CN117876976A - Abnormal driving behavior identification method and system based on vehicle and road side perception data - Google Patents
Abnormal driving behavior identification method and system based on vehicle and road side perception data Download PDFInfo
- Publication number
- CN117876976A CN117876976A CN202311844826.1A CN202311844826A CN117876976A CN 117876976 A CN117876976 A CN 117876976A CN 202311844826 A CN202311844826 A CN 202311844826A CN 117876976 A CN117876976 A CN 117876976A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- abnormal driving
- time
- abnormal
- driving behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000008447 perception Effects 0.000 title claims abstract description 16
- 230000006399 behavior Effects 0.000 claims abstract description 57
- 230000008451 emotion Effects 0.000 claims abstract description 8
- 230000005856 abnormality Effects 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 18
- 230000001133 acceleration Effects 0.000 claims description 10
- 230000003111 delayed effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 4
- 230000035484 reaction time Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 241000497429 Obus Species 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Abstract
The invention provides a method and a system for identifying abnormal driving behaviors based on vehicle and road side perception data. The abnormal driving behavior recognition method comprises the following steps: in each control period, the OBU reports vehicle information to the cloud control platform in real time; the cloud control platform obtains abnormal driving scores of each vehicle based on vehicle information; the road side sensing equipment uploads a vehicle image; the cloud control platform screens out a driver image, and the driver image is processed to obtain a driver state category, wherein the abnormality comprises drunk driving, fatigue, emotion abnormality and inattention; determining whether an abnormal driving behavior exists for each vehicle in combination with the abnormal driving score and the driver status category of the vehicle. The abnormal driving score and the driver state category are combined to judge, so that the accuracy of abnormal driving behavior identification is improved, the real-time performance of abnormal driving behavior identification is improved by utilizing the strong computing capability of the cloud control center, and a plurality of abnormal driving vehicles in the road network can be identified simultaneously.
Description
Technical Field
The invention relates to the technical field of driving behavior analysis, in particular to a method and a system for identifying abnormal driving behaviors based on vehicle and road side perception data.
Background
In recent years, with the rapid development of social economy, the number of automobiles is exponentially increased, and more abnormal driving behaviors are generated, wherein the abnormal driving behaviors comprise drunk driving, fatigue driving, distraction (answering a call while driving, playing a mobile phone and the like), emotional driving and the like, and the abnormal driving behaviors cause more and more traffic accidents, so that the driving behaviors of a driver are monitored and warned, and the occurrence of traffic accident conditions can be effectively reduced.
In the prior art, as disclosed in chinese patent publication No. CN116142063a, an output system of dangerous driving state of an automobile is disclosed, and as disclosed in chinese patent publication No. CN116141963a, a vehicle-mounted alcohol detection method and detection system are disclosed, which all rely on the inside of the automobile to identify abnormal driving behavior. The mode needs the car owner to install the related sensor in a matching way, and is not easy to popularize. Also, some intelligent algorithms require a strong computational effort, which the onboard processor cannot provide.
Along with the development of the vehicle-road collaborative technology, road side sensing equipment is arranged on the road side, an on-board unit (OBU) which is communicated with the cloud control platform is arranged on the vehicle, and the road side sensing equipment synchronously sends the road side information sensed by the road side sensing equipment to the cloud control platform and the vehicle through a V2X technology. However, the road side sensing device cannot collect each vehicle in real time, and the quality of the photographed image is greatly affected by weather, so that the abnormal driving behavior is identified only based on the road side sensing data, and the limitation exists although the powerful operation capability of the cloud control center can be utilized.
Disclosure of Invention
The invention aims to solve the technical problems in the prior art and provides a method and a system for identifying abnormal driving behaviors based on vehicle and road side perception data.
