CN113525391A - Illegal driving identification method and system based on artificial intelligence - Google Patents

Illegal driving identification method and system based on artificial intelligence Download PDF

Info

Publication number
CN113525391A
CN113525391A CN202111088570.7A CN202111088570A CN113525391A CN 113525391 A CN113525391 A CN 113525391A CN 202111088570 A CN202111088570 A CN 202111088570A CN 113525391 A CN113525391 A CN 113525391A
Authority
CN
China
Prior art keywords
vehicle
information
time
speed
road
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.)
Granted
Application number
CN202111088570.7A
Other languages
Chinese (zh)
Other versions
CN113525391B (en
Inventor
吴亚斌
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.)
Jiangsu Juheng Intelligent Technology Co ltd
Original Assignee
Jiangsu Juheng Intelligent Technology 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 Jiangsu Juheng Intelligent Technology Co ltd filed Critical Jiangsu Juheng Intelligent Technology Co ltd
Priority to CN202111088570.7A priority Critical patent/CN113525391B/en
Publication of CN113525391A publication Critical patent/CN113525391A/en
Application granted granted Critical
Publication of CN113525391B publication Critical patent/CN113525391B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/12—Lateral 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
    • B60W2552/30—Road curve radius
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4043—Lateral speed

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses an artificial intelligence-based illegal driving identification method and system, which comprises the following steps: obtaining speed, position information and vehicle type information of vehicles in the current road section and surrounding vehicles at the current moment, and obtaining curvature information of the road through edge processing; obtaining an environmental influence value at the current moment by using speed information, position information, vehicle type information and curvature information of a road of the vehicle and surrounding vehicles at the current moment; predicting speed information, position information and curvature information of vehicles and surrounding vehicles at the next moment, and obtaining an environmental influence value at the next moment; calculating the change quantity of the environmental influence values at the next moment and the current moment, and determining the threshold value of the attention dispersion ratio; and comparing the actual attention distraction ratio of the driver with the attention distraction ratio threshold value to obtain the judgment result of the illegal behavior of the driver. The influence of surrounding vehicles and road conditions on the required attention is considered, so that the detection standard for violation of driver attention is more reasonable, and violation records and warnings are made in time.

