Vehicle driving behavior detection method and device and computer readable medium

Abstract

The invention provides a vehicle driving behavior detection method and device and a computer readable medium, and the method employs the GPS data course change and speed change of a vehicle to calculate and obtain the yaw rate and deceleration condition of the vehicle in the driving process, carries out the preliminary detection of the plugging behavior of the vehicle, and improves the detection precision of the vehicle. Compared with a detection scheme which only depends on speed or position changes in an existing scheme, the method is more accurate, misjudgment caused by other factors is avoided, meanwhile, on the basis that a preliminary detection result is obtained, a future data confirmation mechanism is adopted, GPS data in a future first time window are utilized, the suspected plugging situation is further confirmed, and the detection accuracy is improved. The misjudgment caused by the fluctuation of the yaw rate and the speed at a single moment is avoided, and the recognition accuracy of the plugging behavior is remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a vehicle driving behavior detection method, device and computer-readable medium. Background Art

[0002] With the development of automobile intelligence and autonomous driving technology, more and more vehicles are equipped with GPS positioning systems. The collection and analysis of vehicle trajectories has become an important means of intelligent traffic management and road safety monitoring. Traditional vehicle behavior analysis methods are mainly based on basic data such as vehicle location information and speed, and often ignore more complex driving behaviors, such as sudden acceleration, sudden deceleration, sharp turns, frequent lane changes, and cutting in, which can pose a serious threat to road traffic safety.

[0003] Existing GPS data analysis methods mostly rely on simple parameters, such as vehicle speed and acceleration, but lack comprehensive analysis of multiple factors. This leads to misjudgments or missed judgments when faced with complex driving behaviors, and cannot accurately reflect the driver's actual driving conditions. Summary of the invention

[0004] One object of the present application is to provide a vehicle driving behavior detection method, device and computer-readable medium.

[0005] To achieve the above objectives, the present application provides a vehicle driving behavior detection method, the method comprising:

[0006] Get the vehicle's GPS data;

[0007] Calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data;

[0008] Determine whether the yaw rate is within a preset first threshold interval, and if the yaw rate is within the first threshold interval, calculate a speed change value corresponding to a current GPS data point according to a speed difference between two most recent consecutive GPS data points in the GPS data;

[0009] Determine whether the speed change value exceeds a lane-crossing deceleration threshold, and if the speed change value exceeds the lane-crossing deceleration threshold, determine the current GPS data point as a suspected lane-crossing data point, and continue to acquire GPS data points within a first time window after the suspected lane-crossing data point;

[0010] In the process of continuously acquiring GPS data points in a first time window after the suspected traffic jam data point, determining whether each GPS data point in the first time window is a suspected traffic jam data point;

[0011] If the number of suspected loading data points in the GPS data points within the first time window reaches the jamming determination threshold, it is identified that the vehicle is jamming.

[0012] Further, after calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes:

[0013] determining whether the yaw rate is within a preset second threshold interval and the vehicle speed is greater than a lane-changing speed threshold, and if the yaw rate is within the preset second threshold interval and the vehicle speed is greater than the lane-changing speed threshold, identifying that the vehicle has changed lanes;

[0014] The number of lane changes of the vehicle within a second time window is detected. If the number of lane changes reaches a frequent lane change determination threshold and the accumulated heading change within the second time window is less than a heading change threshold, it is identified that the vehicle has undergone frequent lane changes.

[0015] Further, after calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes:

[0016] Confirm that the vehicle is not in a turning or U-turn state.

[0017] Furthermore, after obtaining the GPS data of the vehicle, the following steps are also included:

[0018] Calculate the acceleration corresponding to the current GPS data point based on the speed difference and time difference between the two most recent consecutive GPS data points in the GPS data;

[0019] determining whether a sudden acceleration detection condition or a sudden deceleration detection condition is satisfied according to the acceleration, and if the sudden acceleration detection condition or the sudden deceleration detection condition is satisfied, identifying that the vehicle has a sudden acceleration behavior or a sudden deceleration behavior;

[0020] The sudden acceleration detection condition includes: the acceleration is greater than the sudden acceleration threshold, the duration of the state where the acceleration is greater than the sudden acceleration threshold exceeds the sudden acceleration duration threshold, and the time interval from the last recognition of the sudden acceleration behavior exceeds the first time interval;

[0021] The sudden deceleration detection condition includes: the acceleration is less than the sudden deceleration threshold, the duration of the state where the acceleration is less than the sudden deceleration threshold exceeds the sudden deceleration duration threshold, and the time interval from the last recognition of the sudden deceleration behavior exceeds the second time interval.