In order to achieve the above object of the present invention, according to a first aspect of the present invention, there is provided an abnormal driving behavior recognition method based on vehicle and roadside awareness data, in each control period, performing: 0BU reports vehicle information to a cloud control platform in real time, wherein the vehicle information comprises position information, vehicle speed, steering wheel rotation angle, front vehicle distance, time tag and vehicle ID; the cloud control platform obtains abnormal driving scores of each vehicle based on the acquired vehicle information of each vehicle; the road side sensing equipment shoots a vehicle image and uploads the vehicle image to the cloud control platform; the cloud control platform screens out a driver image containing a driver, and performs recognition processing on the driver image to obtain a driver state category, wherein the driver state category comprises normal and abnormal states, and the abnormal states comprise drunk driving, fatigue, emotion abnormality and inattention; determining whether an abnormal driving behavior exists for each vehicle in combination with the abnormal driving score and the driver status category of the vehicle.
In order to achieve the above object of the present invention, according to a second aspect of the present invention, there is provided a traffic safety management system based on the abnormal driving behavior recognition method based on the vehicle and the road side perception data according to the first aspect of the present invention, which includes a cloud control platform, a road side perception device, and 0BU of the vehicle in the road network, wherein the cloud control platform is respectively connected and communicated with the road side perception device and the 0BU.
According to the technical scheme, the cloud control platform obtains the abnormal driving score of the vehicle by using the vehicle information uploaded by 0BU, obtains the driver state type by using the image shot by the road side sensing equipment, combines the abnormal driving score and the driver state type to judge, and can improve the accuracy of abnormal driving behavior identification.
Drawings
FIG. 1 is a flow chart of a method for identifying abnormal driving behavior based on vehicle and roadside awareness data in a preferred embodiment of the present invention;
fig. 2 is a system block diagram of a traffic safety management system in accordance with a preferred embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and defined, it should be noted that the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, mechanical or electrical, or may be in communication with each other between two elements, directly or indirectly through intermediaries, as would be understood by those skilled in the art, in view of the specific meaning of the terms described above.
The invention discloses an abnormal driving behavior identification method based on vehicle and road side perception data, in a preferred embodiment, in each control period, as shown in fig. 1, the method comprises the following steps:
step S1, reporting vehicle information to a cloud control platform in real time by 0BU, wherein the vehicle information comprises position information, vehicle speed, steering wheel corner, front vehicle distance, time tag and vehicle ID.
The 0BU can report the vehicle information at regular time, and the reporting frequency can be 1 s/time, 2 s/time and 3 s/time … … s/time. The time attribute of the vehicle information can be obtained by the time tag, and the spatial position attribute of the vehicle information can be obtained by the position information. The time tag can be the acquisition time of position information, vehicle speed, steering wheel rotation angle, front vehicle distance or the reporting time of vehicle information. The vehicle ID is preferably, but not limited to, a license plate number of the vehicle. The position information can be obtained through a vehicle-mounted GPS positioning module, the speed of the vehicle and the steering wheel rotation angle can be collected through a vehicle-mounted sensor, and the distance between the front vehicle and the vehicle can be measured through a vehicle-mounted radar.
Step S2, the cloud control platform obtains abnormal driving scores of each vehicle based on the acquired vehicle information of each vehicle;
s3, the road side sensing equipment shoots a vehicle image and uploads the vehicle image to the cloud control platform; the cloud control platform screens out a driver image containing a driver, and performs recognition processing on the driver image to obtain a driver state category, wherein the driver state category comprises normal and abnormal states, and the abnormal states comprise drunk driving, fatigue, emotion abnormality and inattention; emotional anomalies include anger and sadness. Inattention refers to the actions of opening a small difference, looking at a mobile phone, speaking, etc.
Step S4, determining whether the abnormal driving behavior exists in the vehicle according to the abnormal driving score and the driver state category of each vehicle.
In this embodiment, as the OBU of the vehicle continuously reports the information of the vehicle, the cloud control platform stores more and more vehicle information, and at the same time, the cloud control platform obtains an abnormal driving score of each vehicle based on the obtained vehicle information of each vehicle, specifically: obtaining the number of non-accident speed changes, the number of sudden lane changes, the number of too small vehicle distance before and the number of delayed green light starting of each vehicle; and summing up and calculating the number of the non-accident speed changes, the number of sudden lane changes, the number of the too small vehicle distance and the number of the delayed green light starting times of each vehicle to obtain the abnormal driving score of the vehicle.
In this embodiment, the non-failure speed change refers to the behavior of the driver to accelerate or decelerate at will on the premise of not waiting for a traffic light or suddenly stopping the vehicle ahead or no accident ahead, the risk of collision with the vehicle ahead exists in the random acceleration, the risk of collision caused by the fact that the vehicle behind is not braked in time exists in the random deceleration, and the non-failure speed change is a dangerous driving behavior, and many causes of the non-failure speed change are possible, for example, the driver is out of emotion, is not concentrated in attention, has insufficient experience, is tired, is uncomfortable in body, and is drunk driving and the like.
The sudden lane change refers to sudden large-amplitude turning at a non-turning intersection, and can be judged by exceeding a threshold value by the steering wheel angle, and the sudden lane change can bring collision risks to vehicles behind and obliquely behind, and is also dangerous driving behavior, and drunk driving, inattention, out of concentration of emotion, uncomfortable feeling and the like are all possibly caused.
The safe driving of the vehicle on the road needs to keep a safe distance from the front vehicle so as not to collide, and therefore, too small distance from the front vehicle means that the distance from the front vehicle is smaller than the safe distance in the corresponding scene. The problem of too small distance between vehicles before the driver is possibly caused by out-of-control emotion, insufficient experience, fatigue, drunk driving and inattention of the driver.
The delayed start of the green light is that the green light should be started or started along with the front vehicle when the green light is on at a traffic light intersection, but the green light is not started in time, and the delayed start of the green light is likely to occur when a driver is tired, distracted and drunk driving.
Therefore, the invention can effectively show whether the vehicle has abnormal driving behaviors such as fatigue driving, incontrollable emotion, drunk driving, inattention and the like by adding up the number of times of unoccupied speed change, abrupt lane change, too small vehicle distance and green light lag starting times.
In this embodiment, the road side sensing device is preferably, but not limited to, a camera, which shoots toward the coming vehicle direction, so as to better shoot the driver's image. The road side sensing equipment sends the shot video and the corresponding shooting time to the cloud control platform, and the cloud control platform carries out framing processing on the shot video, and each frame of image corresponds to the shooting time. The human body recognition model which is trained in advance can be utilized to recognize the driver, the human body recognition model is utilized to recognize each frame of vehicle image, the vehicle image which can recognize the human body is screened out and used as the driver image, and the human body recognition model can be selected from the YOLO v7 network model, which is not described in detail in the prior art. And determining the corresponding relation between the driver image and the vehicle according to the position information of the road side sensing equipment, the vehicle position information, the time tag, the image shooting time and the like.
In this embodiment, the cloud control platform is preset with a plurality of driver state recognition models, including a drunk driving recognition model, a fatigue recognition model, a behavior recognition model (recognition of behavior without concentration), and a emotion recognition model. The drunk driving recognition model is preferably but not limited to the technical scheme disclosed in the patent with publication number CN106571033A, and the fatigue recognition model can refer to the technical scheme disclosed in the patent with publication number CN 106781282A. The behavior recognition model can refer to the technical scheme disclosed in the patent with the publication number of CN112270277A, CN 108446645A. The emotion recognition model can refer to the technical scheme disclosed in the patent with the publication number of CN116453195A, CN 106650633A.
In this embodiment, the cloud control platform continuously receives the vehicle information uploaded by each vehicle OBU, and obtains the abnormal driving score of each vehicle according to the received vehicle information of the current driving of each vehicle in each control period. The number of driving times is divided by an interval of the vehicle stop time being greater than 1 hour or 2 hours, and the interval between the start time of the present driving and the end time of the last driving is 1 hour or two hours.
In the present embodiment, the method for obtaining the number of times of the non-accident shift of the entire vehicle i is as follows:
step A1, extracting the speed data of continuous driving segments from the existing speed data of the vehicle i; a continuous driving segment refers to a section of road that travels from green light start to red light stop waiting, and may include one or more continuous driving segments during the traveled journey of vehicle i.
Step A2, traversing each continuous driving section of the vehicle i, and obtaining the number of times of non-fault speed change of the vehicle i in each continuous driving section: calculating the acceleration of the vehicle i based on the vehicle speed data of the vehicle i in the nth consecutive driving segment, if any: i a ijt -a i′(j+Δj)t If the I is more than or equal to deltaa, the vehicle i is considered to have 1 non-fault speed change at the position j at the time t, wherein a ijt Acceleration, a, of vehicle i at position j at time t i′(j+Δj)t Representing the acceleration of vehicle i 'in the range of j + deltaj position in front of vehicle i at time t, preferably vehicle i' represents a vehicle in the range of 5-10 meters in front of vehicle i; Δa represents a preset acceleration difference threshold, which may be empirically set, or the difference between the maximum acceleration and the minimum acceleration of a plurality of normally driven vehicles on consecutive driving segments; i. n and i' are both positive integers; by the above determination, it is possible to eliminate erroneous determination by the shift of the vehicle i due to the shift of the preceding vehicle or by the overall change (obstacle) of the road environment, and to more accurately recognize the non-defective shift.
And A3, accumulating the number of times of the non-reason speed change of the vehicle i in all continuous driving sections of the vehicle i to obtain the number of times of the non-reason speed change of the whole vehicle i.
In the present embodiment, preferably, the method for acquiring the burst transition number of the whole vehicle i is as follows:
and B1, extracting steering wheel angle data of continuous driving segments from the steering wheel angle data of the vehicle i.
Step B2, traversing each continuous driving section of the vehicle i, and obtaining the non-fault transition number of the vehicle i in each continuous driving section: for the nth continuous driving section, if the steering wheel angle of the vehicle i at the position j at the time t is larger than or equal to the steering angle threshold value, and the steering wheel angles of the vehicles at the left front, the front and the right front of the vehicle i at the time t are smaller than the steering angle threshold value, the vehicle i at the position j at the time t is considered to suddenly change the road for 1 time; the steering angle threshold may be empirically set or a steering wheel angle maximum for a plurality of normal vehicles on successive driving segments.
And B3, accumulating the non-fault variable pass numbers of the vehicle i in all continuous driving sections to obtain the non-fault variable pass numbers of the whole vehicle i.
In the present embodiment, preferably, the method for acquiring the number of times that the preceding vehicle distance of the vehicle i is excessively small is as follows:
step C1, acquiring safe front vehicle distances at different time points based on the vehicle speed of the vehicle i at different time points and the front vehicle speed, and if the front vehicle distance of the vehicle i at time t is smaller than the safe front vehicle distance corresponding to the time t, considering that the front vehicle distance of the vehicle i at the time t is too small;
and C2, counting the number of continuous time segments of the vehicle i with the too small front vehicle distance in the travel, and taking the number of continuous time segments as the times of the too small front vehicle distance of the vehicle i.
In this embodiment, the safe front vehicle distance is the minimum vehicle distance that the vehicle i does not collide with the front vehicle when braking even after the front vehicle suddenly brakes. A continuous time segment refers to a continuous time range from a distance from the front of the vehicle i that is less than the safe front distance (i.e., the front distance is too small) to a distance from the front of the vehicle i that is not less than the safe front distance (i.e., the front distance is too small and disappears), and the next continuous time segment is entered when the front distance is too small again.
In this embodiment, the method for obtaining the number of times of green light lag start of the vehicle i is:
and D1, extracting speed data of the vehicle i passing through traffic light segments from vehicle information of the vehicle i. Traffic light segmentation refers to the period of time from when vehicle i is parked waiting for a red light to when a green light passes through a traffic intersection.
Step D2, regarding the mth traffic light segment of the vehicle i, when the vehicle i is the first traffic light to pass through, if the starting time of the vehicle i is later than the green light lighting time and the time difference between the starting time of the vehicle i and the green light lighting time is greater than the preset reaction duration, the vehicle i is considered to have green light lag starting in the mth traffic light segment; when the vehicle i is not the first green light passing vehicle, if the vehicle i is started later than the front vehicle starting time and the time difference between the vehicle i starting time and the front vehicle starting time is larger than the preset reaction time, the vehicle i is considered to have green light lag starting in the mth traffic light section; m is a positive integer. The preset reaction time period may be empirically set, preferably but not limited to 0.5 seconds or 1 second or 1.5 seconds or 2 seconds.
And D3, counting the number of traffic light segments of the vehicle i with the delayed start of the green light, and obtaining the delayed start times of the green light of the vehicle i.
In the present embodiment, if the vehicle i is positioned at the first place of waiting for the green light at the traffic intersection, it is necessary to evaluate whether or not the driver has a driving lag according to the green light lighting time. If the vehicle i is arranged at the traffic intersection and waits for the non-first position of the green light, whether the driver of the vehicle i lags or not is judged directly according to the starting time of the front vehicle. Abnormal driving behaviors such as drunk driving, inattention, fatigue, physical discomfort and the like can be well identified through green light starting hysteresis judgment. Because drunk driving, inattention, fatigue and untimely body response of the driver is slower than normal.
In the present embodiment, preferably, determining whether or not there is abnormal driving behavior of each vehicle in combination with the abnormal driving score and the driver state class of the vehicle includes:
when the driver state category of the vehicle is abnormal and the abnormal driving score is non-zero, determining that abnormal driving behaviors exist in the vehicle;
when the driver state category of the vehicle is normal and the abnormal driving score is larger than the score threshold value, determining that abnormal driving behaviors exist in the vehicle;
when the driver state category of the vehicle is normal and the abnormal driving score is smaller than the score threshold value, but the proportion of the green light lag starting times in the abnormal driving score is more than 60%, determining that abnormal driving behaviors exist in the vehicle.
In this embodiment, flexible combination of abnormal driving score and driver state category is realized, the problem that the drive test sensing device cannot sense the driver state in real time is compensated by using the abnormal driving score, and even if the abnormality cannot be recognized due to poor image quality of the driver caused by weather reasons, or the abnormal driver state cannot be shot at the shooting point, the abnormal driving behavior can be determined by the abnormal driving score, and the abnormal driving behavior is confirmed in a hierarchical manner, which is more accurate. The scoring threshold is preferably, but not limited to, 8 or 9 or 10.
In this embodiment, when it is determined that the vehicle i has abnormal driving behavior, the cloud control platform sends an alert to the OBU of the vehicle i and the OBUs of the vehicles in the vicinity of the vehicle i. And warning the vehicle i to remind the vehicle i of correcting the abnormal driving behavior. The alert to be sent to the OBU of the nearby vehicle i includes information on the direction of the nearby vehicle including the vehicle i, such as front, rear, left, right, and front right. The vehicle in the vicinity of the vehicle i is a vehicle having a radius of 10 meters around the vehicle i.
In this embodiment, when it is determined that the vehicle has abnormal driving behavior, the cloud control platform further transmits early warning information to the traffic management platform, where the early warning information includes a vehicle ID, an abnormal driving score, and a driver status category. So that the traffic management platform pays attention to abnormal driving vehicles and is convenient to manage.
The invention also discloses a traffic safety management system based on the abnormal driving behavior recognition method based on the vehicle and the road side perception data, which comprises a cloud control platform, road side perception equipment and an OBU of the vehicle in the road network, as shown in fig. 2, wherein the cloud control platform is respectively connected and communicated with the road side perception equipment and the OBU.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. An abnormal driving behavior recognition method based on vehicle and roadside awareness data, characterized in that, in each control period, execution of:
0BU reports vehicle information to a cloud control platform in real time, wherein the vehicle information comprises position information, vehicle speed, steering wheel rotation angle, front vehicle distance, time tag and vehicle ID;
the cloud control platform obtains abnormal driving scores of each vehicle based on the acquired vehicle information of each vehicle;
the road side sensing equipment shoots a vehicle image and uploads the vehicle image to the cloud control platform;
the cloud control platform screens out a driver image containing a driver, and performs recognition processing on the driver image to obtain a driver state category, wherein the driver state category comprises normal and abnormal states, and the abnormal states comprise drunk driving, fatigue, emotion abnormality and inattention;
determining whether an abnormal driving behavior exists for each vehicle in combination with the abnormal driving score and the driver status category of the vehicle.
2. The abnormal driving behavior recognition method based on vehicle and roadside awareness data according to claim 1, wherein the cloud control platform obtains an abnormal driving score of each vehicle based on the acquired vehicle information of each vehicle, comprising:
obtaining the number of non-accident speed changes, the number of sudden lane changes, the number of too small vehicle distance before and the number of delayed green light starting of each vehicle;
and summing up and calculating the number of the non-accident speed changes, the number of sudden lane changes, the number of the too small vehicle distance and the number of the delayed green light starting times of each vehicle to obtain the abnormal driving score of the vehicle.
3. The abnormal driving behavior recognition method based on the vehicle and the roadside awareness data according to claim 2, wherein the method of acquiring the number of times of the non-accident shift of the vehicle i as a whole is:
extracting the speed data of continuous driving segments from the existing speed data of the vehicle i;
traversing each continuous driving section of the vehicle i, and acquiring the number of times of non-accident speed change of the vehicle i in each continuous driving section: calculating the acceleration of the vehicle i based on the vehicle speed data of the vehicle i in the nth consecutive driving segment, if any: i a ijt -a i′(j+Δj)t If the I is more than or equal to deltaa, the vehicle i is considered to have 1 non-fault speed change at the position j at the time t, wherein a ijt Acceleration, a, of vehicle i at position j at time t i′(j+Δj)t Time t is representedAcceleration of the vehicle i' in a j+Δj position range in front of the vehicle i, Δa representing a preset acceleration difference threshold; i. n and i' are both positive integers;
and accumulating the number of times of the non-reason speed change of the vehicle i in all continuous driving sections to obtain the number of times of the non-reason speed change of the whole vehicle i.
4. The abnormal driving behavior recognition method based on the vehicle and the roadside awareness data as set forth in claim 3, wherein the method for acquiring the burst transition times of the vehicle i as a whole is as follows:
extracting steering wheel angle data of continuous driving sections from the steering wheel angle data of the vehicle i;
traversing each continuous driving section of the vehicle i, and obtaining the non-accident variable pass number of the vehicle i in each continuous driving section: for the nth continuous driving section, if the steering wheel angle of the vehicle i at the position j at the time t is larger than or equal to the steering angle threshold value, and the steering wheel angles of the vehicles at the left front, the front and the right front of the vehicle i at the time t are smaller than the steering angle threshold value, the vehicle i at the position j at the time t is considered to suddenly change the road for 1 time;
and accumulating the non-fault variable pass number of the vehicle i in all continuous driving sections to obtain the whole non-fault variable pass number of the vehicle i.
5. The abnormal driving behavior recognition method based on the vehicle and the roadside awareness data as set forth in claim 3 or 4, wherein the method of acquiring the number of times that the preceding vehicle distance of the vehicle i is excessively small is as follows:
acquiring safe front vehicle distances at different time points based on the vehicle speed of the vehicle i at different time points and the front vehicle speed, and if the front vehicle distance of the vehicle i at time t is smaller than the safe front vehicle distance corresponding to the time t, considering that the front vehicle distance of the vehicle i at the time t is too small;
and counting the number of continuous time segments of the vehicle i with the too small front vehicle distance in the travel, and taking the number of continuous time segments as the times of the too small front vehicle distance of the vehicle i.
6. The abnormal driving behavior recognition method based on the vehicle and the road side perception data as claimed in claim 5, wherein the method for obtaining the green light lag starting times of the vehicle i is as follows:
extracting speed data of the vehicle i passing through traffic light segments from vehicle information of the vehicle i;
for the mth traffic light segment of the vehicle i, when the vehicle i is the first traffic light to pass through, if the starting time of the vehicle i is later than the green light lighting time and the time difference between the starting time of the vehicle i and the green light lighting time is greater than the preset reaction duration, the vehicle i is considered to have green light lag starting in the mth traffic light segment; when the vehicle i is not the first green light passing vehicle, if the vehicle i is started later than the front vehicle starting time and the time difference between the vehicle i starting time and the front vehicle starting time is larger than the preset reaction time, the vehicle i is considered to have green light lag starting in the mth traffic light section; m is a positive integer.
And counting the number of traffic light segments of the vehicle i with the delayed start of the green light, and obtaining the delayed start times of the green light of the vehicle i.
7. The abnormal driving behavior recognition method based on vehicle and roadside awareness data as set forth in claim 1 or 2 or 3 or 4 or 6, wherein said determining whether the vehicle has abnormal driving behavior by combining the abnormal driving score and the driver state class of each vehicle comprises:
when the driver state category of the vehicle is abnormal and the abnormal driving score is non-zero, determining that abnormal driving behaviors exist in the vehicle;
when the driver state category of the vehicle is normal and the abnormal driving score is larger than the score threshold value, determining that abnormal driving behaviors exist in the vehicle;
when the driver state category of the vehicle is normal and the abnormal driving score is smaller than the score threshold value, but the proportion of the green light lag starting times in the abnormal driving score is more than 60%, determining that abnormal driving behaviors exist in the vehicle.
8. The abnormal driving behavior recognition method based on the vehicle and the roadside sensing data as claimed in claim 7, wherein the cloud control platform transmits an alert reminder to the OBU of the vehicle i and the 0BU of the vehicles near the vehicle i when it is determined that the abnormal driving behavior exists in the vehicle i.
9. The method for identifying abnormal driving behavior based on vehicle and roadside awareness data according to claim 8, wherein when it is determined that abnormal driving behavior exists in the vehicle, the cloud control platform further transmits early warning information to the traffic management platform, wherein the early warning information includes a vehicle ID, an abnormal driving score and a driver state category.
10. A traffic safety management system based on the abnormal driving behavior recognition method based on the vehicle and the road side perception data according to any one of claims 1-9, characterized by comprising a cloud control platform, road side perception equipment and 0BU of vehicles in road network, wherein the cloud control platform is respectively connected and communicated with the road side perception equipment and the OBU.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311844826.1A CN117876976A (en) | 2023-12-28 | 2023-12-28 | Abnormal driving behavior identification method and system based on vehicle and road side perception data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311844826.1A CN117876976A (en) | 2023-12-28 | 2023-12-28 | Abnormal driving behavior identification method and system based on vehicle and road side perception data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117876976A true CN117876976A (en) | 2024-04-12 |
Family
ID=90591363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311844826.1A Pending CN117876976A (en) | 2023-12-28 | 2023-12-28 | Abnormal driving behavior identification method and system based on vehicle and road side perception data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117876976A (en) |
-
2023
- 2023-12-28 CN CN202311844826.1A patent/CN117876976A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220262239A1 (en) | Determining causation of traffic events and encouraging good driving behavior | |
| CN108919256B (en) | Four-dimensional real-scene traffic simulation vehicle overspeed whole-course tracking detection alarm system and method | |
| US10332401B2 (en) | Running vehicle alerting system and method | |
| US9352683B2 (en) | Traffic density sensitivity selector | |
| CN106652558B (en) | Vehicle-road cooperative intelligent traffic control system | |
| WO2018058958A1 (en) | Road vehicle traffic alarm system and method therefor | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| US11180164B2 (en) | Vehicle control apparatus, vehicle, and control method | |
| CN109285349B (en) | Method for detecting highway traffic incident under cooperative vehicle and road environment and early warning system | |
| CN102785660A (en) | Vehicle collision-proof early warning device | |
| CN106114502A (en) | A kind of intelligent automobile aid system | |
| CN108615383B (en) | Automobile traffic intersection auxiliary passing system based on workshop communication and control method thereof | |
| CN110264742B (en) | Vehicle-mounted information monitoring device suitable for expressway and warning method thereof | |
| US10977882B1 (en) | Driver health profile | |
| CN110428662A (en) | Right side intelligent collision pre-warning management system and working method based on millimeter wave | |
| CN111260915B (en) | Early warning reminding method for pedestrian stay in expressway traffic abnormal area | |
| CN110271554A (en) | Driving assistance system and method for vehicle | |
| CN115346370B (en) | Intersection anti-collision system and method based on intelligent traffic | |
| CN109895694B (en) | Lane departure early warning method and device and vehicle | |
| CN217157480U (en) | Highway tunnel risk monitoring system based on people's car behavior analysis | |
| CN113401118B (en) | Driving auxiliary system and method for predicting front vehicle braking | |
| CN117876976A (en) | Abnormal driving behavior identification method and system based on vehicle and road side perception data | |
| CN113053083A (en) | Early warning method and system for dangerous driving vehicle based on V2X | |
| CN110491153A (en) | A kind of intelligent management system of car networking | |
| CN115134491B (en) | Image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |