it is determined that the driver has dangerous driving behavior.
[0073] Based on the above embodiment, in step 105, determining whether there is a dangerous driving behavior according to the accident type and the first driving data includes:
[0074] Step 1051: Determine all emergency driving measures corresponding to the accident type, and determine emergency driving data corresponding to each emergency driving measure.
[0075] When determining whether the driver has engaged in dangerous driving behavior, it is first necessary to determine all emergency driving measures corresponding to the accident type, wherein emergency driving measures are driving measures taken to avoid emergency accidents, and emergency driving measures can be pre-set by the user. Exemplary, when the accident type is foreign objects intruding on the left side of the lane, the corresponding emergency driving measures may be braking and / or the vehicle avoiding to the right. After all emergency driving measures are determined, it is necessary to determine the emergency driving data corresponding to each emergency driving measure, that is, the speed information, acceleration and deceleration information, and steering information corresponding to the vehicle when executing the emergency driving measures.
[0076] Step 1051: Compare the first driving data with each emergency driving data, and determine whether there is any dangerous driving behavior based on the comparison result.
[0077] After determining the emergency driving data corresponding to each emergency driving measure, the Internet of Vehicles platform needs to compare the first driving data with the emergency driving data, and determine whether the driving measure corresponding to the first driving data is an emergency driving measure based on the comparison result, thereby determining whether there is a dangerous driving behavior. Exemplarily, the Internet of Vehicles platform can determine the similarity between the first driving data and the emergency driving data, and determine whether there is a dangerous driving behavior based on the similarity.
[0078] Based on the above embodiment, in step 1051, the first driving data is compared with each emergency driving data, and according to the comparison result, it is determined whether there is a dangerous driving behavior, including:
[0079] Step 10511: Determine the actual steering and actual acceleration change of the vehicle according to the first driving data.
[0080] Step 10512: Determine the emergency steering and emergency acceleration changes of the vehicle based on the emergency driving data.
[0081] Step 10513: compare the actual steering with the emergency steering, compare the actual acceleration change with the emergency acceleration change, and determine whether there is any dangerous driving behavior based on the comparison results.
[0082] In one embodiment, when determining whether there is a dangerous driving behavior, it is necessary to determine the actual steering and actual acceleration change of the vehicle based on the first driving data, and determine the emergency steering and emergency acceleration change of the vehicle based on the emergency driving data. After that, the actual steering is compared with the emergency steering, and the actual acceleration change is compared with the emergency acceleration change. Finally, based on the comparison results of the two data, it is determined whether there is a dangerous driving behavior. Specifically, it can be determined whether there is a target emergency driving data in which the emergency steering is consistent with the actual steering, and the deviation between the emergency acceleration change and the actual acceleration change is within a preset numerical range; in the case of the existence of target emergency driving data, it is determined that there is no dangerous driving behavior. Among them, the consistency of emergency steering and actual steering only requires the direction of steering to be consistent, and there is no need to require the steering angle to be consistent. In addition, the preset numerical range can be set according to actual needs. Considering the different reaction speeds and operating methods of different drivers, the preset numerical range can be set larger, so as to leave sufficient operating space for the driver. In the case of the existence of target emergency driving data, it means that the driver has taken emergency driving measures for suspected dangerous driving behavior, and it is determined that the suspected dangerous driving behavior is not a dangerous driving behavior. In one embodiment, the specific process of determining dangerous driving behavior is as follows Figure 2 shown.
[0083] In another embodiment, in step 1051, the first driving data is compared with each emergency driving data, and according to the comparison result, it is determined whether there is a dangerous driving behavior, including:
[0084] Step 10514: Generate an actual moving trajectory according to the first driving data.
[0085] Step 10515: Generate a theoretical moving trajectory according to each emergency driving data.
[0086] In another embodiment, when comparing the first driving data with each emergency driving data, the Internet of Vehicles platform may generate an actual moving trajectory according to the first driving data, and generate a theoretical moving trajectory according to each emergency driving data.
[0087] Step 10516: Determine whether there is a target theoretical movement trajectory in the theoretical movement trajectory whose similarity with the actual movement trajectory is greater than a preset similarity threshold.
