CN114763145A - Driving behavior detection method and device, electronic equipment and storage medium - Google Patents

Driving behavior detection method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114763145A
CN114763145A CN202110037537.5A CN202110037537A CN114763145A CN 114763145 A CN114763145 A CN 114763145A CN 202110037537 A CN202110037537 A CN 202110037537A CN 114763145 A CN114763145 A CN 114763145A
Authority
CN
China
Prior art keywords
lane line
deviation
vehicle
lane
center
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
Application number
CN202110037537.5A
Other languages
Chinese (zh)
Inventor
马潍
胡荣东
唐铭希
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changsha Intelligent Driving Research Institute Co Ltd
Original Assignee
Changsha Intelligent Driving Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changsha Intelligent Driving Research Institute Co Ltd filed Critical Changsha Intelligent Driving Research Institute Co Ltd
Priority to CN202110037537.5A priority Critical patent/CN114763145A/en
Publication of CN114763145A publication Critical patent/CN114763145A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk

Abstract

The application relates to a driving behavior detection method, a driving behavior detection device, an electronic device and a storage medium. The method comprises the following steps: acquiring the current running speed of the vehicle and a surround view image of the vehicle; detecting a lane line in the all-round looking image; detecting obstacle information in the all-round view image; calculating lane line related statistics of a latest predetermined number of frames of the all-around images based on the lane lines, the lane line related statistics including: deviation frequency, mean of center deviation values, standard deviation of center deviation values; determining a vehicle driving behavior based on the current travel speed, the obstacle information, and the lane line related statistics. By adopting the method, the accuracy of detecting the driving behavior of the vehicle can be improved.

Description

Driving behavior detection method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of intelligent driving technologies, and in particular, to a driving behavior detection method and apparatus, an electronic device, and a storage medium.
Background
With the development of intelligent driving technology, the driving behavior detection technology based on the visual perception system plays an important role in guaranteeing the driving safety of vehicles and reducing the incidence rate of traffic accidents. At present, the conventional technology mainly obtains the lane line in front of the vehicle through a front camera or obtains the facial information of the driver through a camera in the vehicle to realize the judgment of the driving behavior, and when the vehicle touches the lane line or the driver is judged to have fatigue driving, an alarm is sent out to remind the driver.
However, for some active steering behaviors in actual driving, there are cases where a large number of misjudgments exist in the existing driving behavior detection system. For example, a lane line detection error in a certain frame image, an active steering behavior of the driver for avoiding an obstacle, and an accelerated lane change overtaking behavior of the driver may cause the detection system to issue an alarm. Frequent alarming not only fails to play a role in safety guarantee, but also influences normal driving of a driver.
Disclosure of Invention
In view of the above, it is necessary to provide a driving behavior detection method, a driving behavior detection apparatus, an electronic device, and a storage medium, which can improve accuracy in response to the above-described technical problems.
A driving behavior detection method, the method comprising:
acquiring the current running speed of the vehicle and a surround view image of the vehicle;
detecting a lane line in the all-round looking image;
detecting obstacle information in the all-round looking image;
based on the lane lines, calculating lane line related statistics of a recent predetermined number of frames of the panoramic image, the lane line related statistics including: deviation frequency, mean of center deviation values, standard deviation of center deviation values;
determining a vehicle driving behavior based on the current driving speed, the obstacle information, and the lane line-related statistic.
A driving behavior detection apparatus, the apparatus comprising:
the speed acquisition module is used for acquiring the current running speed of the vehicle;
the image acquisition module is used for acquiring a panoramic image of the vehicle;
the lane line processing module is used for detecting a lane line in the all-round looking image;
the obstacle information acquisition module is used for detecting obstacle information in the all-around view image;
a statistic determination module for calculating lane line related statistics of a recent predetermined number of frames of the all-around images based on the lane lines, the lane line related statistics comprising: deviation frequency, mean of center deviation values, standard deviation of center deviation values;
and the behavior judgment module is used for determining the driving behavior of the vehicle based on the current driving speed, the obstacle information and the lane line related statistic.
An electronic device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as set forth above.
According to the driving behavior detection method, the driving behavior detection device, the electronic equipment and the storage medium, when the driving behavior is detected, the vehicle surround view image is obtained, the lane line is detected based on the surround view image, the lane line related statistic of the latest preset number of frames of surround view images is calculated by combining the lane line, then the vehicle driving behavior is determined by combining the current driving speed, the obstacle information and the lane line related statistic, and the vehicle driving behavior is detected comprehensively by combining the panoramic surround view images of a plurality of frames of vehicles, so that the environmental information around the vehicle is fully utilized, the false alarm rate is reduced, the false alarm caused by single-frame detection errors is reduced, and the accuracy of detecting the vehicle driving behavior is improved.