Description

Illegal driving identification method and system based on artificial intelligence
Technical Field
The application relates to the field of artificial intelligence, in particular to an illegal driving identification method and system based on artificial intelligence.
Background
In the driving process of the vehicle, a vehicle driver is easy to cause inattention due to external factors, great potential safety hazards are brought to driving safety and personal safety of drivers and passengers, the attention of the driver is detected, and the driver is reminded when the attention of the driver is inattention, so that the accident rate can be effectively reduced, and the driving safety and the personal safety of the drivers and passengers are guaranteed to the maximum extent.
The existing driver attention detection methods mostly adopt fixed attention violation judgment standards, and do not consider the influence of real-time road conditions and other surrounding vehicles on driving attention requirements, so that the detection result cannot adapt to the road conditions, the surrounding vehicles and other environments.
Disclosure of Invention
Aiming at the technical problems, the invention provides an illegal driving identification method and system based on artificial intelligence.
In a first aspect, a method for identifying offending driving based on artificial intelligence is provided, including:
obtaining the current time
Figure 100002_DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
using the acquired current time
Figure 828743DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 994145DEST_PATH_IMAGE002
An environmental impact value;
according to the current time
Figure 763518DEST_PATH_IMAGE002
Predicting the next time by the speed information, position information, vehicle type information and curvature information of the road
Figure 100002_DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 330765DEST_PATH_IMAGE004
An environmental impact value;
according to the next moment
Figure 19236DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 671934DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure 100002_DEST_PATH_IMAGE006
Determining the variation of the environmental influence value in the time period, and determining the time distraction ratio threshold value corresponding to different variation;
get driver at
Figure 244998DEST_PATH_IMAGE006
And comparing the actual attention dispersion ratio with an attention dispersion ratio threshold value in the time period, and judging whether the driver violates the rules according to the comparison result.
Further, the influencing factors of the environmental influence value include: the area occupation ratio of other surrounding vehicles; the distance between the own vehicle and other surrounding vehicles; the bearing weights of other surrounding vehicles.
Further, the method for calculating the environmental impact value comprises the following steps:
Figure 100002_DEST_PATH_IMAGE008
wherein for the first
Figure 100002_DEST_PATH_IMAGE010
The vehicle is driven by the electric motor,
Figure 100002_DEST_PATH_IMAGE012
in order to be able to control the speed of travel,
Figure 100002_DEST_PATH_IMAGE014
in order to make the area of the film occupy the track ratio,
Figure 100002_DEST_PATH_IMAGE016
in order for its orientation to affect the weights,
Figure 100002_DEST_PATH_IMAGE018
in order for it to be distant from the own vehicle,
Figure 100002_DEST_PATH_IMAGE020
for the curvature data of the current road segment,
Figure 100002_DEST_PATH_IMAGE022
the number of vehicles in the current section.
Further, the next time point
Figure 260227DEST_PATH_IMAGE004
The method for acquiring the speed and position information of the vehicle and surrounding vehicles comprises the following steps:
vehicle is at
Figure 57282DEST_PATH_IMAGE006
The average speed deviation range in the time range is
Figure 100002_DEST_PATH_IMAGE024
Then around
Figure 259593DEST_PATH_IMAGE022
The average speed of the vehicle is taken as
Figure 100002_DEST_PATH_IMAGE026
Wherein
Figure 100002_DEST_PATH_IMAGE028
，
Figure 901927DEST_PATH_IMAGE006
The course of the period is
Figure 100002_DEST_PATH_IMAGE030
Wherein
Figure 100002_DEST_PATH_IMAGE032
Is the current time
Figure 506084DEST_PATH_IMAGE010
Vehicle speed;
translating the center line of the road to the position of each vehicle at the current moment, and intercepting the length of the translated curve as
Figure 100002_DEST_PATH_IMAGE034
The arc length of (a) at the node is the first time of the next moment
Figure 942881DEST_PATH_IMAGE010
Position of vehicle
Figure 100002_DEST_PATH_IMAGE036
Further obtain the surroundings
Figure 632489DEST_PATH_IMAGE022
Position of vehicle
Figure 100002_DEST_PATH_IMAGE038
；
For the own vehicle
Figure 100002_DEST_PATH_IMAGE040
The travel distance is
Figure 100002_DEST_PATH_IMAGE042
In conjunction with the current time of day
Figure 78513DEST_PATH_IMAGE002
The position of the vehicle can be determined
Figure 943701DEST_PATH_IMAGE004
Position of time of day
Figure 100002_DEST_PATH_IMAGE044
。
Further, since the vehicle is in
Figure 673104DEST_PATH_IMAGE006
Within a time rangeThe average speed deviation range is
Figure 459795DEST_PATH_IMAGE024
Then around
Figure 709510DEST_PATH_IMAGE022
Vehicle presence
Figure 100002_DEST_PATH_IMAGE046
And (4) a speed combination is selected, and the environment influence value with the largest environment influence value in all the speed combinations is used as the environment influence value at the next moment.
Further, the method for calculating the change in the environmental influence value includes:
Figure 288259DEST_PATH_IMAGE006
variation of influence value of ambient environment within time period
Figure 100002_DEST_PATH_IMAGE048