[0088] After generating the actual moving trajectory and the theoretical moving trajectory, the Internet of Vehicles platform needs to determine in the theoretical moving trajectory whether there is a target theoretical moving trajectory whose similarity with the actual moving trajectory is greater than a preset similarity threshold, wherein the preset similarity threshold is a pre-set similarity threshold, and the preset similarity threshold can be set in advance according to actual needs.
[0089] Step 10517: In the case where the target theoretical moving trajectory exists, determine that there is no dangerous driving behavior.
[0090] If there is a target theoretical moving trajectory in the theoretical moving trajectory whose similarity with the actual moving trajectory is greater than a preset threshold, it can be determined that there is no dangerous driving behavior at this time. In addition, if it is determined that there is suspected dangerous driving behavior and it is determined that there is no emergency accident based on the video data, it can be determined that there is dangerous driving behavior.
[0091] Based on the above embodiment, it also includes:
[0092] Step 106: Obtain the driver's monitoring data in real time through the vehicle terminal;
[0093] In one embodiment, the Internet of Vehicles platform also obtains the driver's monitoring data in real time through the vehicle terminal, where the monitoring data refers to the data obtained by monitoring the driver. For example, the monitoring data may be an image of the driver during driving captured by a camera in the vehicle, or the driving data may be the driver's physical state data during driving detected by a sensor.
[0094] Step 107: When it is determined based on the monitoring data that the driver is driving fatigued, determine that there is dangerous driving behavior.
[0095] After obtaining the driver's monitoring data, the Internet of Vehicles platform will further analyze the monitoring data to determine whether the driver is in a state of fatigue driving. Specifically, when the monitoring data is an image, the Internet of Vehicles platform first needs to preprocess the image. The preprocessing process includes graying, normalization, cropping to highlight the facial area, etc., to ensure that the quality and format of the input data meet the requirements of the subsequent processing algorithm. After that, the Internet of Vehicles platform can use a deep learning model (such as CNN) to extract fatigue-related features from the preprocessed image. The features include: eye closure degree, blinking frequency, head posture, mouth opening and closing, and facial expression changes. After that, the deep learning model can output the probability score of the driver's fatigue state based on the extracted features. When the score exceeds the set score threshold, the Internet of Vehicles platform believes that the driver is in a state of fatigue driving. In the case of determining that the driver is driving fatigued, since the driver is extremely easy to be distracted or doze off during driving, it poses a serious threat to the safety of other vehicles. At this time, the Internet of Vehicles platform will directly determine that the driver has dangerous driving behavior.
[0096] The embodiment of the present invention provides a dangerous driving identification method. In the embodiment of the present invention, when the vehicle networking platform determines that the driver has suspected dangerous driving behavior based on the driving data of the vehicle, it will obtain the video data of the driving recorder through the vehicle terminal, and when it is determined that an emergency accident has occurred in front of the vehicle based on the video data, it will determine whether the first driving data is an emergency driving measure corresponding to the accident type based on the first driving data corresponding to the suspected dangerous driving behavior and the accident type of the emergency accident, thereby determining whether the suspected dangerous driving behavior is a dangerous driving behavior. The embodiment of the present invention can identify the situation where the driver has dangerous driving behavior due to the need for emergency avoidance, improve the accuracy of identifying dangerous driving behavior, and solve the technical problem of low accuracy in identifying the driver's dangerous driving behavior in the prior art. In addition, the vehicle networking platform of the embodiment of the present invention will obtain the driver's monitoring data in real time during the driver's driving process, and when it is determined that the driver is driving fatigued based on the monitoring data, it will determine that the driver has dangerous driving behavior, further improving the accuracy of identifying dangerous driving behavior.
[0097] The embodiment of the present invention also provides a dangerous driving identification device, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of a dangerous driving identification device provided by an embodiment of the present invention. The dangerous driving identification device provided by an embodiment of the present invention includes:
[0098] The data receiving module 201 is used to receive driving data uploaded by the vehicle terminal in real time.
[0099] The time determination module 202 is used to determine the first time when the suspected dangerous driving behavior occurs when it is determined according to the driving data that there is a suspected dangerous driving behavior.