[0022] Further, after calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes:

[0023] determining whether the yaw rate is within a preset third threshold interval and the vehicle speed is greater than a sharp turn speed threshold, and if the yaw rate is within the preset third threshold interval and the vehicle speed is greater than the sharp turn speed threshold, identifying that the vehicle may make a sharp turn;

[0024] The number of times that the vehicle may make a sharp turn is detected continuously, and if it exceeds a sharp turn detection threshold and the time interval from the last sharp turn behavior is more than a third time interval, the sharp turn behavior of the vehicle is identified.

[0025] Further, after calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes:

[0026] Determining whether the yaw rate is within a preset fourth threshold interval and the vehicle speed is greater than a right turn speed threshold, and if the yaw rate is within the preset fourth threshold interval and the vehicle speed is greater than the right turn speed threshold, identifying that the vehicle is turning right;

[0027] detecting, according to the vehicle speed, whether the vehicle stops during the right turn;

[0028] If no parking behavior occurs and the duration of the right turn behavior exceeds a preset time length, it is identified that the vehicle turns right without stopping.

[0029] Furthermore, before calculating the yaw rate corresponding to the current GPS data point based on the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes:

[0030] The GPS data is preprocessed.

[0031] Furthermore, the preprocessing method includes at least one of the following:

[0032] Perform accuracy filtering according to the positioning accuracy of the GPS data points, and select the GPS data points whose positioning accuracy meets the first preprocessing condition requirement;

[0033] Perform time difference verification based on the time of the GPS data point and the current standard time, and select the GPS data points whose time difference meets the second preprocessing condition;

[0034] Comparing the time of the GPS data point with the time of the previous GPS data point, filtering out the GPS data points whose time difference satisfies the third preprocessing condition;

[0035] The speed information of the GPS data points is acquired, and the GPS data points whose speed information meets the fourth preprocessing condition are screened out.

[0036] Based on another aspect of the present application, a vehicle driving behavior detection device is also provided, which includes a memory for storing computer program instructions and a processor for executing computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the vehicle driving behavior detection method.

[0037] An embodiment of the present application also provides a computer-readable medium on which computer program instructions are stored. The computer program instructions can be executed by a processor to implement the vehicle driving behavior detection method.

[0038] Compared with the prior art, the present application provides a vehicle driving behavior detection solution. After acquiring the GPS data of the vehicle, the solution can calculate the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data; then determine whether the yaw rate is within a preset first threshold interval. If the yaw rate is within the first threshold interval, calculate the speed change value corresponding to the current GPS data point according to the speed difference between the two most recent consecutive GPS data points in the GPS data; then determine whether the speed change value exceeds the lane-in deceleration threshold. If the speed change value exceeds the lane-in deceleration threshold, determine the current GPS data point as a suspected lane-in data point, and continuously acquire GPS data points within a first time window after the suspected lane-in data point; in the process of continuously acquiring GPS data points within a first time window after the suspected lane-in data point, determine whether each GPS data point within the first time window is a suspected lane-in data point; if the number of suspected loading data points among the GPS data points within the first time window reaches the lane-in determination threshold, identify that the vehicle has engaged in lane-in behavior. This solution uses the vehicle's GPS data heading changes and speed changes to calculate the vehicle's yaw rate and deceleration during driving, and uses this to perform preliminary detection of the vehicle's squeezing behavior. Compared with the existing detection scheme that only relies on speed or position changes, it is more accurate and avoids misjudgment caused by other factors. At the same time, based on the preliminary detection results, it adopts a future data confirmation mechanism and uses the GPS data in the first time window in the future to further confirm the suspected squeezing situation, avoiding misjudgment caused by yaw rate and speed fluctuations at a single moment, and significantly improving the recognition accuracy of squeezing behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0040] Figure 1 A flow chart of a vehicle driving behavior detection method provided in an embodiment of the present application;

[0041] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0042] The present application is described in further detail below in conjunction with the accompanying drawings.

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] In a typical configuration of the present application, the terminal and the equipment of the service network each include one or more processors (CPU), input / output interface, network interface and memory.

[0045] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0046] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0047] An embodiment of the present application provides a vehicle driving behavior detection method, which utilizes the vehicle's GPS data heading changes and speed changes to calculate the vehicle's yaw rate and deceleration during driving, and uses this to perform a preliminary detection of the vehicle's jamming behavior. Compared with the existing detection scheme that only relies on speed or position changes, the method is more accurate and avoids misjudgment caused by other factors. At the same time, based on the preliminary detection results, a future data confirmation mechanism is adopted to further confirm the suspected jamming situation using GPS data in the first time window in the future, thereby avoiding misjudgment caused by fluctuations in the yaw rate and speed at a single moment, and significantly improving the recognition accuracy of the jamming behavior.