Drawings
FIG. 1 is a diagram of an exemplary driving behavior detection method;
FIG. 2 is a flow diagram illustrating a driving behavior detection method according to one embodiment;
FIG. 3 is a flow chart illustrating a process for determining lane-line related statistics in one particular example;
FIG. 4 is a flow diagram illustrating a driving behavior detection method in one particular example;
FIG. 5 is a block diagram showing the structure of a driving behavior detection apparatus according to an embodiment;
FIG. 6 is a diagram of the internal structure of an electronic device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The driving behavior detection method provided by the application can be applied to the application environment shown in fig. 1. When the vehicle 10 is running on a road, in order to ensure the running safety of the vehicle, the driving behavior of the vehicle 10 is detected by a driving behavior detection technology, and once dangerous driving behaviors are detected, an alarm is given to remind a driver. In a conventional driving behavior detection method, an alarm is given to remind a driver when a vehicle touches a lane line. However, as shown in fig. 1, when there is an obstacle 20 in front of the vehicle, for example, the obstacle 20 is a stationary obstacle and needs to detour, or when the obstacle 20 is a slow-traveling vehicle and needs to overtake, the driver needs to travel the vehicle 10 to another lane to make detour or overtake. However, in this process, the driver inevitably touches the lane line, and according to the conventional method, the driver only touches the lane line and then gives an alarm, so that a false alarm is generated, and the safe driving of the driver is affected. In the scheme of the embodiment of the application, the driving behavior of the vehicle is comprehensively detected by combining the panoramic all-round images of multiple frames of the vehicle, so that the environmental information around the vehicle is fully utilized, the false alarm rate is reduced, and the false alarm caused by single-frame detection errors is reduced.
In one embodiment, as shown in fig. 2, a driving behavior detection method is provided, which is described by taking the method as an example applied to the vehicle 10 in fig. 1, and includes the following steps S201 to S205.
Step S201: the current running speed of the vehicle and the all-round image of the vehicle are obtained.
The current running speed of the vehicle refers to the speed of the vehicle in the current running process. This current driving speed may be obtained in various possible ways. In some embodiments of the present application, the current driving speed of the host vehicle may be obtained through a CAN (Controller Area Network) bus of the vehicle.
The panoramic image of the vehicle is a 360-degree overhead image of the vehicle body periphery. In the embodiment of the application, the looking-around image can be obtained by combining with a vehicle-mounted looking-around system of a vehicle. The vehicle-mounted all-round looking system is characterized in that a plurality of wide-angle cameras which can cover all view field ranges around a vehicle are erected around the vehicle, generally 4-8 wide-angle cameras are erected around the vehicle, and a plurality of paths of videos collected at the same time are influenced and processed into a vehicle body top view of 360 degrees around the vehicle. Therefore, whether obstacles exist around the vehicle and the relative position and distance of the obstacles can be clearly checked through the top view of the vehicle body.
Step S202: and detecting a lane line in the all-round looking image.
As described above, the obtained panoramic image includes the lane lines of the road on which the vehicle is traveling. By performing image processing on the obtained panoramic image, a lane line in the panoramic image can be obtained. Specifically, the method for obtaining the lane line from the ring-view image may be performed by using an existing image processing method, and the embodiment of the present application is not particularly limited.
In one embodiment, after the lane line in the look-around image is detected, the detected lane line may be further fitted to obtain a lane line fitting equation in a vehicle body coordinate system, where the lane line fitting equation includes a current lane line fitting equation of a lane line of a current driving lane of the host vehicle. The method of the present application is not particularly limited, and for example, a least square method may be used to fit the lane line fitting equation. It can be understood that, since the driving lane generally includes two lane lines on both sides, the current lane line fitting equation consists of a first lane line equation and a second lane line equation. In the embodiment of the present application, the first lane line equation and the second lane line equation may each be a one-dimensional quadratic equation.
If the first lane line equation and the second lane line equation are both quadratic equations of unity, the first lane line equation can be recorded as y1＝a1x2+b1x+c1The second lane line equation may be noted as y2＝a2x2+b2x+c2. Wherein, a1Is the second order coefficient of the first lane line equation, b1Is the coefficient of the first order of the first lane line equation, c1Is a constant term of the first lane line equation, also referred to as the first constant term in the embodiments of the present application. a is2Is the coefficient of the second order of the second lane line equation, b2Is the first order coefficient of the second lane line equation, c2Is a constant term of the second lane line equation, also referred to as the second constant term in the embodiments of the present application.
Step S203: and detecting obstacle information in the all-round looking image.
In the driving field, an obstacle generally refers to an object that may affect or plan normal driving of a vehicle, such as a pothole, a cone, a water horse, a motor vehicle, a pedestrian, etc., in front of or on both sides of the driving of the vehicle. Distinguishing from the type of movement, there may be a division into stationary obstacles, which may include, for example, potholes, cones, water horses, etc., and moving obstacles, which may include, for example, motor vehicles, pedestrians, etc. The method for detecting and obtaining the obstacle information from the panoramic image may be performed by any image processing method that is already available or will appear in the future, for example, the application network is used to process the panoramic image to identify the obstacle in the image and the type and position of the obstacle, and the embodiment of the present application is not limited in particular.
Step S204: calculating lane line related statistics of a latest predetermined number of frames of the all-around images based on the lane lines, the lane line related statistics including: deviation frequency, mean of center deviation values, standard deviation of center deviation values.