[0100] The data acquisition module 203 is used to acquire the video data captured by the driving recorder within a preset time length before the first moment through the vehicle terminal.
[0101] The type determination module 204 is used to determine the type of the emergency accident when it is determined according to the video data that an emergency accident occurs in front of the vehicle.
[0102] The dangerous driving determination module 205 is used to determine the first driving data corresponding to the suspected dangerous driving behavior in the driving data, and determine whether there is a dangerous driving behavior according to the accident type and the first driving data.
[0103] Based on the above embodiment, the dangerous driving determination module 205 includes:
[0104] An emergency driving data determination submodule, used to determine all emergency driving measures corresponding to the accident type, and to determine emergency driving data corresponding to each emergency driving measure;
[0105] The dangerous driving judgment submodule is used to compare the first driving data with each emergency driving data, and determine whether there is any dangerous driving behavior based on the comparison result.
[0106] Based on the above embodiment, the dangerous driving judgment submodule includes:
[0107] an actual driving determination unit, configured to determine an actual steering and an actual acceleration change of the vehicle according to the first driving data;
[0108] An emergency driving determination unit, used to determine the emergency steering and emergency acceleration changes of the vehicle according to the emergency driving data;
[0109] The comparison unit is used to compare the actual steering with the emergency steering, and to compare the actual acceleration change with the emergency acceleration change, and to determine whether there is any dangerous driving behavior based on the comparison results.
[0110] Based on the above embodiment, the comparison unit is specifically used to determine whether there is target emergency driving data in which the emergency steering is consistent with the actual steering, and the deviation between the emergency acceleration change and the actual acceleration change is within a preset numerical range; if there is target emergency driving data, it is determined that there is no dangerous driving behavior.
[0111] Based on the above embodiment, the dangerous driving judgment submodule includes:
[0112] An actual trajectory generating unit, configured to generate an actual moving trajectory according to the first driving data;
[0113] A theoretical trajectory generating unit, used for generating a theoretical moving trajectory according to each emergency driving data;
[0114] A similarity determination unit, used to determine whether there is a target theoretical movement trajectory in the theoretical movement trajectory whose similarity with the actual movement trajectory is greater than a preset similarity threshold;
[0115] The dangerous driving determination unit is used to determine whether there is no dangerous driving behavior when there is a target theoretical moving trajectory.
[0116] Based on the above embodiment, the type determination module 204 includes:
[0117] An object recognition submodule, configured to recognize a first object and an object type of the first object appearing in the video data;
[0118] A movement trajectory determination submodule, used to determine the movement trajectory of the first object according to the video data;
[0119] An emergency matching submodule, for determining whether there is a matching emergency in a preset emergency database according to the first object, the object type and the movement trajectory, wherein the emergency database includes movement trajectories of objects of different object types under different emergency situations;
[0120] An emergency determination submodule, for determining that an emergency has occurred if it is determined that a matching emergency exists;
[0121] The accident type determination submodule is used to determine the accident type corresponding to the emergency accident that occurred according to the movement trajectory.
[0122] Based on the above embodiment, it also includes:
[0123] A monitoring data acquisition module is used to obtain the driver's monitoring data in real time through the vehicle terminal;
[0124] The fatigue driving determination module is used to determine the presence of dangerous driving behavior when the driver is determined to be driving fatigued according to monitoring data.
[0125] The embodiment of the present invention provides a dangerous driving identification method. In the embodiment of the present invention, when the vehicle networking platform determines that the driver has suspected dangerous driving behavior based on the driving data of the vehicle, it will obtain the video data of the driving recorder through the vehicle terminal, and when it is determined that an emergency accident has occurred in front of the vehicle based on the video data, it will determine whether the first driving data is an emergency driving measure corresponding to the accident type based on the first driving data corresponding to the suspected dangerous driving behavior and the accident type of the emergency accident, thereby determining whether the suspected dangerous driving behavior is a dangerous driving behavior. The embodiment of the present invention can identify the situation where the driver has dangerous driving behavior due to the need for emergency avoidance, improve the accuracy of identifying dangerous driving behavior, and solve the technical problem of low accuracy in identifying the driver's dangerous driving behavior in the prior art. In addition, the vehicle networking platform of the embodiment of the present invention will obtain the driver's monitoring data in real time during the driver's driving process, and when it is determined that the driver is driving fatigued based on the monitoring data, it will determine that the driver has dangerous driving behavior, further improving the accuracy of identifying dangerous driving behavior.