Wherein
Figure 100002_DEST_PATH_IMAGE050
Is composed of
Figure 66859DEST_PATH_IMAGE004
The ambient influence value at the moment of time,
Figure 100002_DEST_PATH_IMAGE052
is composed of
Figure 731059DEST_PATH_IMAGE002
The ambient influence value at the moment of time,
Figure 100002_DEST_PATH_IMAGE054
to normalize the tuning parameters.
Further, the driver is obtained
Figure 50045DEST_PATH_IMAGE006
The actual rate of distraction over the time period is determined by:
obtained by means of video monitoring equipment
Figure 93087DEST_PATH_IMAGE006
Monitoring video images of the driver during the time period; obtaining
Figure 839326DEST_PATH_IMAGE006
The time length of the face of the driver facing other front directions in the time period is utilized to account for the face of the driver facing other directions
Figure 459663DEST_PATH_IMAGE006
The proportion of the time period is obtained
Figure 316761DEST_PATH_IMAGE006
Actual rate of distraction over time;
and when the actual attention dispersion ratio is larger than the attention dispersion ratio threshold corresponding to the environment influence value variation, judging that the driver has the attention dispersion violation behavior.
In a second aspect, the present invention provides an artificial intelligence-based illegal driving recognition system, including:
an information acquisition unit for acquiring the current time
Figure 276627DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
a first calculating unit for using the obtained current time
Figure 131450DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 442346DEST_PATH_IMAGE002
An environmental impact value;
a second calculation unit for calculating a current time
Figure 837555DEST_PATH_IMAGE002
Predicting the next time by the speed information, position information, vehicle type information and curvature information of the road
Figure 714244DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 67865DEST_PATH_IMAGE004
An environmental impact value;
a third calculating unit for calculating a time point according to the next time
Figure 538161DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 737061DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure 405940DEST_PATH_IMAGE006
Determining the variation of the environmental influence value in the time period, and determining the time distraction ratio threshold value corresponding to different variation;
an attention judging unit for acquiring driver presence
Figure 992779DEST_PATH_IMAGE006
And comparing the actual attention dispersion ratio with an attention dispersion ratio threshold value in the time period, and judging whether the driver violates the rules according to the comparison result.
Compared with the traditional technical scheme, the invention has the beneficial effects that:
1. the influence of surrounding vehicles and roads is comprehensively considered, and violation judgment boundaries of driver attention detection are given, so that the judgment standard is more reasonable and scientific;
2. the method can prevent the judgment condition from being given mechanically, and avoid the condition that the violation judgment standard does not meet the actual requirement.
Drawings
Embodiments herein will be described in more detail, by way of example only, with reference to the accompanying drawings, in which:
FIG. 1 is a block diagram of an artificial intelligence based illegal driving identification method of the present invention.
FIG. 2 is a block diagram of the environmental impact value calculation step in artificial intelligence based violation driving recognition of the present invention.
FIG. 3 is a block diagram of an artificial intelligence based violation driving recognition system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention 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 invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature; in the description of the present embodiment, "a plurality" means two or more unless otherwise specified.
Fig. 1 is a block diagram of an artificial intelligence-based illegal driving identification method according to the present embodiment, and as shown in fig. 1, the artificial intelligence-based illegal driving identification method includes the following steps:
step S101: obtaining the current time
Figure 12688DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
first, two-dimensional position location information of the speed V, GPS of the own vehicle (own vehicle) at the present time is obtained by the sensor.
And secondly, extracting the position information of the vehicles around the current moment, wherein the position information comprises the current road section division and the surrounding vehicle information extraction:
(1) current road section division: translating the central curve to the position of the vehicle, and respectively intercepting the central curve in front of and behind the position of the vehicle
Figure 952962DEST_PATH_IMAGE020
Obtaining nodes from curve segments of rice
Figure 100002_DEST_PATH_IMAGE056
Respectively through the node
Figure 741926DEST_PATH_IMAGE056
Making a perpendicular line to the road boundary to obtain an area boundary;
(2) method for acquiring running speed of other vehicles around own vehicle on current road section in vehicle networking mode
Figure 100002_DEST_PATH_IMAGE058
Position, position
Figure 100002_DEST_PATH_IMAGE060
And vehicle type information.
And finally, acquiring curvature information of the current road section, wherein the specific implementation method comprises the following steps:
(1) the vertical line is drawn from the position of the vehicle to the center line of the road at the current moment to obtain the foot
Figure 100002_DEST_PATH_IMAGE062
；