Based on the lane lines identified above, lane line-based correlation statistics are combined with the most recent frames of the all-around images of the predetermined number of frames. The predetermined number can be determined by combining with actual technical requirements, generally, the predetermined number is too small to set, the panoramic image with too few frames is difficult to reflect the actual change condition, but the predetermined book is too large to set, the panoramic image with too many frames causes the increase of the processing amount, and information before too early time is included, which affects the accuracy of the final determination result.
Wherein the calculated deviation frequency represents the number of changes of the vehicle center within the predetermined number of frames, the mean value of the center deviation values represents the average of the changes of the vehicle center within the predetermined number of frames, and the standard deviation of the center deviation values represents the dispersion degree of the changes of the vehicle center within the predetermined number of frames. Therefore, based on the calculated lane line related statistics, the change information of the vehicle center in the vehicle driving process can be reasonably and effectively reflected, and the vehicle driving behavior is evaluated accordingly.
In an embodiment, when the current lane line fitting equation is fitted, calculating the lane line related statistic of the latest predetermined number of frames of the panoramic image based on the lane line fitting equation may specifically include: and calculating and determining the lane line related statistic of the latest frames of the all-around images in the preset number based on the current lane line fitting equation corresponding to the latest frames of the all-around images in the preset number.
In a specific example, referring to fig. 3, calculating the lane line related statistic for determining the latest predetermined number of frames of the circular-view images based on the current lane line fitting equation corresponding to the latest predetermined number of frames of the circular-view images may include the following steps S2041 to S2043.
Step S2041: and determining the center deviation value, the slope and the curvature of the lane line based on the current lane line fitting equation.
When determining the center deviation value, the slope and the curvature, taking the example that the current lane line fitting equation includes a first lane line equation with one or two times and a second lane line equation with one or two times as an example, at this time, the center deviation value may be a mean value of a first constant term of the first lane line equation and a second constant term of the second lane line equation; the slope may be a mean of a first order coefficient of the first lane line equation and a first order coefficient of the second lane line equation; the curvature may be a mean of a second order coefficient of the first lane line equation and a second order coefficient of the second lane line equation.
In one embodiment, the first lane line equation y is based on1＝a1x2+b1x+c1And a second lane line equation y2＝a2x2+b2x+c2If the center deviation value is denoted by d, the slope is denoted by θ, and the curvature is denoted by ρ, then: d ═ c1+c2)/2、θ＝(b1+b2)/2、ρ＝(a1+a2)/2。
Step S2042: and determining deviation frequency according to the center deviation value, the slope and the curvature corresponding to the latest frame all-round-looking images with preset number.
In determining the deviation frequency based on the center deviation value, the slope and the curvature corresponding to the most recent predetermined number of frames of the all-round image, an embodiment may include the following steps.
Firstly, determining a deviation frequency coefficient of the most recent frames of all-round images according to the center deviation value, the slope and the curvature corresponding to the most recent frames of all-round images. In some specific examples, the deviation frequency coefficient is an average of the center deviation value, the slope, and the number of times the curvature has changed in direction within a predetermined number of recent frames of the surround view image. For example, if the number of times of the direction change of the center deviation value in the latest predetermined number of frames of the panoramic image is defined as a first number, the number of times of the direction change of the slope in the latest predetermined number of frames of the panoramic image is defined as a second number, and the number of times of the direction change of the curvature in the latest predetermined number of frames of the panoramic image is defined as a third number, the frequency coefficient may be an average of the first number, the second number, and the third number.
In some specific examples, the frequency coefficient may be defined by the formula:
Figure BDA0002893833340000061
wherein the function g (x)1,x2) For the deviation from the frequency function, the following is defined:
Figure BDA0002893833340000062
it can be seen that when x1And x2Is that g (x)1,x2) And recording the number of times, otherwise not counting, thereby reflecting the change number of the signs in the N frames. For example, in the case of a liquid,
Figure BDA0002893833340000063
the number of times of change in the sign of the center deviation value d within the N frame, i.e. the first time,
Figure BDA0002893833340000064
the change times of the signs of the slopes theta in the N frames, namely the second times,
Figure BDA0002893833340000071
the number of changes in the sign of the curvature ρ within the N frame, i.e., the third number, is represented.
Then, the deviation frequency is determined based on the deviation frequency coefficient and the frame rate of the all-round image. In one embodiment, the deviation frequency may be a ratio of a product of the deviation frequency coefficient and the frame rate to the predetermined number.
Noting the deviation frequency f and the frame rate s, the following formula can be expressed as: and f is gs/N.
Step S2043: and calculating and determining the mean value of the central deviation values and the standard deviation of the central deviation values according to the central deviation values corresponding to the latest frames of all-round images with preset number.
The mean value of the center deviation values represents an average of the changes of the vehicle center within the predetermined number of frames, and therefore, in some specific examples, it may be that the most recent center deviation values corresponding to the predetermined number of frames of the panoramic image are directly averaged and the average value is taken as the mean value of the center deviation values. And calculating a standard deviation of the center deviation value in combination with the mean of the center deviation values. In one embodiment, the standard deviation is the square root of the ratio of the sum of the absolute value of the center deviation value and the mean of the center deviation values for each frame of the ring-view image pair to a predetermined number.
Recording the mean value of the center deviation as mudStandard deviation of the center deviation value is deltadThen, it can be formulated as:
Figure BDA0002893833340000072
Figure BDA0002893833340000073
step S205: determining a vehicle driving behavior based on the current driving speed, the obstacle information, and the lane line-related statistic.
In some specific examples, when determining the driving behavior of the vehicle based on the current traveling speed, the obstacle information, and the lane line-related statistic, there may be different comprehensive determination manners in combination with the actual current traveling speed, the obstacle information, and the lane line-related statistic.
In some embodiments, it may be a direct determination that dangerous driving behavior is occurring when the deviation frequency is greater than a deviation frequency threshold. Since the deviation frequency represents the number of times of change of the vehicle center within the predetermined number of frames, if the deviation frequency is greater than the deviation frequency threshold, it means that the vehicle has changed the vehicle center too many times within the predetermined number of frames, and it can be directly determined that dangerous driving behavior has occurred without considering other related information such as obstacle information.
Wherein the deviation frequency threshold may Set in conjunction with actual needs, in some embodiments, the deviation frequency threshold may be determined based on the current travel speed. For example, in some specific examples, the deviation frequency threshold may be a ratio of the current driving degree to a first predetermined parameter, and the deviation frequency threshold is denoted as TfThe first predetermined parameter is DfThen can be formulated as Tf＝v/Df. The first predetermined parameter DfIs a constant value that can be set empirically, e.g., in some embodiments, the first predetermined parameter D can be setfSet to 20.
In some embodiments, when the deviation frequency is less than or equal to a deviation frequency threshold, the mean of the center deviation values is less than or equal to a mean threshold, and the standard deviation of the center deviation values is less than or equal to a standard deviation threshold, it is determined that dangerous driving behavior of the vehicle has not occurred. Since the mean value of the center deviation values represents the average condition of the change of the vehicle center within the predetermined number of frames, and the standard deviation of the center deviation values represents the discrete degree of the change of the vehicle center within the predetermined number of frames, when the deviation frequency is less than or equal to the deviation frequency threshold value, the mean value of the center deviation values is less than or equal to the mean threshold value, and the standard deviation of the center deviation values is less than or equal to the standard deviation threshold value, it is indicated that the change of the center deviation values of the vehicle is still within the controllable range, and it can be determined that the dangerous driving behavior of the vehicle does not occur.
Wherein the mean threshold may be determined according to a first constant term of the first lane line equation and a second constant term of the second lane line equation. In some embodiments, the mean threshold may be a ratio of an absolute value of a difference of the first constant term and the second constant term to the second predetermined parameter. Recording the average threshold value as TμThe second predetermined parameter is DμThen can be formulated as
Figure BDA0002893833340000081
The second predetermined parameter DμIs a constant value that may be set empirically, e.g., in some embodiments, the second predetermined parameter D may be setμSet to 10.
The standard deviation threshold is determined from a first constant term of the first lane line equation and a second constant term of the second lane line equation. In some embodiments, the standard deviation threshold may be a ratio of an absolute value of a difference of the first constant term and the second constant term to a third predetermined parameter. Recording the mean threshold value as TσThe third predetermined parameter is DσThen can be expressed as
Figure BDA0002893833340000091
The third predetermined parameter DσIs a constant value that may be set empirically, e.g., in some embodiments, the third predetermined parameter D may be setσSet to 5.
In some embodiments, when the deviation frequency is less than or equal to a deviation frequency threshold, the mean of the center deviation values is greater than a mean threshold or the standard deviation of the center deviation values is greater than a standard deviation threshold, and a vehicle exists in an adjacent lane in which the vehicle deviates from the direction, it is determined that dangerous driving behavior of the vehicle occurs.
In some embodiments, it is determined that the dangerous driving behavior of the vehicle does not occur when the deviation frequency is less than or equal to a deviation frequency threshold, the mean of the center deviation values is greater than a mean threshold or the standard deviation of the center deviation values is greater than a standard deviation threshold, and no vehicle exists in an adjacent lane in which the vehicle deviates from the direction.
In some embodiments, when the deviation frequency is less than or equal to the deviation frequency threshold, the mean value of the center deviation values is greater than the mean threshold, the standard deviation of the center deviation values is greater than the standard deviation threshold, and it is determined that there is detour behavior according to the obstacle information, it is determined that dangerous driving behavior does not occur to the vehicle.
In some embodiments, it may be determined that a detour behavior exists, that a static obstacle exists in front of the current driving lane, and that the mean value of the center deviation values of the obstacle information is greater than the obstacle detour width threshold. Wherein, in some embodiments, the obstacle detour width threshold is determined from the vehicle body width and the obstacle width. For example, in some embodiments, the obstacle detour width threshold may be half of the sum of the vehicle body width and the obstacle width.
Note that the width of the car body is w1The width of the obstacle is w 2Then the obstacle detour width threshold is: (w)1+w2)/2。
In some embodiments, when the deviation frequency is less than or equal to a deviation frequency threshold, the mean value of the center deviation values is greater than a mean threshold, the standard deviation of the center deviation values is greater than a standard deviation threshold, and it is determined that the dangerous driving behavior does not occur when it is determined that the passing behavior exists according to the obstacle information.