[0126] The dangerous driving identification device provided in the embodiment of the present invention is included in the dangerous driving identification equipment and can be used to execute the dangerous driving identification method provided in the above embodiment, and has corresponding functions and beneficial effects.
[0127] It is worth noting that in the above-mentioned embodiment of the dangerous driving identification device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0128] This embodiment also provides a dangerous driving identification device, such as Figure 4 As shown, Figure 4 A schematic diagram of the structure of a dangerous driving identification device provided in an embodiment of the present invention, wherein the dangerous driving identification device 30 includes a processor 300 and a memory 301;
[0129] The memory 301 is used to store the computer program 302 and transmit the computer program 302 to the processor 300;
[0130] The processor 300 is used to execute the steps in the above-mentioned dangerous driving identification method embodiment according to the instructions in the computer program 302.
[0131] Exemplarily, the computer program 302 may be divided into one or more modules / units, one or more modules / units are stored in the memory 301, and are executed by the processor 300 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 302 in the dangerous driving identification device 30.
[0132] The dangerous driving identification device 30 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The dangerous driving identification device 30 may include, but is not limited to, a processor 300 and a memory 301. Those skilled in the art will appreciate that Figure 4 It is only an example of the dangerous driving identification device 30 and does not constitute a limitation of the dangerous driving identification device 30. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the dangerous driving identification device 30 may also include input and output devices, network access devices, buses, etc.
[0133] The processor 300 may be a central processing unit (CPU), or 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.
[0134] The memory 301 may be an internal storage unit of the dangerous driving identification device 30, such as a hard disk or memory of the dangerous driving identification device 30. The memory 301 may also be an external storage device of the dangerous driving identification device 30, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the dangerous driving identification device 30. Further, the memory 301 may also include both an internal storage unit and an external storage device of the dangerous driving identification device 30. The memory 301 is used to store computer programs and other programs and data required by the dangerous driving identification device 30. The memory 301 may also be used to temporarily store data that has been output or is to be output.
[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0136] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store computer programs.
[0140] An embodiment of the present invention further provides a storage medium containing computer executable instructions, which are used to execute a dangerous driving identification method when executed by a computer processor. The method includes the following steps:
[0141] Receive driving data uploaded by the vehicle terminal in real time;
[0142] In the case where suspected dangerous driving behavior is determined based on the driving data, determining the first moment when the suspected dangerous driving behavior occurs;
[0143] Acquire, through the vehicle terminal, video data captured by the driving recorder within a preset time length before the first moment;
[0144] In the case where an emergency accident is determined to have occurred in front of the vehicle based on the video data, determining the accident type of the emergency accident;
[0145] In the driving data, first driving data corresponding to the suspected dangerous driving behavior is determined, and whether the dangerous driving behavior exists is determined according to the accident type and the first driving data.
[0146] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the embodiments of the present invention are not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the embodiments of the present invention. Therefore, although the embodiments of the present invention are described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.
Claims
1. A dangerous driving identification method, the method is applicable to a vehicle networking platform, the vehicle networking platform is communicatively connected with a vehicle-mounted terminal on a vehicle, It is characterized in that The method comprises: Receiving driving data uploaded by the vehicle-mounted terminal in real time; In the case where it is determined according to the driving data that there is a suspected dangerous driving behavior, determining a first moment when the suspected dangerous driving behavior occurs; Acquiring, through the vehicle terminal, video data captured by the driving recorder within a preset time length before the first moment; In the case where it is determined according to the video data that an emergency accident occurs in front of the vehicle, determining the accident type of the emergency accident; In the driving data, first driving data corresponding to the suspected dangerous driving behavior is determined, and whether there is a dangerous driving behavior is determined according to the accident type and the first driving data.
2. The dangerous driving identification method according to claim 1, It is characterized in that The determining, based on the accident type and the first driving data, whether there is a dangerous driving behavior includes: Determining all emergency driving measures corresponding to the accident type, and determining emergency driving data corresponding to each of the emergency driving measures; The first driving data is compared with each of the emergency driving data, and whether there is a dangerous driving behavior is determined based on the comparison result.
3. The dangerous driving identification method according to claim 2, It is characterized in that The comparing the first driving data with each of the emergency driving data, and determining whether there is a dangerous driving behavior according to the comparison result, includes: Determine the actual steering and actual acceleration change of the vehicle according to the first driving data; Determining emergency steering and emergency acceleration changes of the vehicle according to the emergency driving data; The actual steering is compared with the emergency steering, the actual acceleration change is compared with the emergency acceleration change, and whether there is a dangerous driving behavior is determined based on the comparison result.
4. The dangerous driving identification method according to claim 3, It is characterized in that The comparing the actual steering with the emergency steering, comparing the actual acceleration change with the emergency acceleration change, and determining whether there is a dangerous driving behavior according to the comparison result, includes: Determine whether there is target emergency driving data in which the emergency steering is consistent with the actual steering and the deviation between the emergency acceleration change and the actual acceleration change is within a preset value range; In the presence of the target emergency driving data, it is determined that there is no dangerous driving behavior.
5. The dangerous driving identification method according to claim 2, It is characterized in that The comparing the first driving data with each of the emergency driving data, and determining whether there is a dangerous driving behavior according to the comparison result, includes: generating an actual movement trajectory according to the first driving data; generating a theoretical moving trajectory according to each of the emergency driving data; Determining whether there is a target theoretical movement trajectory in the theoretical movement trajectory whose similarity with the actual movement trajectory is greater than a preset similarity threshold; In the case where the target theoretical movement trajectory exists, it is determined that there is no dangerous driving behavior.
6. The dangerous driving identification method according to claim 1, It is characterized in that In the case where it is determined according to the video data that an emergency accident occurs in front of the vehicle, determining the type of the emergency accident includes: identifying a first object appearing in the video data and an object type of the first object; determining a movement trajectory of the first object according to the video data; Determining whether there is a matching emergency event in a preset emergency event database according to the first object, the object type, and the movement trajectory, wherein the emergency event database includes movement trajectories of objects of different object types under different emergency events; In the case where it is determined that a matching emergency exists, determining that an emergency has occurred; The accident type corresponding to the emergency accident that occurs is determined according to the movement trajectory.
7. The dangerous driving identification method according to claim 1, It is characterized in that Also includes: Acquiring the driver's monitoring data in real time through the vehicle-mounted terminal; When it is determined according to the monitoring data that the driver is driving fatigued, it is determined that there is dangerous driving behavior.
8. A dangerous driving identification device, the device is applicable to a vehicle networking platform, the vehicle networking platform is communicatively connected with a vehicle-mounted terminal on a vehicle, It is characterized in that The device comprises: A data receiving module, used for receiving driving data uploaded by the vehicle-mounted terminal in real time; a time determination module, for determining a first time when the suspected dangerous driving behavior occurs, when it is determined according to the driving data that there is a suspected dangerous driving behavior; A data acquisition module, used to acquire, through the vehicle-mounted terminal, video data captured by the driving recorder within a preset time length before the first moment; A type determination module, configured to determine the type of the emergency accident when it is determined according to the video data that an emergency accident occurs in front of the vehicle; The dangerous driving determination module is used to determine the first driving data corresponding to the suspected dangerous driving behavior in the driving data, and determine whether there is a dangerous driving behavior according to the accident type and the first driving data.
9. A dangerous driving identification device, It is characterized in that The dangerous driving identification device includes a processor and a memory; The memory is used to store a computer program and transmit the computer program to the processor; The processor is used to execute the dangerous driving identification method according to any one of claims 1-7 according to the instructions in the computer program.
10. A storage medium storing computer executable instructions, It is characterized in that The computer executable instructions are used to execute the dangerous driving identification method according to any one of claims 1 to 7 when executed by a computer processor.