[0048] In actual scenarios, the device executing the method may include a network device, or a device formed by integrating a user device and a network device through a network, or may also be an application running on the above device. The user device includes but is not limited to a computer, a mobile phone, a tablet computer, or various types of vehicle-mounted terminal devices; the network device includes but is not limited to a network host, a single network server, a server in which multiple network servers are concentrated, or a server in a distributed cloud network. The distributed cloud network described here is composed of a large number of hosts or network servers based on cloud computing.

[0049] Figure 1 The processing flow of a vehicle driving behavior detection method provided in an embodiment of the present application is shown, which at least includes the following processing steps:

[0050] Step S101, obtaining GPS data of the vehicle. The GPS data may include information such as time, position, speed, and heading of the vehicle during the process. In actual scenarios, when collecting GPS data, specific information such as position, speed, and heading at each sampling time point may be obtained based on a certain sampling frequency, so that the specific form of the GPS data may include GPS data points corresponding to each sampling time point collected in sequence.

[0051] In order to improve the accuracy of subsequent processing, the GPS data may be preprocessed before subsequent processing is performed. The preprocessing method may include at least one of the following:

[0052] 1. Precision filtering.

[0053] According to the positioning accuracy of the GPS data points, precision filtering is performed to filter out the GPS data points whose positioning accuracy meets the requirements of the first preprocessing condition. For example, for the acquisition device of some GPS data, the accuracy information about the GPS data can be obtained, and the first preprocessing condition can be set based on the accuracy, such as setting 150 meters as the threshold for precision filtering. If the accuracy of the GPS data point exceeds this threshold, the GPS data point is considered invalid. If the accuracy does not exceed this threshold, the GPS data point is considered valid, thereby filtering out the GPS data points whose positioning accuracy meets the requirements of the first preprocessing condition.

[0054] In addition, if the acquisition device of some GPS data cannot directly obtain the accuracy value, the acquisition accuracy of some specific information in the GPS data point can also be used as the accuracy of the GPS data point. For example, the number of decimal places of the longitude and latitude in the location information can be used as the accuracy value. If the number of decimal places is greater than or equal to 5, it is considered that the positioning accuracy meets the first preprocessing condition requirement and the GPS data point is valid. When the number of decimal places is less than 5, it is considered that the positioning accuracy does not meet the first preprocessing condition requirement and the GPS data point is invalid. This can also achieve accuracy filtering of GPS data points.

[0055] 2. Time filtering.

[0056] A time difference check is performed based on the time of the GPS data point and the current standard time, and the GPS data points whose time difference meets the second preprocessing condition are screened out. The time of the GPS data point can be the time point at which each specific information in the GPS data point is collected, that is, the positioning time. The current standard time can be any time information that can be used as a judgment standard. For example, in this embodiment, the server time can be used as the current standard time. The second preprocessing condition can be set based on the difference between the time of the GPS data point and the current standard time. Thus, the difference between the positioning time of the GPS data point and the server time is judged. If the difference exceeds a set threshold (such as 1 hour), the GPS data point is considered invalid. If the difference does not exceed the set threshold, the GPS data point is considered valid, thereby screening out the GPS data points whose time difference meets the second preprocessing condition.

[0057] 3. Repeated filtering of data points.

[0058] By comparing the time of the GPS data point with the time of the previous GPS data point, the GPS data points whose time difference satisfies the third preprocessing condition are screened out. The third preprocessing condition can be set based on the time difference between the two GPS data points before and after. For example, in this embodiment, the positioning time of the currently collected GPS data point is compared with the positioning time of the previous GPS data point. If it is less than or equal to the positioning time of the previous GPS data point, the GPS data point is considered invalid. If it is greater than the positioning time of the previous GPS data point, the GPS data point is considered valid, thereby screening out the GPS data points whose time difference satisfies the third preprocessing condition.

[0059] 4. Speed ​​filtering.

[0060] Obtain the speed information of the GPS data point, and filter out the GPS data points whose speed information meets the fourth preprocessing condition. When obtaining the speed information of the GPS data point, if some GPS data acquisition equipment can directly detect the speed information, the speed information can be directly obtained from the GPS data point in this solution, and then judged based on the fourth preprocessing condition. For example, the fourth preprocessing condition can be set as a threshold value for speed. If the speed information of the GPS data point is greater than the threshold (such as 40 meters / second), it is considered that the change in speed exceeds a reasonable range, and the GPS data point is judged to be invalid. If the speed information of the GPS data point is less than or equal to the threshold, it is considered that the change in speed is within a reasonable range, and the GPS data point is judged to be valid, thereby filtering out the GPS data points whose time difference meets the fourth preprocessing condition.

[0061] In addition, in actual scenarios, if some GPS data collection devices cannot directly detect speed information, the corresponding speed information can be calculated using the location information and time information of the GPS data point. For example, in this embodiment, the location of the currently collected GPS data point and the location of the previous GPS data point can be used to calculate the distance between the two, and the time difference between the two can be calculated, thereby calculating the speed information as the speed information of the GPS data point, and then judging whether the fourth preprocessing condition is met to achieve preprocessing of speed filtering.

[0062] Through the above-mentioned preprocessing of GPS data, the validity of the data can be effectively improved, and invalid data that may cause errors in the processing results can be eliminated, making the detection results of driving behavior more accurate.

[0063] Step S102, calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data.

[0064] The yaw rate refers to the change in the vehicle heading per unit time, which can be calculated based on the heading difference between consecutive GPS data points and the time difference between GPS data points. The specific calculation formula can be as follows:

[0065] Yaw rate = (C1-C2) / (T1-T2)

[0066] Among them, C1 is the heading of the current GPS data point, C2 is the heading of the previous GPS data point, T1 is the time of the current GPS data point, and T2 is the time of the previous GPS data point.

[0067] In some embodiments of the present application, in order to further improve the accuracy of the detection results, after calculating the yaw rate corresponding to the current GPS data point based on the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, a turning and U-turn exclusion mechanism can be added to confirm that the vehicle is not in a turning or U-turn driving state. Therefore, during the detection process, if the vehicle has turned or turned when collecting the current GPS data point, these behaviors can be automatically excluded to avoid mistakenly judging the turning or U-turn driving behavior as the behavior of cutting in.

[0068] In actual scenarios, the yaw rate can be used to implement the turning and U-turn exclusion mechanism. For example, after calculating the yaw rate corresponding to the current GPS data point based on the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, the yaw rate can be compared with a preset threshold (such as 30 degrees / second). If the yaw rate is greater than 30 degrees / second, it is considered that the vehicle is turning or turning, rather than changing lanes, that is, it is in a turning and U-turn driving state. If the yaw rate is less than or equal to 30 degrees / second, it is confirmed that the vehicle is not in a turning and U-turn driving state.

[0069] Step S103, determining whether the yaw rate is within a preset first threshold interval, if the yaw rate is within the first threshold interval, calculating a speed change value corresponding to the current GPS data point according to a speed difference between two most recent consecutive GPS data points in the GPS data.

[0070] In the solution of this embodiment, by analyzing the yaw rate of the GPS data point, it can be confirmed whether the vehicle has preliminary signs of cutting in. Specifically, the yaw rate can be compared with a preset first threshold interval to determine whether the yaw rate is within the preset first threshold interval. For example, in an actual scenario, the first threshold interval can be set to be lower than 45 degrees / second. If the yaw rate is within the first threshold interval, it is considered that there are preliminary signs of cutting in. At this time, the speed change value corresponding to the current GPS data point can be further calculated based on the speed difference between the two most recent consecutive GPS data points in the GPS data, and then the speed change value can be used to make further judgments.

[0071] Step S104, determining whether the speed change value exceeds the lane-hopping deceleration threshold; if the speed change value exceeds the lane-hopping deceleration threshold, determining the current GPS data point as a suspected lane-hopping data point, and continuously acquiring GPS data points within the first time window after the suspected lane-hopping data point.

[0072] In actual scenarios, since vehicles generally slow down during the process of jamming, further detection can be achieved using the speed change value corresponding to the current GPS data point. In this solution, after using the yaw rate to identify the initial signs of jamming, the speed change value can be calculated and compared with the jamming deceleration threshold to determine whether the speed change value exceeds the jamming deceleration threshold. If the speed change value exceeds the jamming deceleration threshold, it means that the vehicle has a certain degree of deceleration, so the current GPS data point can be determined as a suspected jamming data point and added to the list to be confirmed. Otherwise, if the speed change value does not exceed the jamming deceleration threshold, it does not conform to the normal driving habits of the vehicle when jamming, so the current GPS data point can be excluded and not used as a suspected jamming data point. After completing the speed change judgment, for the suspected jamming data points in the list to be confirmed, the GPS data points in the first time window after the suspected jamming data point can be continuously obtained, thereby waiting for future GPS data for detection, and further improving the accuracy of detection.

[0073] Step S105, while continuously acquiring the GPS data points in the first time window after the suspected lane-cutting data point, determine whether each GPS data point in the first time window is a suspected lane-cutting data point; if the number of suspected lane-cutting data points in the GPS data points in the first time window reaches the lane-cutting determination threshold, identify that the vehicle has cut in.

[0074] The first time window is the time window for further detection, and its length can be set according to the needs of the actual scene. For example, in this embodiment, the first time window can be set to 10 seconds, that is, after the suspected jam data point, continue to obtain GPS data points within 10 seconds, and for each GPS data point within these 10 seconds, the method in the aforementioned steps S102 to S104 can be used to determine whether it is a suspected jam data point, and the number of suspected jam data points can be recorded.

[0075] For example, in this embodiment, 20 GPS data points are continuously acquired in the first time window. After the 20 GPS data points are processed in the manner of steps S102 to S104, 6 suspected jamming data points are detected. If the jamming determination threshold is set to 5, it can be determined that the number of suspected loading data points in the GPS data points in the first time window has exceeded the jamming determination threshold, and it is recognized that the vehicle has jammed.

[0076] It can be seen that the main innovation of this solution is to use the vehicle's GPS data heading changes and speed changes to calculate the vehicle's yaw rate and deceleration during driving, and use this to perform preliminary detection of the vehicle's jamming behavior. Compared with the existing detection scheme that only relies on speed or position changes, it is more accurate and avoids misjudgment caused by other factors. At the same time, on the basis of obtaining preliminary detection results, a future data confirmation mechanism is adopted to further confirm the suspected jamming situation using GPS data in the first time window in the future, avoiding misjudgment caused by yaw rate and speed fluctuations at a single moment, and significantly improving the recognition accuracy of jamming behavior.

[0077] In some embodiments of the present application, the vehicle driving behavior detection method can also detect frequent lane change behaviors. The specific scheme is as follows: First, the lane change behavior can be detected by the yaw rate and the vehicle speed. That is, after calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, it is determined whether the yaw rate is within the preset second threshold interval and the vehicle speed is greater than the lane change speed threshold. If the yaw rate is within the preset second threshold interval and the vehicle speed is greater than the lane change speed threshold, it is identified that the vehicle has changed lanes. For example, the second threshold interval can be set to an interval greater than a certain value, such as 10 degrees / second, and the lane change speed threshold can also be set to a suitable value, such as 20km / h. Therefore, when it is detected that the yaw rate is greater than 10 degrees / second and the vehicle speed is greater than a certain 20km / h, it can be considered that the vehicle has changed lanes.

[0078] Then, the number of lane changes of the vehicle within the second time window can be further detected. If the number of lane changes reaches the frequent lane change determination threshold, and the cumulative heading change within the second time window is less than the heading change threshold, the vehicle is identified as having frequent lane changes. Among them, the second time window, the frequent lane change determination threshold, and the heading change threshold can all be set according to the requirements of the actual application scenario. For example, if the second time window in this embodiment is set to 15 seconds, the frequent lane change determination threshold is set to 3 times, and the heading change threshold is set to 45 degrees, it means that when the vehicle is detected to have changed lanes 3 times within a 15-second time window, and the cumulative heading change during this period is less than 45 degrees, it is considered that the vehicle has changed lanes frequently.

[0079] When identifying the vehicle's lane change behavior, in order to improve accuracy, a turning and U-turn exclusion mechanism can also be introduced. Thus, after calculating the yaw rate corresponding to the current GPS data point based on the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, it can be confirmed that the vehicle is not in a turning or U-turn driving state, so that during the detection process, the vehicle's turning and U-turn behaviors can be automatically excluded, avoiding the mistaken identification of turning or U-turn driving behaviors as lane change behaviors.

[0080] It can be seen that this solution has at least the following innovations when performing frequent lane change detection: This solution can accurately determine whether the vehicle has changed lanes by analyzing the heading changes of continuous GPS data points and combining them with the vehicle speed. In the lane change detection process, a mechanism for excluding turning and U-turning behaviors is introduced to avoid erroneous judgments and improve the accuracy of detection. Frequent lane changes are judged by detecting the number of lane changes within a specific time window and combining them with the cumulative heading changes, which effectively avoids misjudgments and improves the stability of detection. In addition, when frequent lane changes are detected, an alarm can be generated in a timely manner, and relevant data can be recorded and marked to facilitate subsequent analysis and processing.

[0081] In some embodiments of the present application, the vehicle driving behavior detection method can also realize the detection of sudden acceleration behavior and sudden deceleration behavior. The specific scheme is as follows: after obtaining the GPS data of the vehicle, the acceleration corresponding to the current GPS data point can be calculated based on the speed difference and time difference between the two most recent consecutive GPS data points in the GPS data.

[0082] The acceleration can be calculated based on the speed difference between consecutive GPS data points combined with the time difference between GPS data points. The specific calculation formula can be as follows:

[0083] Acceleration = (S1-S2) / (T1-T2)

[0084] Among them, S1 is the speed of the current GPS data point, S2 is the speed of the previous GPS data point, T1 is the time of the current GPS data point, and T2 is the time of the previous GPS data point.

[0085] It is determined whether a sudden acceleration detection condition or a sudden deceleration detection condition is satisfied according to the acceleration; if the sudden acceleration detection condition or the sudden deceleration detection condition is satisfied, it is identified that the vehicle has a sudden acceleration behavior or a sudden deceleration behavior.

[0086] Among them, the sudden acceleration detection conditions include the following points: a. The acceleration is greater than the sudden acceleration threshold; b. The duration of the state where the acceleration is greater than the sudden acceleration threshold exceeds the sudden acceleration duration threshold; c. The time interval from the last time the sudden acceleration behavior was identified exceeds the first time interval. When the above three points are met, it can be identified that the vehicle has undergone sudden acceleration. For example, in an actual scenario, when it is detected that the acceleration of the vehicle is greater than the sudden acceleration threshold, it can be preliminarily considered that the vehicle has begun to accelerate suddenly; if the duration of the state where the acceleration is greater than the sudden acceleration threshold exceeds the set sudden acceleration duration threshold, it is confirmed that the vehicle is accelerating suddenly. Therefore, when it is further detected that the time interval from the last time the sudden acceleration behavior was identified exceeds the first time interval, it can be determined that the sudden acceleration detected this time is a new sudden acceleration behavior, thereby accurately detecting the sudden acceleration behavior of the vehicle.

[0087] Similarly, the sudden deceleration detection conditions may include the following points: a. The acceleration is less than the sudden deceleration threshold; b. The duration of the state where the acceleration is less than the sudden deceleration threshold exceeds the sudden deceleration duration threshold; c. The time interval from the last time the sudden deceleration behavior was identified exceeds the second time interval. When it is detected that the acceleration of the vehicle is less than the sudden acceleration threshold, it can be preliminarily considered that the vehicle has begun to accelerate suddenly. In actual scenarios, since the acceleration of the vehicle when decelerating is a negative value, a negative sudden acceleration threshold can be set. When the acceleration of the vehicle is less than the sudden acceleration threshold, it means that the vehicle is decelerating at a speed change rate exceeding a certain degree, so it can be preliminarily considered that the vehicle has begun to accelerate suddenly. On this basis, if the duration of the state where the acceleration is less than the sudden deceleration threshold exceeds the sudden deceleration duration threshold, it can be confirmed that the vehicle is accelerating suddenly. At this time, if it is further detected that the time interval from the last time the sudden deceleration behavior was identified exceeds the second time interval, it can be determined that the sudden deceleration detected this time is a new sudden deceleration behavior, thereby accurately detecting the sudden deceleration behavior of the vehicle.

[0088] It can be seen that this solution has at least the following innovations when performing sudden acceleration and deceleration detection: judging sudden acceleration and deceleration behaviors by acceleration rather than relying solely on simple speed differences can more accurately reflect the dynamic characteristics of driving behavior, and by setting the sudden acceleration duration threshold and the sudden deceleration duration threshold, the impact of short-term sudden acceleration changes on the detection results is avoided, thereby improving the accuracy of the detection. By setting the first time interval and the second time interval, it is ensured that there is enough time interval between each detection and the last behavior detection, avoiding repeated identification of a sudden acceleration or deceleration behavior, and improving the stability of the system.

[0089] In some embodiments of the present application, the vehicle driving behavior detection method can also realize the detection of sharp turn behavior. The specific scheme is as follows: after calculating the yaw rate corresponding to the current GPS data point based on the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, it can be determined whether the yaw rate is within a preset third threshold range and the vehicle speed is greater than the sharp turn speed threshold. If the yaw rate is within the preset third threshold range and the vehicle speed is greater than the sharp turn speed threshold, it is identified that the vehicle may make a sharp turn.

[0090] The third threshold interval and the sharp turn speed threshold can also be set according to the requirements of the actual application scenario. For example, the third threshold interval can be set to an interval greater than a certain value, such as 20 degrees / second, and the sharp turn speed threshold can be set to 10km / h. Therefore, when it is detected that the yaw rate is greater than 20 degrees / second and the vehicle speed is greater than a certain 10km / h, it can be considered that the vehicle may make a sharp turn.

[0091] On this basis, the number of times the vehicle is continuously identified as possibly making a sharp turn can be detected, and the possible sharp turn behavior initially identified can be further confirmed. If the sharp turn detection threshold is exceeded and the time interval from the last sharp turn behavior identified exceeds the third time interval, the sharp turn behavior of the vehicle is identified. For example, when detection is performed based on several consecutive GPS data points and the vehicle is identified as possibly making a sharp turn, the number of times the vehicle is continuously identified as possibly making a sharp turn can be recorded, and the number can be compared with the pre-set sharp turn detection threshold (such as 3 times). When it exceeds 3 times, it can be determined whether the third time interval has been exceeded from the last sharp turn behavior identified, thereby avoiding repeated identification of the same sharp turn behavior, increasing the accuracy of the judgment, and effectively reducing false detections.

[0092] In some embodiments of the present application, the vehicle driving behavior detection method can also detect the behavior of turning right without stopping. The specific scheme is as follows: determine whether the yaw rate is within the preset fourth threshold interval and the vehicle speed is greater than the right turn speed threshold. If the yaw rate is within the preset fourth threshold interval and the vehicle speed is greater than the right turn speed threshold, identify that the vehicle has turned right. For example, when the yaw rate is within the range corresponding to a certain fourth threshold interval and the vehicle speed is greater than the set value corresponding to the right turn speed threshold, it can be determined that the right turn behavior is currently detected. In order to further improve the accuracy of the detection, during the right turn process, the cumulative yaw rate change can be continuously obtained, and it can be determined whether it exceeds the set right turn yaw threshold.

[0093] After determining that the vehicle has started to turn right, it is possible to detect whether the vehicle has stopped during the right turn according to the vehicle speed. If the vehicle has not stopped and the duration of the right turn exceeds a preset time, it is identified that the vehicle has turned right without stopping.

[0094] Among them, the judgment of whether the parking behavior occurs can be realized based on whether the vehicle speed drops below a certain threshold value during the right turn behavior and lasts for a preset time. For example, when the vehicle speed drops below 3km / h during the right turn behavior and lasts for more than 2 seconds, it can be determined that the vehicle has stopped during the right turn behavior. Otherwise, it is considered that the vehicle has not been detected to have stopped during the right turn. At this time, it can be further determined that the duration of the right turn behavior exceeds the preset time. If it exceeds the preset time, it can be finally confirmed that the right turn without stopping behavior has been identified. Therefore, the scheme of the embodiment of the present application can accurately judge the right turn without stopping behavior and reduce the possibility of misjudgment by introducing multiple conditions such as the duration of the right turn behavior, the accumulated heading change, and the parking judgment.

[0095] Based on the same inventive concept, a vehicle driving behavior detection device is also provided in an embodiment of the present application, and the method corresponding to the device is the vehicle driving behavior detection method in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The vehicle driving behavior detection device provided in an embodiment of the present application includes a memory for storing computer program instructions and a processor for executing computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to implement the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0096] The specific implementation of the device may include a network device, or a device formed by integrating a user device and a network device through a network, or it may also be an application running on the above device. The user device includes but is not limited to computers, mobile phones, tablet computers, and various types of vehicle-mounted terminal devices; the network device includes but is not limited to network hosts, single network servers, servers concentrated in multiple network servers, or servers in a distributed cloud network. The distributed cloud network described here is composed of a large number of hosts or network servers based on cloud computing.

[0097] In particular, the methods and / or embodiments in the embodiments of the present application may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. When the computer program is executed by the processing unit, the above functions defined in the method of the present application are executed.

[0098] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0099] In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0100] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] As another aspect, the present application further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer program instructions, which may be executed by a processor to implement the methods and / or technical solutions of the above multiple embodiments of the present application.

[0103] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0104] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to represent names, and do not represent any specific order. The numerical order of the serial numbers corresponding to the steps does not represent any specific execution order, and each step can be executed in any order combination under the premise of conforming to the execution logic.

Claims

1. A vehicle driving behavior detection method, characterized in that: The method comprises: Get the vehicle's GPS data; Calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data; Determine whether the yaw rate is within a preset first threshold interval, and if the yaw rate is within the first threshold interval, calculate a speed change value corresponding to a current GPS data point according to a speed difference between two most recent consecutive GPS data points in the GPS data; Determine whether the speed change value exceeds a lane-crossing deceleration threshold, and if the speed change value exceeds the lane-crossing deceleration threshold, determine the current GPS data point as a suspected lane-crossing data point, and continue to acquire GPS data points within a first time window after the suspected lane-crossing data point; In the process of continuously acquiring GPS data points in a first time window after the suspected traffic jam data point, determining whether each GPS data point in the first time window is a suspected traffic jam data point; If the number of suspected loading data points in the GPS data points within the first time window reaches the jamming determination threshold, it is identified that the vehicle is jamming.

2. The method according to claim 1, characterized in that After calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes: determining whether the yaw rate is within a preset second threshold interval and the vehicle speed is greater than a lane-changing speed threshold, and if the yaw rate is within the preset second threshold interval and the vehicle speed is greater than the lane-changing speed threshold, identifying that the vehicle has changed lanes; The number of lane changes of the vehicle within a second time window is detected. If the number of lane changes reaches a frequent lane change determination threshold and the accumulated heading change within the second time window is less than a heading change threshold, it is identified that the vehicle has undergone frequent lane changes.

3. The method according to claim 1 or 2, characterized in that: After calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes: Confirm that the vehicle is not in a turning or U-turn state.

4. The method according to claim 1, characterized in that: After obtaining the vehicle's GPS data, it also includes: Calculate the acceleration corresponding to the current GPS data point based on the speed difference and time difference between the two most recent consecutive GPS data points in the GPS data; Determining whether a sudden acceleration detection condition or a sudden deceleration detection condition is satisfied according to the acceleration, and if the sudden acceleration detection condition or the sudden deceleration detection condition is satisfied, identifying that the vehicle has a sudden acceleration behavior or a sudden deceleration behavior; The sudden acceleration detection condition includes: the acceleration is greater than the sudden acceleration threshold, the duration of the state where the acceleration is greater than the sudden acceleration threshold exceeds the sudden acceleration duration threshold, and the time interval from the last recognition of the sudden acceleration behavior exceeds the first time interval; The sudden deceleration detection condition includes: the acceleration is less than the sudden deceleration threshold, the duration of the state where the acceleration is less than the sudden deceleration threshold exceeds the sudden deceleration duration threshold, and the time interval from the last recognition of the sudden deceleration behavior exceeds the second time interval.

5. The method according to claim 1, characterized in that After calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes: determining whether the yaw rate is within a preset third threshold interval and the vehicle speed is greater than a sharp turn speed threshold, and if the yaw rate is within the preset third threshold interval and the vehicle speed is greater than the sharp turn speed threshold, identifying that the vehicle may make a sharp turn; The number of times that the vehicle may make a sharp turn is detected continuously, and if it exceeds a sharp turn detection threshold and the time interval from the last sharp turn behavior is more than a third time interval, the sharp turn behavior of the vehicle is identified.

6. The method according to claim 1, characterized in that After calculating the yaw rate corresponding to the current GPS data point according to the heading difference and time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes: determining whether the yaw rate is within a preset fourth threshold interval and the vehicle speed is greater than a right turn speed threshold, and if the yaw rate is within the preset fourth threshold interval and the vehicle speed is greater than the right turn speed threshold, identifying that the vehicle is turning right; detecting, according to the vehicle speed, whether the vehicle stops during the right turn; If no parking behavior occurs and the duration of the right turn behavior exceeds a preset time length, it is identified that the vehicle turns right without stopping.

7. The method according to claim 1, characterized in that Before calculating the yaw rate corresponding to the current GPS data point according to the heading difference and the time difference between the two most recent consecutive GPS data points in the GPS data, the method further includes: The GPS data is preprocessed.

8. The method according to claim 7, characterized in that The pre-processing method includes at least one of the following: Perform accuracy filtering according to the positioning accuracy of the GPS data points, and select the GPS data points whose positioning accuracy meets the first preprocessing condition requirement; Perform time difference verification based on the time of the GPS data point and the current standard time, and select the GPS data points whose time difference meets the second preprocessing condition; Comparing the time of the GPS data point with the time of the previous GPS data point, filtering out the GPS data points whose time difference satisfies the third preprocessing condition; The speed information of the GPS data points is acquired, and the GPS data points whose speed information meets the fourth preprocessing condition are screened out.

9. A vehicle driving behavior detection device, the device comprising a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein: When the computer program instructions are executed by the processor, the device is triggered to execute the method according to any one of claims 1 to 8.

10. A computer readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images