In this case, it may be determined that the passing behavior exists when there is a vehicle in front of the current driving lane and it is determined that the acceleration behavior exists according to the current driving speed. Wherein, it can be determined whether there is a vehicle in front of the current driving lane in combination with the detected obstacle information. In general, when there is a vehicle in front of the current driving lane, it may be determined that there is a vehicle in front of the current driving lane. When determining whether there is an acceleration behavior based on the current running speed, any possible manner of memorization may be employed, and for example, when the running speed of the vehicle continues to increase for a certain period of time, it may be determined that there is an acceleration behavior in the vehicle.
In some embodiments, when the deviation frequency is less than or equal to a deviation frequency threshold, the mean of the center deviation values is greater than a mean threshold, the standard deviation of the center deviation values is greater than a standard deviation threshold, and the detour behavior and the overtaking behavior are not detected according to the obstacle information, that is, when neither the detour behavior nor the overtaking behavior exists, it is determined that the dangerous driving behavior occurs.
Based on the embodiments described above, a flowchart of a driving behavior detection method in a specific example is shown in fig. 4. As shown in fig. 4, in the flow of the specific driving behavior detection, the following steps may be included.
First, the current running speed v of the vehicle is acquired through the CAN bus.
And acquiring a look-around image of the vehicle by using the vehicle-mounted look-around system, detecting a lane line in the look-around image, and fitting the detected lane line to obtain a lane line fitting equation. The lane line fitting equation comprises a current lane line fitting equation of a current lane, and specifically comprises a first lane line equation and a second lane line equation.
And carrying out omnibearing obstacle detection on the all-around view image to obtain obstacle information in the all-around view image. The obtained obstacle information may include information of a stationary obstacle, such as information of a pot hole, a cone, a water horse, and the like, and information of a moving obstacle, such as information of a motor vehicle, a pedestrian, and the like.
According to the first lane line equation y1＝a1x2+b1x+c1And a second lane line equation y2＝a2x2+b2x+c2The center deviation value d, the slope θ, and the curvature ρ of the lane line can be determined.
And determining a deviation frequency coefficient g of the ring-view images of the latest preset number of frames according to the center deviation value, the slope and the curvature corresponding to the latest preset number (N frames) of ring-view images, and calculating to obtain a deviation frequency f-gs/N if the frame rate of the vehicle-mounted ring-view system is s.
Then, the mean value mu of the center deviation values of a predetermined number N of frames accumulated up to the current frame is calculateddAnd standard deviation deltad。
Then, the driving behavior of the vehicle is determined in combination with the vehicle speed, the obstacle information, and the lane line-related statistic.
Wherein, if the deviation frequency f is larger than the threshold value TfAnd judging that the vehicle has dangerous driving behavior. Otherwise, according to the mean value mu of the center deviation valuedStandard deviation deltadAnd carrying out the next judgment.
If mean value μ of center deviation valuesdStandard deviation deltadAre not greater than corresponding threshold values Tμ、TσAnd judging that the dangerous driving behavior of the vehicle does not occur.
If mean value μ of center deviation valuesdStandard deviation deltadIs greater than the corresponding threshold value Tμ、TσAnd if the vehicle is in the adjacent lane of the vehicle deviating direction, the vehicle is judged to have dangerous driving behavior, and an alarm is given. And if the adjacent lane of the vehicle deviating from the direction does not have the vehicle, judging that the vehicle does not have dangerous driving behavior and is in a normal driving state.
If mean value μ of center deviation valuesdStandard deviation deltadAre all greater than the corresponding threshold value Tμ、TσAnd an obstacle exists in front of the current driving lane and the mean value mu of the center deviation valuedAnd if the vehicle speed is larger than the obstacle detour width threshold value, determining that the vehicle detour behavior is generated and the dangerous driving behavior is not generated.
Mean value μ if center deviation valuedStandard deviation deltadAre all greater than the corresponding threshold value Tμ、TσAnd if the vehicle is detected to be in front of the current driving lane and the acceleration behavior of the vehicle is determined according to the current driving speed acquired by the CAN bus, the overtaking behavior of the vehicle is judged and the dangerous driving behavior does not occur.
Mean value μ if center deviation valuedStandard deviation deltadAre all greater than the corresponding threshold value Tμ、TσAnd if the detour behavior and the overtaking behavior are not detected, judging that the vehicle has dangerous driving behavior, and giving an alarm.
It should be understood that, although the steps in the relevant flowcharts referred to in the embodiments of the present application are shown in sequence as indicated by arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in these flowcharts may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the steps or stages in other steps.
In one embodiment, as shown in fig. 5, there is provided a driving behavior detection device including:
a speed obtaining module 501, configured to obtain a current running speed of the vehicle;
an image acquisition module 502 for acquiring a look-around image of the host vehicle;
a lane line processing module 503, configured to detect a lane line in the panoramic image;
an obstacle information obtaining module 504, configured to detect obstacle information in the panoramic image;
a statistic determination module 505, configured to calculate, based on the lane line, lane line related statistics of the latest predetermined number of frames of the all-round-looking images, where the lane line related statistics include: deviation frequency, mean of center deviation values, standard deviation of center deviation values;
a behavior determination module 506, configured to determine a driving behavior of the vehicle based on the current driving speed, the obstacle information, and the lane line related statistics.
In some embodiments, further comprising: and the lane line fitting module is used for fitting the detected lane lines to obtain a lane line fitting equation under the vehicle body coordinate system, wherein the lane line fitting equation comprises a current lane line fitting equation of the lane line of the current driving lane of the vehicle.
At this time, the statistic determination module 505 calculates and determines the lane line related statistic of the latest predetermined number of frames of the circular-view images based on the current lane line fitting equation corresponding to the latest predetermined number of frames of the circular-view images.
In some embodiments, the statistic determination module 505 comprises:
the deviation information determination module is used for determining the center deviation value, the slope and the curvature of the lane line based on the current lane line fitting equation;
a deviation frequency determination module for determining a deviation frequency according to the center deviation value, the slope and the curvature corresponding to the latest predetermined number of frames of the all-round images;
and the mean standard deviation determining module is used for calculating and determining the mean value of the central deviation values and the standard deviation of the central deviation values according to the central deviation values corresponding to the latest frames of all-round images with preset number.
In some embodiments, the deviation frequency determining module determines a deviation frequency coefficient of the most recent predetermined number of frames of the surround-view image according to the center deviation value, the slope and the curvature corresponding to the most recent predetermined number of frames of the surround-view image; determining the deviation frequency based on the deviation frequency coefficient and a frame rate of the all-round image.
In some embodiments, the deviation frequency coefficient is an average of the center deviation value, the slope, and the number of times the curvature has changed in direction within the most recent predetermined number of frames of the panoramic image.
In some embodiments, the deviation frequency is a ratio of a product of the deviation frequency coefficient and the frame rate to the predetermined number.
In some embodiments, the current lane line fitting equation comprises a first lane line equation that is quadratic in terms of unity and a second lane line equation that is quadratic in terms of unity; the center deviation value is an average value of a first constant term of the first lane line equation and a second constant term of the second lane line equation; the slope is the mean of the first order coefficient of the first lane line equation and the first order coefficient of the second lane line equation; the curvature is an average of a quadratic coefficient of the first lane line equation and a quadratic coefficient of the second lane line equation.
In some embodiments, the behavior determination module 506 determines that dangerous driving behavior occurs when the deviation frequency is greater than a deviation frequency threshold.
In some embodiments, the behavior determining module 506 determines that the dangerous driving behavior of the vehicle does not occur when the deviation frequency is less than or equal to the deviation frequency threshold, the mean of the center deviation values is less than or equal to the mean threshold, and the standard deviation of the center deviation values is less than or equal to the standard deviation threshold.
In some embodiments, the behavior determination module 506 determines that the vehicle has dangerous driving behavior when the deviation frequency is less than or equal to the deviation frequency threshold, the mean value of the center deviation values is greater than the mean threshold or the standard deviation of the center deviation values is greater than the standard deviation threshold, and the vehicle exists in an adjacent lane in the vehicle deviation direction.
In some embodiments, the behavior determination module 506 determines that the dangerous driving behavior does not occur when the deviation frequency is less than or equal to the deviation frequency threshold, the mean value of the center deviation values is greater than the mean value threshold, or the standard deviation of the center deviation values is greater than the standard deviation threshold, and no vehicle exists in the adjacent lane of the vehicle deviating direction.
In some embodiments, the behavior determination module 506 determines that the vehicle does not have the dangerous driving behavior when the deviation frequency is less than or equal to the deviation frequency threshold, the mean of the center deviation values is greater than the mean threshold, the standard deviation of the center deviation values is greater than the standard deviation threshold, and the detour behavior is determined to exist according to the obstacle information.
In some embodiments, the behavior determination module 506 determines that the detour behavior exists when a static obstacle exists in front of the current driving lane and the mean value of the deviation values of the center of the obstacle information is greater than the obstacle detour width threshold.
In some embodiments, the behavior determining module 506 determines that the dangerous driving behavior does not occur when the deviation frequency is less than or equal to the deviation frequency threshold, the mean value of the center deviation values is greater than the mean value threshold, the standard deviation of the center deviation values is greater than the standard deviation threshold, and it is determined that the overtaking behavior exists according to the obstacle information.
In some embodiments, the behavior determination module 506 determines that there is a cut-in behavior when there is a vehicle in front of the current driving lane and it is determined that there is an acceleration behavior according to the current driving speed.
In some embodiments, the behavior determination module 506 determines that dangerous driving behavior occurs when the deviation frequency is less than or equal to the deviation frequency threshold, the mean of the center deviation values is greater than the mean threshold, the standard deviation of the center deviation values is greater than the standard deviation threshold, and the detour behavior and the passing behavior are not detected according to the obstacle information.
For the specific definition of the driving behavior detection device, see the above definition of the driving behavior detection method, which is not described in detail herein. The various modules in the driving behavior detection device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules may be embedded in a hardware form or may be independent of a processor in the electronic device, or may be stored in a memory in the electronic device in a software form, so that the processor calls and executes operations corresponding to the modules.