(2) Sober operator is used for processing the road center line to obtain the edge characteristics of the road center line, and the derivation method is used for processing the edge characteristics of the road center line to obtain the drop foot point
Figure 968508DEST_PATH_IMAGE062
Curvature data of
Figure DEST_PATH_IMAGE064
。
Step S102: using the acquired current time
Figure 538030DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 78732DEST_PATH_IMAGE002
An environmental impact value;
since the vehicle is moving continuously, and the tightness degree of the attention detection system cannot be adjusted and detected in real time due to the real-time change of the environment around the vehicle, the change of the environmental influence value at different times is used as the tightness degree judgment threshold of the attention detection system in this embodiment.
In this embodiment, if the difference between the next time and the current time is large, a new situation will occur, and the necessity of paying attention to the front at the current time is high, and if the difference between the next time and the current time is zero, that is, the own vehicle and the surrounding vehicles move in a rigid body in an abstract manner as a whole, the necessity of paying attention to the front will not be high.
The following is to calculate the environmental impact value at the current time in this embodiment with reference to fig. 2, fig. 2 shows a block diagram of the step of calculating the environmental impact value in the artificial intelligence based illegal driving recognition method, and the calculation of the environmental impact value shown in fig. 2 includes the following contents:
step S201, calculating the area ratio of each vehicle around:
the vehicle type information of surrounding vehicles acquired by the Internet of vehicles can be used for determining the length and width value data of vehicle bodies of different vehicle types
Figure DEST_PATH_IMAGE066
And further the projected area of the bounding box of the surrounding vehicle is:
Figure DEST_PATH_IMAGE068
then the area of all surrounding vehicles is
Figure DEST_PATH_IMAGE070
。
Calculating the road area of the current road section
Figure DEST_PATH_IMAGE072
: the area of the area enclosed by the boundary line of the two areas and the boundary of the two roads is the area of the road section where the vehicle is located at the current moment and is recorded as the area of the road section where the vehicle is located
Figure DEST_PATH_IMAGE074
The area can be approximately calculated by a sector calculation formula, so that the first road section in the current road section
Figure 53029DEST_PATH_IMAGE010
The area occupation ratio of the vehicle is as follows:
Figure DEST_PATH_IMAGE076
。
further obtaining the area per lane ratio of each vehicle around
Figure DEST_PATH_IMAGE078
。
Step S202, calculating the distance between the vehicle and other vehicles around;
suppose that
Figure 857037DEST_PATH_IMAGE010
The position of the vehicle is
Figure DEST_PATH_IMAGE080
Position information of own vehicle
Figure DEST_PATH_IMAGE082
Whereby the distance between the vehicles is
Figure DEST_PATH_IMAGE084
。
Further obtaining the distance between the vehicle and all the vehicles around the road section
Figure DEST_PATH_IMAGE086
Step S203, calculating the orientation weight of each vehicle around:
because its influence effect of the vehicle in different position is different, and the influence in the vehicle dead ahead is great, and the influence in rear is less relatively, and there is the possibility of overtaking in the left vehicle, therefore this embodiment gives different position weights to the car in different positions, and the concrete mode is:
firstly, the azimuth angle of the vehicle is calculated:
Figure DEST_PATH_IMAGE088
then, calculating the azimuth weight:
Figure DEST_PATH_IMAGE090
。
step S204, calculating the ambient environment influence value: the influence value of the surrounding vehicle is mainly influenced by the distance between the own vehicle and the surrounding vehicle, the vehicle speed, the vehicle area ratio, and the front and rear vehicle weights.
First, the influence value of each vehicle is calculated
Figure DEST_PATH_IMAGE092
Wherein
Figure DEST_PATH_IMAGE094
Is the current time
Figure 445013DEST_PATH_IMAGE010
Vehicle with a motorThe speed of travel of the vehicle,
Figure DEST_PATH_IMAGE096
is the current time
Figure 789407DEST_PATH_IMAGE010
The area of the vehicle is the ratio of the road,
Figure DEST_PATH_IMAGE098
is the current time
Figure 615281DEST_PATH_IMAGE010
The vehicle orientation of the vehicle affects the weight,
Figure DEST_PATH_IMAGE100
is the current time
Figure 590190DEST_PATH_IMAGE010
Distance of the vehicle.
Secondly, calculating the influence value of all vehicles on the road section at the current moment as
Figure DEST_PATH_IMAGE102
Finally taking into account the road curvature
Figure 71987DEST_PATH_IMAGE064
The influence of (2), the current time (
Figure 282388DEST_PATH_IMAGE002
Time of day) environmental impact value
Figure 900451DEST_PATH_IMAGE052
Comprises the following steps:
Figure DEST_PATH_IMAGE104
。
step S103: according to the current time
Figure 46262DEST_PATH_IMAGE002
Speed information and position of own and surrounding vehiclesPredicting the next moment by the information, the vehicle type information and the curvature information of the road
Figure 749776DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 498289DEST_PATH_IMAGE004
The environmental impact value specifically includes:
analyzing the distribution of the vehicles around the next moment, and predicting the vehicles according to the speed information of the current vehicles
Figure DEST_PATH_IMAGE106
The method includes the steps that the vehicle travels in a time interval, the speed of the vehicle changes in real time during the traveling process, in order to reflect speed change information of the vehicle in the time interval, a speed change range is introduced to speed change of the vehicle during prediction, a plurality of vehicle distribution conditions are obtained by utilizing the speed change range, and in order to guarantee driving safety to the maximum degree, the distribution with the highest requirement on driving energy is selected from all possible vehicle distributions to serve as vehicle parameters for determining environmental influence values.
In the embodiment, the speed change range is provided, the prediction is performed in a traversal mode within the range, the result with the largest difference compared with the current moment is predicted, and the situation that the attention of a driver exceeds a threshold value but is not prompted is avoided.
First, the next time is predicted (
Figure 236438DEST_PATH_IMAGE004
Time of day) vehicle position: using position information of vehicles around the current time
Figure 287570DEST_PATH_IMAGE060
And velocity
Figure 212801DEST_PATH_IMAGE058
Information, in order to achieve as real-time as possible the attention detection systemThe time interval is shortened as much as possible, i.e.
Figure 702688DEST_PATH_IMAGE106
The value is as small as possible. If the vehicle speed is limited to a fixed variation interval with a small time interval, the range deviation of the speed can be determined empirically from the time interval
Figure 357660DEST_PATH_IMAGE024
To a first order
Figure 907591DEST_PATH_IMAGE010
The vehicle is exemplified by
Figure 320117DEST_PATH_IMAGE006
The average speed in the time range is in the range of
Figure DEST_PATH_IMAGE108
。
Speed and in this embodiment
Figure 551378DEST_PATH_IMAGE024
Are all integers, so that each vehicle exists in the speed range
Figure DEST_PATH_IMAGE110
The speed is taken and all vehicles have
Figure 60857DEST_PATH_IMAGE046
And (4) speed combination.
The way of solving the influence value of the vehicle at the next moment is illustrated by taking a speed combination as an example, and the surrounding is assumed
Figure 781689DEST_PATH_IMAGE022
The speed of the vehicle being taken as
Figure 884774DEST_PATH_IMAGE026
Wherein
Figure DEST_PATH_IMAGE112
Knowing the speed, the distance can be determined
Figure 716464DEST_PATH_IMAGE030
。
Assuming that all the surrounding vehicle driving tracks are parallel to the road center line, the road center line can be translated to the position of each vehicle at the current moment, and the length of the curve is cut into
Figure 89238DEST_PATH_IMAGE034
The arc length of (a) at the node is the first time of the next moment
Figure 980971DEST_PATH_IMAGE010
Position of vehicle
Figure 368089DEST_PATH_IMAGE036
. Class the method to find surroundings
Figure 675574DEST_PATH_IMAGE022
Position of vehicle
Figure 97328DEST_PATH_IMAGE038
。
Since the greater the traveling speed of the vehicle, the more effort is required, the maximum value of the speed range, i.e., the maximum value of the speed range, is taken by the own vehicle in the present embodiment
Figure 222279DEST_PATH_IMAGE040
Whereby the travel distance of the vehicle is
Figure DEST_PATH_IMAGE114
。
Determine that the own vehicle is
Figure 96694DEST_PATH_IMAGE004
Position of time of day
Figure 473449DEST_PATH_IMAGE044
Then the way of dividing the road section area is carried out, and the vehicle can be obtained
Figure 749709DEST_PATH_IMAGE004
Section of road in which the moment is located
Figure DEST_PATH_IMAGE116
Then select out the Chinese characters belonging to
Figure 311141DEST_PATH_IMAGE116
Vehicles in the road section, i.e.
Figure DEST_PATH_IMAGE118
To obtain
Figure DEST_PATH_IMAGE120
The vehicle belongs to the vehicle in the area.
Then, the method described in step S102 can be used to find
Figure 876114DEST_PATH_IMAGE010
Area ratio of vehicle
Figure DEST_PATH_IMAGE122
Distance, distance
Figure DEST_PATH_IMAGE124
Azimuth weight
Figure DEST_PATH_IMAGE126
And then get the first
Figure 118877DEST_PATH_IMAGE010
The influence value of the vehicle is
Figure DEST_PATH_IMAGE128
Then all vehicles have an influence value of
Figure DEST_PATH_IMAGE130
。
Further obtain
Figure 843119DEST_PATH_IMAGE046
At the time of seed speed combinationThe maximum value of the vehicle influence values in all the speed combinations is used as the vehicle influence value at the next moment
Figure DEST_PATH_IMAGE132
Then, the method of step S101 is used to obtain the curvature of the road at the current moment
Figure DEST_PATH_IMAGE134
Finally, calculate to obtain
Figure 716397DEST_PATH_IMAGE004
Time of day environmental impact value
Figure DEST_PATH_IMAGE136
。
Step S104: according to the next moment
Figure 627721DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 143016DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure 331552DEST_PATH_IMAGE006
The method includes the following steps that the change amount of the environmental influence value in the time period determines the time distraction ratio threshold value corresponding to different change amounts, and specifically includes:
the driving effort may be required differently for different changes in the surrounding environment, for example, the surrounding vehicles may become more crowded within a certain period of time, and thus more effort may be required to cope with the environmental changes, and the driver's effort may be required differently due to the change in the curvature of the road, so that the driving effort may be determined by comparing the changes in the influence values of the surrounding environment within a certain period of time.
Computing
Figure 641311DEST_PATH_IMAGE006
Variation of influence value of ambient environment within time period
Figure 977614DEST_PATH_IMAGE048
Wherein
Figure 358917DEST_PATH_IMAGE050
Is composed of
Figure 464276DEST_PATH_IMAGE004
The ambient influence value at the moment of time,
Figure 944936DEST_PATH_IMAGE052
is composed of
Figure 440640DEST_PATH_IMAGE002
The ambient influence value at the moment of time,
Figure 563316DEST_PATH_IMAGE054
for normalizing the regulation parameter, the parameter is used for limiting the ambient influence value at two time points
Figure DEST_PATH_IMAGE138
Is used to adjust the driver distraction ratio given a suitable threshold. The two parameters need to be adjusted in time according to the values of the two ambient environment influence values.
Determining a driver distraction ratio threshold
Figure DEST_PATH_IMAGE140
Figure DEST_PATH_IMAGE142
，
In this example
Figure DEST_PATH_IMAGE144
，
Figure DEST_PATH_IMAGE146
，
Figure DEST_PATH_IMAGE148
And
Figure DEST_PATH_IMAGE150
is an empirical threshold value and is timely adjusted according to the acquired data in the subsequent system operation process.
Step S105: get driver at
Figure 916325DEST_PATH_IMAGE006
Comparing the actual distraction ratio with a distraction ratio threshold value in the actual distraction ratio in the time period, and judging whether the driver violates rules according to the comparison result, wherein the method specifically comprises the following steps:
firstly, utilizing video monitoring equipment to obtain a monitoring video image of the position of a driver in the driving process of a vehicle; taking the acquired video image as a data set, marking the image of the face of the driver facing to the front driving window as 1, and marking the image of the face facing to other directions as 0 to obtain the label data of the video image;
inputting video images and label data into a DNN network for training, wherein the DNN network is of an Encoder-FC structure, the Encoder extracts face orientation features, and the FC outputs whether the face faces towards a front driving window or not, wherein the training set accounts for 80%, the verification set accounts for 20%, and a trained network is obtained; the trained network can obtain the time length of the face of the driver facing to other front directions in a certain time period, in the embodiment, the driver is in a distraction state when the face of the driver faces to other directions, and the proportion of the face of the driver facing to other directions in the time period is the distraction ratio;
and when the actual attention dispersion ratio is larger than the attention dispersion ratio threshold corresponding to the environment influence value variation, judging that the driver has the attention dispersion violation behavior.
The system of an embodiment of the present disclosure is described below with reference to fig. 3, where fig. 3 shows a block diagram of an artificial intelligence based offending drive recognition system, which as shown includes the following:
an information acquisition unit 301 for obtaining the current time
Figure 771148DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
a first calculating unit 302, configured to utilize the obtained current time
Figure 816465DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 477253DEST_PATH_IMAGE002
An environmental impact value;
a second calculating unit 303 for calculating a current time
Figure 353942DEST_PATH_IMAGE002
Predicting the next time by the speed information, position information, vehicle type information and curvature information of the road
Figure 707563DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 974597DEST_PATH_IMAGE004
An environmental impact value;
a third calculating unit 304 for calculating according to the next time
Figure 111180DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 45638DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure 632477DEST_PATH_IMAGE006
Determining the variation of the environmental influence value in the time period, and determining the time distraction ratio threshold value corresponding to different variation;
attention judging unit 305 for acquiring the presence of the driver
Figure 121227DEST_PATH_IMAGE006
And comparing the actual attention dispersion ratio with an attention dispersion ratio threshold value in the time period, and judging whether the driver violates the rules according to the comparison result.
Compared with the traditional technical scheme, the method comprehensively considers the influences of surrounding vehicles and roads, and provides the violation judgment boundary for the driver attention detection, so that the judgment standard is more reasonable and scientific; the method can prevent the judgment condition from being given mechanically, and avoid the condition that the violation judgment standard does not meet the actual requirement.
The use of words such as "including," "comprising," "having," and the like in this disclosure is an open-ended term that means "including, but not limited to," and is used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that the various components or steps may be broken down and/or re-combined in the methods and systems of the present invention. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The above-mentioned embodiments are merely examples for clearly illustrating the present invention and do not limit the scope of the present invention. It will be apparent to those skilled in the art that other variations and modifications may be made in the foregoing description, and it is not necessary or necessary to exhaustively enumerate all embodiments herein. All designs identical or similar to the present invention are within the scope of the present invention.

Claims (8)

1. An illegal driving identification method based on artificial intelligence is characterized by comprising the following steps:
obtaining the current time
Figure DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
using the acquired current time
Figure 978665DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 36750DEST_PATH_IMAGE002
An environmental impact value;
according to the current time
Figure 82067DEST_PATH_IMAGE002
Predicting the next time by the speed information, position information, vehicle type information and curvature information of the road
Figure DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 742855DEST_PATH_IMAGE004
An environmental impact value;
according to the next moment
Figure 822807DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 645269DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure DEST_PATH_IMAGE006
The amount of change in the environmental impact value over a period of time,determining the attention dispersion ratio threshold corresponding to different variation quantities;
get driver at
Figure 315898DEST_PATH_IMAGE006
And comparing the actual attention dispersion ratio with an attention dispersion ratio threshold value in the time period, and judging whether the driver violates the rules according to the comparison result.
2. The artificial intelligence based illegal driving identification method according to claim 1, characterized in that the influencing factors of the environmental influence value include: the area occupation ratio of other surrounding vehicles; the distance between the own vehicle and other surrounding vehicles; the bearing weights of other surrounding vehicles.
3. The artificial intelligence-based illegal driving recognition method according to claim 2, characterized in that the environmental impact value calculation method is as follows:
Figure DEST_PATH_IMAGE008
wherein for the first
Figure DEST_PATH_IMAGE010
The vehicle is driven by the electric motor,
Figure DEST_PATH_IMAGE012
in order to be able to control the speed of travel,
Figure DEST_PATH_IMAGE014
in order to make the area of the film occupy the track ratio,
Figure DEST_PATH_IMAGE016
in order for its orientation to affect the weights,
Figure DEST_PATH_IMAGE018
is it andthe distance between the host vehicle and the host vehicle,
Figure DEST_PATH_IMAGE020
for the curvature data of the current road segment,
Figure DEST_PATH_IMAGE022
the number of vehicles in the current section.
4. The artificial intelligence-based illegal driving identification method according to claim 2, characterized in that the next moment in time
Figure 124585DEST_PATH_IMAGE004
The method for acquiring the speed and position information of the vehicle and surrounding vehicles comprises the following steps:
vehicle is at
Figure 59043DEST_PATH_IMAGE006
The average speed deviation range in the time range is
Figure DEST_PATH_IMAGE024
Then around
Figure 317986DEST_PATH_IMAGE022
The average speed of the vehicle is taken as
Figure DEST_PATH_IMAGE026
Wherein
Figure DEST_PATH_IMAGE028
，
Figure 478840DEST_PATH_IMAGE006
The course of the period is
Figure DEST_PATH_IMAGE030
Wherein
Figure DEST_PATH_IMAGE032
Is the current time
Figure 747010DEST_PATH_IMAGE010
The speed of the vehicle is set to be,
Figure DEST_PATH_IMAGE034
is the next moment
Figure 676920DEST_PATH_IMAGE010
Vehicle speed;
Figure DEST_PATH_IMAGE036
the average speed deviation value is obtained;
translating the center line of the road to the position of each vehicle at the current moment, and intercepting the length of the translated curve as
Figure DEST_PATH_IMAGE038
The arc length of (a) at the node is the first time of the next moment
Figure 637923DEST_PATH_IMAGE010
Position of vehicle
Figure DEST_PATH_IMAGE040
Further obtain the surroundings
Figure 145127DEST_PATH_IMAGE022
Position of vehicle
Figure DEST_PATH_IMAGE042
；
For the own vehicle
Figure DEST_PATH_IMAGE044
The travel distance is
Figure DEST_PATH_IMAGE046
In conjunction with the current time of day
Figure 92355DEST_PATH_IMAGE002
The position of the vehicle can be determined
Figure 1405DEST_PATH_IMAGE004
Position of time of day
Figure DEST_PATH_IMAGE048
，
Figure DEST_PATH_IMAGE050
As the speed of the own vehicle at the present time,
Figure DEST_PATH_IMAGE052
the speed of the own vehicle at the next time.
5. The artificial intelligence based illegal driving identification method according to claim 4, characterized in that vehicle is in
Figure 743096DEST_PATH_IMAGE006
The average speed deviation range in the time range is
Figure 737597DEST_PATH_IMAGE024
Then around
Figure 81990DEST_PATH_IMAGE022
Vehicle presence
Figure DEST_PATH_IMAGE054
And (4) a speed combination is selected, and the environment influence value with the largest environment influence value in all the speed combinations is used as the environment influence value at the next moment.
6. The method for identifying illegal driving based on artificial intelligence of claim 1, wherein the method for calculating the change of the environmental influence value is as follows:
Figure 720913DEST_PATH_IMAGE006
variation of influence value of ambient environment within time period
Figure DEST_PATH_IMAGE056
Wherein
Figure DEST_PATH_IMAGE058
Is composed of
Figure 23719DEST_PATH_IMAGE004
The ambient influence value at the moment of time,
Figure DEST_PATH_IMAGE060
is composed of
Figure 377952DEST_PATH_IMAGE002
The ambient influence value at the moment of time,
Figure DEST_PATH_IMAGE062
to normalize the tuning parameters.
7. The method for identifying illegal driving based on artificial intelligence of claim 1, characterized in that the driver is obtained
Figure 526037DEST_PATH_IMAGE006
The actual rate of distraction over the time period is determined by:
obtained by means of video monitoring equipment
Figure 144100DEST_PATH_IMAGE006
Monitoring video images of the driver during the time period; obtaining
Figure 352227DEST_PATH_IMAGE006
The duration that the face of the driver faces to other directions in the time period is utilized to account for the duration that the face of the driver faces to other directions
Figure 790162DEST_PATH_IMAGE006
The proportion of the time period is obtained
Figure 351724DEST_PATH_IMAGE006
Actual rate of distraction over time;
and when the actual attention dispersion ratio is larger than the attention dispersion ratio threshold corresponding to the environment influence value variation, judging that the driver has the attention dispersion violation behavior.
8. An artificial intelligence based illegal driving recognition system, comprising:
an information acquisition unit for acquiring the current time
Figure 89873DEST_PATH_IMAGE002
The speed, position information and vehicle type information of the vehicle in the current road section and surrounding vehicles are obtained, and the curvature information of the road is obtained through edge processing;
a first calculating unit for using the obtained current time
Figure 203323DEST_PATH_IMAGE002
Obtaining speed information, position information, vehicle type information and curvature information of the road of the self vehicle and the surrounding vehicles to obtain the current time
Figure 394133DEST_PATH_IMAGE002
An environmental impact value;
a second calculation unit for calculating a current time
Figure 884020DEST_PATH_IMAGE002
Predicting the next time by the speed information, position information, vehicle type information and curvature information of the road
Figure 86462DEST_PATH_IMAGE004
Speed information, position information, and curvature information of the road of the vehicle and the surrounding vehicle, and obtaining the next time based on the predicted information
Figure 370813DEST_PATH_IMAGE004
An environmental impact value;
a third calculating unit for calculating a time point according to the next time
Figure 48919DEST_PATH_IMAGE004
Environmental impact value and current time
Figure 342497DEST_PATH_IMAGE002
The environmental impact value is obtained at
Figure 524080DEST_PATH_IMAGE006
Determining the variation of the environmental influence value in the time period, and determining the time distraction ratio threshold value corresponding to different variation;
an attention judging unit for acquiring driver presence
Figure 979332DEST_PATH_IMAGE006
And comparing the actual attention dispersion ratio with an attention dispersion ratio threshold value in the time period, and judging whether the driver violates the rules according to the comparison result.
CN202111088570.7A 2021-09-16 2021-09-16 Illegal driving identification method and system based on artificial intelligence Active CN113525391B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111088570.7A CN113525391B (en) 2021-09-16 2021-09-16 Illegal driving identification method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111088570.7A CN113525391B (en) 2021-09-16 2021-09-16 Illegal driving identification method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN113525391A true CN113525391A (en) 2021-10-22
CN113525391B CN113525391B (en) 2021-12-10

Family

ID=78092797

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111088570.7A Active CN113525391B (en) 2021-09-16 2021-09-16 Illegal driving identification method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN113525391B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103150786A (en) * 2013-04-09 2013-06-12 北京理工大学 Non-contact type unmanned vehicle driving state measuring system and measuring method
CN105823479A (en) * 2016-03-04 2016-08-03 上海畅星软件有限公司 Driving behavior analysis method
US20170116485A1 (en) * 2015-10-21 2017-04-27 Ford Global Technologies, Llc Perception-Based Speed Limit Estimation And Learning
CN110610326A (en) * 2019-09-30 2019-12-24 广州大道信息科技有限公司 Driving management system based on driving data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103150786A (en) * 2013-04-09 2013-06-12 北京理工大学 Non-contact type unmanned vehicle driving state measuring system and measuring method
US20170116485A1 (en) * 2015-10-21 2017-04-27 Ford Global Technologies, Llc Perception-Based Speed Limit Estimation And Learning
CN105823479A (en) * 2016-03-04 2016-08-03 上海畅星软件有限公司 Driving behavior analysis method
CN110610326A (en) * 2019-09-30 2019-12-24 广州大道信息科技有限公司 Driving management system based on driving data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
高尚兵 等: "视觉协同的违规驾驶行为分析方法", 《智能系统学报》 *

Also Published As

Publication number Publication date
CN113525391B (en) 2021-12-10

Similar Documents

Publication Publication Date Title
US11990036B2 (en) Driver behavior monitoring
CN109927719B (en) Auxiliary driving method and system based on obstacle trajectory prediction
CN108437986B (en) Vehicle driving assistance system and assistance method
CN112712717B (en) Information fusion method, device and equipment
US11315026B2 (en) Systems and methods for classifying driver behavior
CN110077398B (en) Risk handling method for intelligent driving
CN112885145B (en) Crossing risk early warning method and device
EP3403219A1 (en) Driver behavior monitoring
KR20180092101A (en) Ecu, autonomous vehicle including the ecu, and method of determing driving lane for the same
WO2023197408A1 (en) Method and apparatus for determining vehicle speed control model training sample
CN114475651B (en) Blind area obstacle emergency avoidance method and device based on vehicle-road cooperation
EP3842307A1 (en) System and method for providing vehicle safety distance and speed alerts under slippery road conditions
CN113525391B (en) Illegal driving identification method and system based on artificial intelligence
CN111104824A (en) Method for detecting lane departure, electronic device, and computer-readable storage medium
CN113022586A (en) Vehicle behavior prediction method and device and storage medium
JP5125214B2 (en) Obstacle detection method and obstacle detection device
WO2023197409A1 (en) Speed control model generation method and apparatus, and vehicle control method and apparatus
CN114530057B (en) Vehicle early warning method and device, vehicle and storage medium
CN106203383B (en) Vehicle safety method for early warning based on image
CN108597217A (en) A kind of expressway traffic accident monitoring reminding method
KR101985074B1 (en) Adaptive cruise control apparatus and method thereof
CN114655203A (en) Driving assistance method, device, equipment and storage medium
US20220371587A1 (en) Method and Apparatus for Determining Vehicle Speed Control Model Training Sample
Islam Investigating the speed and rear-end collision relationship at urban signalized intersections
JP2022037779A (en) Road obstacle detection apparatus, road obstacle detection method, and program

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
GR01 Patent grant
GR01 Patent grant