In one embodiment, an electronic device is provided, which may be a vehicle terminal device mounted on a vehicle, and an internal structure diagram thereof may be as shown in fig. 6. The electronic device includes a processor, memory, a communication interface, and in some embodiments a display screen and an input device, connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the electronic device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a driving behavior detection method. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the electronic equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the configuration shown in fig. 6 is a block diagram of only a portion of the configuration associated with the present application, and does not constitute a limitation on the electronic device to which the present application is applied, and a particular electronic device may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided an electronic device comprising a memory in which a computer program is stored and a processor which, when executing the computer program, implements the steps of the driving behavior detection method in any of the embodiments described above.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, realizes the steps of the driving behavior detection method of any of the embodiments as described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (12)

1. A driving behavior detection method, characterized in that the method comprises:
acquiring the current running speed of the vehicle and a surround view image of the vehicle;
detecting a lane line in the all-round looking image;
detecting obstacle information in the all-round looking image;
calculating lane line related statistics of a latest predetermined number of frames of the all-around images based on the lane lines, the lane line related statistics including: deviation frequency, mean of center deviation values, standard deviation of center deviation values;
Determining a vehicle driving behavior based on the current travel speed, the obstacle information, and the lane line related statistics.
2. The method of claim 1, wherein:
after the lane line in the all-round looking image is detected, the method further comprises the following steps: fitting the detected lane lines to obtain a lane line fitting equation under a vehicle body coordinate system, wherein the lane line fitting equation comprises a current lane line fitting equation of the lane line of the current driving lane of the vehicle;
calculating lane line related statistics for a recent predetermined number of frames of the all-around image based on the lane line fitting equation, comprising: and calculating and determining the lane line related statistic of the latest frame of the circular-looking images in the preset number based on the current lane line fitting equation corresponding to the latest frame of the circular-looking images in the preset number.
3. The method of claim 2, wherein calculating lane line related statistics that determine the most recent frames of the all-around images based on a current lane line fitting equation corresponding to the most recent frames of the all-around images comprises:
determining a central deviation value, a slope and a curvature of the lane line based on the current lane line fitting equation;
Determining deviation frequency according to the center deviation value, the slope and the curvature corresponding to the latest frames of all-round images with preset number;
and calculating and determining the mean value of the center deviation values and the standard deviation of the center deviation values according to the center deviation values corresponding to the latest frames of all-round-looking images with the preset number.
4. The method of claim 3, wherein determining a deviation frequency based on the center deviation value, the slope, and the curvature for the most recent predetermined number of frames of the all-round image comprises:
determining a deviation frequency coefficient of the latest frame of the all-round-looking images with the preset number according to the center deviation value, the slope and the curvature corresponding to the latest frame of the all-round-looking images with the preset number;
determining the deviation frequency based on the deviation frequency coefficient and a frame rate of the look-around image.
5. The method of claim 4, comprising at least one of:
the deviation frequency coefficient is the average value of the center deviation value, the slope and the number of times of the direction change of the curvature in the latest preset number of frames of all-round images;
the deviation frequency is a ratio of a product of the deviation frequency coefficient and the frame rate to the predetermined number.
6. The method of claim 3, wherein the current lane line fitting equation comprises a first lane line equation that is quadratic in terms of unity and a second lane line equation that is quadratic in terms of unity;
the center deviation value is an average value of a first constant term of the first lane line equation and a second constant term of the second lane line equation;
the slope is an average of a first order coefficient of the first lane line equation and a first order coefficient of the second lane line equation;
the curvature is an average of a quadratic coefficient of the first lane line equation and a quadratic coefficient of the second lane line equation.
7. The method of any of claims 1 to 6, wherein determining vehicle driving behavior based on the current travel speed, the obstacle information, and the lane line related statistics comprises at least one of:
determining that dangerous driving behavior occurs when the deviation frequency is greater than a deviation frequency threshold;
when the deviation frequency is less than or equal to a deviation frequency threshold, the mean value of the center deviation values is less than or equal to a mean value threshold, and the standard deviation of the center deviation values is less than or equal to a standard deviation threshold, determining that the vehicle does not have dangerous driving behaviors;
When the deviation frequency is smaller than or equal to a deviation frequency threshold, the mean value of the center deviation values is larger than a mean value threshold or the standard deviation of the center deviation values is larger than a standard deviation threshold, and vehicles exist in adjacent lanes in the vehicle deviation direction, determining that dangerous driving behaviors occur to the vehicles;
when the deviation frequency is smaller than or equal to a deviation frequency threshold value, the mean value of the center deviation values is larger than a mean value threshold value or the standard deviation of the center deviation values is larger than a standard deviation threshold value, and no vehicle exists in an adjacent lane in the vehicle deviation direction, determining that no dangerous driving behavior occurs in the vehicle;
when the deviation frequency is smaller than or equal to a deviation frequency threshold value, the mean value of the center deviation values is larger than a mean value threshold value, the standard deviation of the center deviation values is larger than a standard deviation threshold value, and when the detour behavior is judged to exist according to the obstacle information, it is determined that the dangerous driving behavior does not occur to the vehicle;
when the deviation frequency is smaller than or equal to a deviation frequency threshold value, the mean value of the center deviation values is larger than a mean value threshold value, the standard deviation of the center deviation values is larger than a standard deviation threshold value, and when the overtaking behavior is judged to exist according to the obstacle information, it is determined that no dangerous driving behavior occurs;
And when the deviation frequency is less than or equal to the deviation frequency threshold, the mean value of the center deviation values is greater than the mean value threshold, the standard deviation of the center deviation values is greater than the standard deviation threshold, and the dangerous driving behavior is determined to occur when the detour behavior and the overtaking behavior are not detected according to the obstacle information.
8. The method of claim 7, comprising at least one of:
a static obstacle exists in front of the current driving lane, and the mean value of the center deviation values of the obstacle information is larger than the obstacle detouring width threshold value, so that the detouring behavior is determined to exist;
when there is a vehicle ahead of the current driving lane and it is determined that there is an acceleration behavior according to the current driving speed, it is determined that there is a passing behavior.
9. The method of claim 8, comprising at least one of:
the deviation frequency threshold value is determined according to the current running speed;
the mean threshold value is determined according to a first constant term of the first lane line equation and a second constant term of the second lane line equation; the first lane line equation and the second lane line equation are lane line fitting equations of the current lane in a vehicle body coordinate system;
The standard deviation threshold is determined according to a first constant term of the first lane line equation and a second constant term of the second lane line equation; the first lane line equation and the second lane line equation are lane line fitting equations of the current lane in a vehicle body coordinate system;
the obstacle detour width threshold is determined according to the width of the vehicle body and the width of the obstacle.
10. A driving behavior detection apparatus, characterized in that the apparatus comprises:
the speed acquisition module is used for acquiring the current running speed of the vehicle;
the image acquisition module is used for acquiring a panoramic image of the vehicle;
the lane line processing module is used for detecting a lane line in the all-round looking image;
the obstacle information acquisition module is used for detecting obstacle information in the all-around view image;
a statistic determination module for calculating lane line related statistics of a recent predetermined number of frames of the all-around images based on the lane lines, the lane line related statistics comprising: deviation frequency, mean of center deviation values, standard deviation of center deviation values;
and the behavior judgment module is used for determining the driving behavior of the vehicle based on the current running speed, the obstacle information and the lane line related statistic.
11. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any of claims 1 to 9 when executing the computer program.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
CN202110037537.5A 2021-01-12 2021-01-12 Driving behavior detection method and device, electronic equipment and storage medium Pending CN114763145A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110037537.5A CN114763145A (en) 2021-01-12 2021-01-12 Driving behavior detection method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110037537.5A CN114763145A (en) 2021-01-12 2021-01-12 Driving behavior detection method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114763145A true CN114763145A (en) 2022-07-19

Family

ID=82364112

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110037537.5A Pending CN114763145A (en) 2021-01-12 2021-01-12 Driving behavior detection method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114763145A (en)

Similar Documents

Publication Publication Date Title
CN112389448B (en) Abnormal driving behavior identification method based on vehicle state and driver state
CN110909419B (en) Automobile safety integrity performance level calculation method, device and server
CN109345829B (en) Unmanned vehicle monitoring method, device, equipment and storage medium
CN112163543A (en) Method and system for detecting illegal lane occupation of vehicle
CN109766867B (en) Vehicle running state determination method and device, computer equipment and storage medium
CN110738081B (en) Abnormal road condition detection method and device
CN105243701A (en) Driving information reporting method and driving recording terminal
CN110949381B (en) Method and device for monitoring driving behavior risk degree
CN112109633A (en) Lane departure early warning method, device, equipment, vehicle and storage medium
CN112562406B (en) Method and device for identifying off-line driving
US10977882B1 (en) Driver health profile
CN112009470B (en) Vehicle running control method, device, equipment and storage medium
US20100145618A1 (en) Vehicle collision management systems and methods
CN111104824A (en) Method for detecting lane departure, electronic device, and computer-readable storage medium
CN114763145A (en) Driving behavior detection method and device, electronic equipment and storage medium
CN110705495A (en) Detection method and device for vehicle, electronic equipment and computer storage medium
JP6989347B2 (en) Vehicle condition determination device, vehicle condition determination system, vehicle condition determination method, and vehicle condition determination program
US11383733B2 (en) Method and system for detecting a dangerous driving condition for a vehicle, and non-transitory computer readable medium storing program for implementing the method
CN112990117B (en) Installation data processing method and device based on intelligent driving system
CN113569666B (en) Method for detecting continuous illegal lane change of vehicle and computer equipment
CN115520216A (en) Driving state judging method and device, computer equipment and storage medium
JP7402753B2 (en) Safety support system and in-vehicle camera image analysis method
CN111319627B (en) Driving assistance method, apparatus, computer device, and storage medium
CN114333414A (en) Parking yield detection device, parking yield detection system, and recording medium
CN111612140A (en) Automatic driving safety discrimination method, equipment and storage medium based on road side unit

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination