CN108986473A - Vehicle mounted traffic unlawful practice identification and processing system and method - Google Patents

Vehicle mounted traffic unlawful practice identification and processing system and method Download PDF

Info

Publication number
CN108986473A
CN108986473A CN201710399848.XA CN201710399848A CN108986473A CN 108986473 A CN108986473 A CN 108986473A CN 201710399848 A CN201710399848 A CN 201710399848A CN 108986473 A CN108986473 A CN 108986473A
Authority
CN
China
Prior art keywords
vehicle
information
lane
traffic
unlawful practice
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
CN201710399848.XA
Other languages
Chinese (zh)
Inventor
赵来刚
胡伟
胡伟一
章健勇
钱威
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.)
NIO Holding Co Ltd
Original Assignee
NIO Nextev 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 NIO Nextev Ltd filed Critical NIO Nextev Ltd
Priority to CN201710399848.XA priority Critical patent/CN108986473A/en
Publication of CN108986473A publication Critical patent/CN108986473A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/017Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/16Anti-collision systems
    • G08G1/166Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

A kind of vehicle mounted traffic unlawful practice identification and processing system and method comprising: traffic rules are modeled, is facilitated and subsequent added, deletes inside the rule base of system, changing, searching some traffic rules;Using existing onboard sensor detection information, the extraction and fusion of information are then carried out, necessary input information needed for traffic rules carry out logic judgment is provided;The verifying and decision of traffic rules carry out statistics judgement using the relevant machine learning techniques of data and direct loic judge, obtain the conclusion for whether being breached and how being breached about traffic rules under current scene;After obtaining the conclusion that traffic rules are breached, the movement state information of vehicle when showing violation;Data relevant to event are stored and do teletransmission to system, and by In-vehicle networking.The present invention is stored and has been transmitted to the details for being related to traffic violations, and sufficient evidence can be provided for subsequent divisions of responsibility.

Description

Vehicle mounted traffic unlawful practice identification and processing system and method
Technical field
The present invention relates to advanced driving assistance system fields, and specifically, the present invention provides a kind of vehicle mounted traffics to know in violation of rules and regulations Not with processing system and method.
Background technique
Advanced driving assistance system (Advanced Driver Assistant System), abbreviation ADAS are to utilize peace Loaded on the miscellaneous sensor on vehicle, environmental data inside and outside first time collecting cart carries out quiet, dynamic object distinguishes The technical processing such as knowledge, detecting and tracking, so as to allow driver to discover the danger that may occur in the most fast time, with Arouse attention and improve the active safety technologies of safety.
ADAS use sensor mainly have camera, radar, laser and ultrasonic wave etc., can detect light, heat, pressure or Other variables for being used to monitor vehicle condition, are usually located inside the front/rear collision bumper, side-view mirror, control stick of vehicle or keep out the wind On glass.Based on the ADAS technology of early stage is mainly alarmed with passive type, when vehicle detection is to potential danger, it can sound an alarm and mention Awake motorist pays attention to abnormal vehicle or road conditions.For newest ADAS technology, active intervention is also very common.
But ADAS scheme in Vehicles Collected from Market and traffic rules are not introduced into, vehicle owner and traffic police can not be provided The evidence that sufficient accident responsibility divides;General automobile data recorder is also simple recording image information, to being related to traffic The key message of rule does not carry out detailed record and refers to so that vehicle owner clarifies responsibility.When traffic accident occurs, Often there is the partition problem of accident responsibility, event both sides often strongly go to shirk responsibility from oneself interests angle.This The case where sample, overtakes other vehicles in rear car acceleration, rear car is inserted under the situations such as vehicle, front truck car slipping, pedestrian's blackmail frequent occurrence.
Summary of the invention
The object of the present invention is to provide sufficient accident responsibility to vehicle owner and traffic police when traffic accident occurs The evidence of division.
It is a further object of the invention that when special scenes occur and driving and carrying out interaction appropriate, for example remind Front someone may have blackmail behavior, avoid unexpected accident.
For this purpose, it includes: sensor that the present invention, which devises a kind of vehicle mounted traffic unlawful practice identification and processing system, the system, Module, main processor modules, memory module;
The sensor module is configured to continue recording information of vehicles and ambient condition information;
The main processor modules include three units: signal processing and integrated unit, traffic rules judging unit, data Parsing and processing unit, signal processing and integrated unit are configured to the information of vehicles and ambient enviroment of the record of sensor module Information is extracted and is merged, and traffic rules judging unit is configured to prestore the unlawful practice of modelling, according to signal processing Input with integrated unit judges whether traffic rules are breached, and data parsing and processing unit are configured to be obtained according to judgement result Data after preset time and event trigger before taking event to trigger in preset time, and it is transmitted to memory module;
Memory module is configured to after obtaining the judgement result that traffic rules are breached, preset time before event is triggered And the data after event triggering in preset time are stored.
The sensor module and the main processor modules communicate to connect, the information transmission that sensor module will test To main processor modules;The main processor modules and memory module communicate to connect, and main processor modules will treated information It is transmitted to memory module.
Preferably, the sensor module includes vehicle-mounted camera, vehicle mounted electric magnetic wave radar, cartborne ultrasound wave radar, vehicle Carry one or more of laser radar and navigator.
Preferably, the information of vehicles include this vehicle speed, this vehicle yaw acceleration, this vehicle acceleration, his vehicle speed, he Vehicle acceleration, Ta Che are at a distance from this vehicle, the azimuth information of Ta Che and this vehicle;The ambient condition information include road etc. Grade, length, curvature, width, grade information and carriageway type, lane line, lane speed limit, lane width information.
Preferably, signal processing and integrated unit extract the information of vehicles and ambient condition information of sensor module record, And merge extracted information of vehicles and ambient condition information, to obtain this vehicle movement state information, his vehicle moves Status information, road information and lane information, wherein described vehicle movement state information is by described vehicle speed, this vehicle sideway Acceleration and Ben Che acceleration information fusion gained;His vehicle movement state information by his vehicle speed, his vehicle acceleration, Vehicle is at a distance from this vehicle and Ta Che merges gained with the azimuth information of this vehicle for he;The road information by the road etc. Grade, length, curvature, width, grade information fusion gained;The lane information is limited by the carriageway type, lane line, lane Speed, lane width information fusion gained.
Preferably, the unlawful practice include illegally overtake other vehicles, illegal lane change, one of front truck car slipping and blackmail behavior or It is a variety of.
Preferably, memory module is that vehicle-mounted memory and/or In-vehicle networking ECU, the memory module touch the event Data after preset time and event trigger before sending out in preset time are stored into vehicle-mounted memory, or pass through In-vehicle networking ECU is stored to cloud.
Preferably, the system also includes output modules violating the regulations, after obtaining the judgement result that traffic rules are breached, disobey Chapter output module shows violation information.
Preferably, the system also includes network transmission module, network transmission module can be by In-vehicle networking by event Data after preset time and event trigger before triggering in preset time carry out remote transmission.
Preferably, output module violating the regulations includes that instrument or middle control display screen or the electronics communicated with electronic system in vehicle are set It is standby.
Preferably, network transmission module obtains communication by the network system of In-vehicle networking and the police, before event is triggered Data after preset time and event triggering in preset time carry out remote transmission to the police.
The present invention has also been devised a kind of traffic violations Activity recognition and processing method based on vehicle-mounted multisensory, including with Lower step:
Unlawful practice is modeled and is added in traffic rules library by the foundation of S1, traffic rules library, facilitates subsequent handing over It adds, delete, changing, searching some traffic rules inside logical rule base;
The extraction and fusion of S2, information, information of vehicles and ambient condition information are persistently recorded, and by the information of record into Row extracts and fusion, necessary input information needed for obtaining traffic rules judgement;
The verifying and decision of S3, traffic rules carry out logic judgment to the necessary input information, obtain current scene Under the traffic rules conclusion that whether is breached and how to be breached, after obtaining the conclusion that traffic rules are breached;
If the traffic rules under S4, current scene are breached, data relevant to event are stored
Preferably, the unlawful practice in step S1 include illegally overtake other vehicles, illegal lane change, front truck car slipping and blackmail behavior One of or it is a variety of.
Preferably, when the unlawful practice in step S1 is illegally to overtake other vehicles, necessary input letter described in step 2 Breath include the lane line information of present road, present road current lane and side lane speed-limiting messages and this vehicle movement The movement state information of status information, side lane state of motion of vehicle information or vehicle of jumping a queue;The logic in step S3 Judgement include relatively side lane vehicle or vehicle of jumping a queue speed whether be more than the affiliated lane of present road speed limit;Step S4 Described in data relevant to event include that lane where the front and back video of preset time, this vehicle speed, this vehicle occurs for event Speed limit, the speed limit in lane where the speed of illegal passing vehicle and illegal passing vehicle.
Preferably, when the unlawful practice in step S1 is illegal lane change, necessary input letter described in step 2 Breath includes the lane line information of present road, the speed-limiting messages in each lane of present road, the motion state for vehicle of jumping a queue, this vehicle Motion state and Ben Che and front truck range information;The logic judgment in step S3 include judgement jump a queue vehicle whether Whether this vehicle is greater than the length of a vehicle body at a distance from front truck when being compacted line, yellow line, or jumping a queue;Described in step S4 with The relevant data of event include that the video of front and back preset time, the lane line information of present road, present road occur for event The range information of the speed-limiting messages in each lane, the motion state for vehicle of jumping a queue, the motion state of this vehicle and Ben Che and front truck.
Preferably, when the unlawful practice in step S1 is front truck car slipping, necessary input letter described in step 2 Breath includes the motion state of front truck;The logic judgment in step S3 includes the speed and acceleration for judging front truck and whether having backward Degree;Data relevant to event described in step S4 include that the front and back video of preset time and the movement shape of front truck occur for event State.
Preferably, when the unlawful practice in step S1 is blackmail behavior,
Necessary input information described in step 2 include the type of current object, current object at a distance from this vehicle, when The vertically and horizontally velocity variations of preceding object and the vertically and horizontally acceleration change of current object;The logic judgment in step S3 includes Judge that current object leaves the movement state information of current object in the time of danger zone and whether mutates;Institute in step S4 The data relevant to event stated include that the front and back video of preset time, the type for referring to current object, current object occur for event At a distance from this vehicle, vertically and horizontally velocity variations and vertically and horizontally acceleration change.
Preferably, the information of vehicles include this vehicle speed, this vehicle yaw acceleration, this vehicle acceleration, his vehicle speed, he Vehicle acceleration, Ta Che are at a distance from this vehicle, the azimuth information of Ta Che and this vehicle;The ambient condition information include road etc. Grade, length, curvature, width, grade information and carriageway type, lane line, lane speed limit and lane width information.
Preferably, the information of vehicles of record and ambient condition information are extracted and are merged packet described in step S2 It includes: extracting the information of vehicles and ambient condition information of record, and extracted information of vehicles and ambient condition information are melted It closes, to obtain this vehicle movement state information, his vehicle movement state information, road information and lane information, wherein described vehicle Movement state information merges gained by described vehicle speed, this vehicle yaw acceleration and Ben Che acceleration information;His vehicle is transported Dynamic status information is by his vehicle speed, his vehicle acceleration, Ta Che at a distance from this vehicle and the azimuth information of Ta Che and this vehicle Fusion gained;The road information is by the grade of the road, length, curvature, width, grade information fusion gained;The vehicle Road information is by the carriageway type, lane line, lane speed limit, lane width information fusion gained.
Preferably, the method also includes step S5: being done data relevant to event in step S4 by In-vehicle networking Teletransmission operation makes reference for subsequent evidence obtaining.
A kind of computer readable storage medium has also been devised in the present invention, for storing computer instruction, described instruction by The step of one computer or processor realize method as mentioned when executing.
A kind of electronic equipment, including processor and memory has also been devised in the present invention, is stored with calculating in the memory Machine instruction, the processor realize the step in the method when executing described instruction.
By above-mentioned technical proposal, the present invention is at least had the advantage that
1, the data before the present invention triggers event in preset time and after event triggering in preset time store, and are Subsequent divisions of responsibility provides sufficient evidence;
2, it is interacted actively with driver when special scenes occur, it can be to avoid unexpected accident.
3, it can choose and provide field data to the police in time, the equal behaviors that prevent from destorying the scene are to the unfavorable shadow of duty goal It rings.
4, the existing advanced driving assistance system of vehicle can be made full use of, structure is simple, at low cost.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention, And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the invention can It is clearer and more comprehensible, it is special below to lift preferred embodiment, and cooperate attached drawing, detailed description are as follows.
Detailed description of the invention
General frame figure Fig. 1 of the invention;
The traffic violations Activity recognition and processing method flow chart of vehicle-mounted multisensory Fig. 2 of the invention;
Decision flowchart of illegally overtaking other vehicles Fig. 3 of the invention;
Illegal lane change decision flowchart Fig. 4 of the invention;
Front truck car slipping decision flowchart Fig. 5 of the invention;
Blackmail behavior decision flowchart Fig. 6 of the invention.
Main parts size description of symbols:
1, sensor module 11, vehicle mounted electric magnetic wave radar 12, vehicle-mounted camera 13, cartborne ultrasound wave radar
14, mobile lidar 15, navigator 2, main processor modules 21, information processing and integrated unit
22, traffic rules judging unit 23, data parsing and processing unit 3, memory module
31, vehicle-mounted 32 In-vehicle networking ECU 4 of memory, display module violating the regulations
Specific embodiment
It is of the invention to reach the technical means and efficacy that predetermined goal of the invention is taken further to illustrate, below in conjunction with Attached drawing and preferred embodiment, to the traffic violations identification proposed according to the present invention based on vehicle-mounted multisensory and processing system its Specific embodiment, structure, method, step, feature and its effect, detailed description is as follows.
On the hardware foundation of the existing radar, camera installed the present invention is based on traditional ADAS function, according to existing Public traffic rules library, it is established that internal distinctive traffic rules logical base, radar, camera persistently record surrounding vehicles, The movement state information of pedestrian or its moving object call the traffic rule inside traffic logical base when specific scene occurs Then judge, obtain the violation vehicle responsibility of current scene, and when output end shows violation vehicle movement state information, it is defeated Outlet can be instrument, middle control display screen also or the electronic equipment that can communicate with Department of Electronics in vehicle, and pass through with the police The agreements such as network transmit the information of necessary evidence, prevent responsible party from deliberately changing the erroneous judgement that responsibility is caused at scene.
As shown in Figure 1, the traffic violations identification of the invention based on vehicle-mounted multisensory and processing system mainly include passing Sensor module 1, main processor modules 2, memory module 3, wherein
The sensor module 1 is configured to continue recording information of vehicles and ambient condition information;
The main processor modules 2 include three units: signal processing and integrated unit 21, traffic rules judging unit 22, data parsing and processing unit 23, signal processing and integrated unit 21 are configured to believe on the vehicle of the record of sensor module Breath and ambient condition information are extracted and are merged, and traffic rules judging unit 22 is configured to prestore the violation row of modelling For, judge whether the traffic rules under current scene are breached according to the input of signal processing and integrated unit, data parsing and Processing unit 23 is configured to according to the number after preset time before judgement result acquisition event triggering and event triggering in preset time According to, and it is transmitted to memory module 3;
Memory module 3 is configured to after obtaining the judgement result that traffic rules are breached, preset time before event is triggered And the data after event triggering in preset time are stored.
Preferably, the system can also include output module 4 violating the regulations.
Sensor of the invention module 1 can obtain the information of ambient condition information and vehicle well, and be subsequent Traffic rules judgement provides sufficient data, such as can be used to advanced driving assistance system and provide each biography of sensing data Sensor, such as vehicle-mounted camera 11 (vehicle-mounted camera may include vehicle-mounted front camera and/or vehicle-mounted look around camera), vehicle Carry electromagnetic radar 12, cartborne ultrasound wave radar 13, laser radar 14, navigator 15 etc.;Be also possible to it is existing in vehicle but Not necessarily advanced driving assistance system provides the sensor of sensing data.The present invention utilizes sensor module 1, lasting to record Information of vehicles and ambient condition information.Single-sensor or simple sensor combinations can only meet the realization of specific function, lead to Cross signal processing and integrated unit 21 information of multiple sensors is subjected to fusion could be to ambient enviroment, peripheral motor and static The feature of object is more preferably recorded.It is the advanced common technology in driving assistance system field by the information fusion of multiple sensors Means, such as get up altogether by the transverse shifting feature for the object that camera obtains and by the longitudinal movement characteristic synthetic that radar measures With the motion feature of composition object.Sensor module 1 continues recording information of vehicles and ambient condition information, wherein vehicle-mounted camera 11 identification target types are vehicle, pedestrian, bicycle or barrier etc., and provide the lane line of target, speed, acceleration and Azimuth;Vehicle mounted electric magnetic wave radar 12 provides speed, acceleration and the azimuth of target;Cartborne ultrasound wave radar 13 provides low coverage From obstacle information, mobile lidar 14 provides the point cloud information of ambient enviroment, target, navigator 15 provide road information, Location information, lane information and POI information etc..
Signal processing and integrated unit 21 extract the information of vehicles and ambient condition information of sensor module (1) record, institute State information of vehicles include this vehicle speed, this vehicle yaw acceleration, this vehicle acceleration, his vehicle speed, his vehicle acceleration, Ta Che and this The azimuth information of the distance of vehicle, Ta Che and this vehicle;The ambient condition information includes the grade, length, curvature, width of road Degree, grade information and carriageway type, lane line, lane speed limit, lane width information.Signal processing and integrated unit 21 are further Extracted information of vehicles and ambient condition information are merged, to obtain this vehicle movement state information, his vehicle moves shape State information, road information and lane information, wherein described vehicle movement state information is added by described vehicle speed, this vehicle sideway Speed and Ben Che acceleration information fusion gained;His vehicle movement state information by his vehicle speed, his vehicle acceleration, he Vehicle is at a distance from this vehicle and Ta Che merges gained with the azimuth information of this vehicle;The road information by the road grade, Length, curvature, width, grade information fusion gained;The lane information is by the carriageway type, lane line, lane speed limit, vehicle Road width information fusion gained.Traffic rules judging unit 22 is the unlawful practice for prestoring modelling, according to signal processing and The input of integrated unit judges whether the traffic rules under current scene are breached, and the unlawful practice includes illegally overtaking other vehicles, being non- One of method lane change, front truck car slipping and blackmail behavior are a variety of, and it further includes other that the unlawful practice, which is not limited to above-mentioned several, Unlawful practice.After data parsing and processing unit 23 then obtain the preceding preset time of event triggering and event triggering according to judgement result Data in preset time, and it is transmitted to memory module 3.
Memory module 3, including vehicle-mounted memory 31 and/or In-vehicle networking ECU32 will cache after obtaining judgement result In event trigger before data after preset time and event triggering in preset time stored, the preset time is according to visitor Family demand is set, and the memory module stores data into vehicle-mounted memory, or will be counted by In-vehicle networking ECU Cloud is arrived according to storage, it is subsequent to directly acquire.
Data can also be carried out remote transmission by In-vehicle networking ECU32 by the system, for example, the network system with the police System obtains communication, notifies at once when accident occurs about the collected critical data relevant to accident of this vehicle institute, meets A possibility that accident generation moment just obtains related real time data.Alternatively, communication transmitting device can also be separately provided, by phase It closes data and carries out remote transmission.
Output module 4 violating the regulations breaks rules and regulations the display of output module 4 in violation of rules and regulations after obtaining the judgement result that traffic rules are breached Information, the movement state information of vehicle or be the information for prompting user the to break rules and regulations when violation information is violating the regulations are described violating the regulations Output module 4 is set as when violation information instruction is transferred in reception, and the violation information of vehicle when showing violation may be alternatively provided as only Vehicle violation information when occurring just exporting violation for rule situation, can be arranged specific output condition according to the demand of user.It disobeys Chapter output module 4 preferably includes instrument and middle control display screen, may also comprise the electronic equipment that can be communicated with Department of Electronics in vehicle, Such as mobile phone, tablet computer etc..
The present invention also provides a kind of traffic violations Activity recognition and processing method based on vehicle-mounted multisensory, such as Fig. 2 It is shown, it mainly comprises the steps that
S1, traffic rules library pre-establish, and by traffic violations behavior modeling and are added in traffic rules library, specifically Include:
The foundation in traffic rules library carries out the abstract modeling of expert system to public traffic rules library, will be common Unlawful practice is all modeled and is added in traffic rules library, facilitate it is subsequent inside traffic rules library add, delete, change, Some traffic rules is searched, the later period can expand more rules, and the system configuration for inventing itself varies without;System operation Each period can provide input data to the Different Rule of rule base, draw a conclusion, and then pack when intercepting sensing data Specific rule classification and number.
The unlawful practice include illegally overtake other vehicles, illegal lane change, one of front truck car slipping and blackmail behavior or a variety of, institute It states unlawful practice and is not limited to above-mentioned several, further include other unlawful practices.
Modeling process includes: the input that every kind of traffic rules are arranged, output parameter, by a large amount of vehicle in every kind of traffic The lower training sample of rule is trained model, obtains the decision threshold of often middle traffic rules, most test sample to model into Row verifying, so that traffic rules be modeled.For judging that vehicle is jumped a queue, it is first determined the input and output of this traffic rules, Input vertically and horizontally speed, acceleration of front truck when jumping a queue for vehicle, with this vehicle distance, in the position in this vehicle lane, this vehicle speed, Position in this lane;Lateral distance, the relatively transverse speed of his vehicle and this vehicle when output occurs for behavior of jumping a queue.Then lead to Cross the training sample that a large amount of vehicle is jumped a queue this model be trained and obtain model parameter, finally with test sample to model into Row verifying, so that vehicle be jumped a queue modelling.
The extraction and fusion of S2, information, sensor module continue recording information of vehicles and ambient condition information, the vehicle Information include this vehicle speed, this vehicle yaw acceleration, this vehicle acceleration, his vehicle speed, his vehicle acceleration, Ta Che and this vehicle away from From, the azimuth information of Ta Che and this vehicle;The ambient condition information includes grade, length, curvature, width, the gradient of road Information and carriageway type, lane line, lane speed limit, lane width information.Extract information of vehicles and the week of sensor module record Environmental information is enclosed, and extracted information of vehicles and ambient condition information are merged, to obtain this vehicle motion state letter Breath, his vehicle movement state information, road information and lane information, wherein described vehicle movement state information is by the Ben Cheche Speed, this vehicle yaw acceleration and Ben Che acceleration information fusion gained;His vehicle movement state information by his vehicle speed, Vehicle acceleration, Ta Che are at a distance from this vehicle and Ta Che merges gained with the azimuth information of this vehicle for he;The road information is by institute State the grade, length, curvature, width, grade information fusion gained of road;The lane information is by the carriageway type, lane Line, lane speed limit, lane width information fusion gained;Go out traffic rules judgement needed for necessary input information.
The verifying and decision of S3, traffic rules carry out logic judgment to the necessary input information, obtain current scene Under the traffic rules conclusion that whether is breached and how to be breached;
The step S3 can be completed by following steps: the relevant machine learning of maintenance data divides current scene Class is ready to extract key message, carries out statistics judgement and logic judgment using the relevant machine learning techniques of data, The conclusion whether lower traffic rules of current scene are breached and how to be breached is obtained, is obtaining what traffic rules were breached Determine result after, show violation when vehicle violation information, the violation information be break rules and regulations when vehicle movement state information or Person is the information for prompting user to break rules and regulations;
If the traffic rules under S4, current scene are breached, data relevant to event are stored.
The data relevant to event can be relevant vehicle movement state information, his vehicle movement state information, road Road information and lane information etc.;
The method can also include: that step S4 data relevant to event are teletransmission behaviour by In-vehicle networking Make, relevant data are stored beyond the clouds by teletransmission, are made reference for subsequent evidence obtaining;Or it transmits relevant data to Police's network.
The triggering that traffic rules the determine generation either violating the regulations for the generation of collision accident.In the threshold that traffic rules determine When value is difficult to selected, the method that machine learning can be used carries out study to parameter and is calculated.
After decision is obtained a result, system will be before the event triggering in caching, when presetting after preset time and event triggering Interior data are stored into system, subsequent to directly acquire.Optionally, it directly can remotely be passed by In-vehicle networking It is defeated.For example, obtain communication with the network systems of the police, notify at once collected with accident phase about this vehicle institute when accident occurs The critical data of pass.
Method of the invention is illustrated using the non-limiting example of specific traffic violations below, wherein being previously mentioned Design parameter can subsequent adjustment.
Embodiment one is illegally overtaken other vehicles, as shown in figure 3, the lane line of present road where judging this vehicle by vehicle-mounted camera Information is obtained the speed-limiting messages of present road current lane and side lane by navigator, by vehicle mounted electric magnetic wave radar and is taken the photograph The motion state of this vehicle and the motion state of side lane vehicle or vehicle of jumping a queue are obtained as head, wherein the movement shape of vehicle State includes speed, acceleration and azimuth;The traffic rules of hypervelocity behavior judgement are carried out, i.e. side lane vehicle or vehicle of jumping a queue Speed be more than the affiliated lane of present road speed limit after, traffic rules are breached.Front and back occurs for storage event 1-5 minutes at this time Video and this vehicle speed, the speed limit in lane where this vehicle, the speed of illegal passing vehicle, illegal passing vehicle where vehicle The speed limit etc. in road, is then carried out data transmission by In-vehicle networking.
Embodiment two, illegal lane change, as shown in figure 4, the lane of present road where obtaining this vehicle by vehicle-mounted camera Line information is obtained the speed-limiting messages in each lane of present road by navigator, passes through vehicle mounted electric magnetic wave radar and camera The motion state for obtaining vehicle of jumping a queue obtains the range information of jump a queue vehicle and this vehicle by cartborne ultrasound wave radar, this vehicle Motion state is obtained by vehicle-mounted particular sensor such as velocity sensor, electric stabilizing system ESP, engine, vehicle-mounted motor etc.; Traffic rules modelling, when current vehicle is in a certain specific speed, when by road solid line, double solid line, yellow line etc., Qi Tache It cannot jump a queue, separately in the location that can be jumped a queue, if Ben Che follows front truck to travel, be less than spy in Ben Che and leading vehicle distance It is, for example, less than the length of a vehicle body in the case where determining threshold value, it is also illegally that similar scene can lead to that other vehicles, which are jumped a queue, Cross the mode constantly added come it is perfect, but realize input, output and processing mode be all with the former;Event triggering can be with Be divided into two kinds: accident occurs or traffic rules are breached, this configuration user is optional.Event occurs postscript copyist part and front and back occurs The video and the lane line information of present road of preset time, the speed-limiting messages in each lane of present road, vehicle of jumping a queue Motion state, the motion state of this vehicle and Ben Che and front truck range information, for subsequent evidence obtaining refer to.
Embodiment three, front truck car slipping, as shown in figure 5, obtaining the movement of front truck by vehicle mounted electric magnetic wave radar and camera State can determine whether front truck car slipping once front truck has speed backward, the fusion of this sensor, which can accurately obtain front truck, is The no velocity and acceleration having backward, the mode than simple automobile data recorder recording image are more accurate, reliable.
Example IV, blackmail behavior, as shown in fig. 6, may determine that current object by vehicle mounted electric magnetic wave radar and camera Body be pedestrian, bicycle or other similar configurations, and can accurately obtain current object at a distance from this vehicle, current object in length and breadth To velocity variations, vertically and horizontally acceleration change of current object etc.;Traffic rules modelling, in the current athletic posture of this vehicle Under, the time that current object leaves danger zone can be calculated by the athletic posture of current object, danger zone may be defined as Vehicle width both sides specific range, fore-and-aft distance may be selected to ignore, if the movement state information of current object occurs within this time It is mutated or there is true Horizontal Distance to be less than given threshold, then assert that traffic rules are breached and trigger data records behavior.
Aforementioned four embodiment is only described in conjunction with four kinds of unlawful practices and described is according to the present invention sensed based on vehicle-mounted more The traffic violations Activity recognition of device and the example of processing method, it should be understood that the other unlisted unlawful practices herein of processing may need Otherwise same sensing data.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the journey The step of preceding method is realized when sequence is executed by processor, so that traffic violations behavior is identified and handles.
The embodiment of the invention also provides a kind of electronic equipment, including processor and memory, meter is stored in memory The instruction of calculation machine, which realizes the step of realizing preceding method when executing described instruction, so that traffic violations behavior is known Not with processing.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, though So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention, any technology people for being familiar with this profession Member, without departing from the scope of the present invention, when the technology contents using the disclosure above make a little change or modification For the equivalent embodiment of equivalent variations, but anything that does not depart from the technical scheme of the invention content, according to the technical essence of the invention Any simple modification, equivalent change and modification to the above embodiments, all of which are still within the scope of the technical scheme of the invention.

Claims (16)

1. a kind of vehicle mounted traffic unlawful practice identification and processing system, which is characterized in that the system include: sensor module (1), Main processor modules (2), memory module (3);
The sensor module (1) is configured to continue recording information of vehicles and ambient condition information;
The main processor modules (2) include three units: signal processing and integrated unit (21), traffic rules judging unit (22), data parsing and processing unit (23), signal processing and integrated unit (21) are configured to the record of sensor module Information of vehicles and ambient condition information are extracted and are merged, and traffic rules judging unit (22) is configured to prestore modelling Unlawful practice judges whether the traffic rules under current scene are breached according to the input of signal processing and integrated unit, data When parsing and processing unit (23) are configured to default after triggering according to preset time and event before judgement result acquisition event triggering Interior data, and it is transmitted to memory module (3);
Memory module (3) is configured to after obtaining the judgement result that traffic rules are breached, by event trigger before preset time and Data after event triggering in preset time are stored.
2. vehicle mounted traffic unlawful practice identification according to claim 1 and processing system, which is characterized in that the sensor Module (1) includes vehicle-mounted camera (11), vehicle mounted electric magnetic wave radar (12), cartborne ultrasound wave radar (13), mobile lidar (14) and one or more of navigator (15).
3. vehicle mounted traffic unlawful practice identification according to claim 2 and processing system, which is characterized in that signal processing and Integrated unit (21) extracts the information of vehicles and ambient condition information of sensor module (1) record, and extracted vehicle is believed Breath and ambient condition information are merged, thus obtain this vehicle movement state information, his vehicle movement state information, road information and Lane information, wherein described vehicle movement state information is melted by this vehicle speed, this vehicle yaw acceleration and Ben Che acceleration information Close gained;His vehicle movement state information is by his vehicle speed, his vehicle acceleration, Ta Che at a distance from this vehicle and Ta Che and this vehicle Azimuth information merge gained;The road information merges institute by the grade of road, length, curvature, width, grade information ?;The lane information is by carriageway type, lane line, lane speed limit, lane width information fusion gained.
4. vehicle mounted traffic unlawful practice identification according to any one of claim 1-3 and processing system, which is characterized in that Memory module (3) is vehicle-mounted memory (31) and/or In-vehicle networking ECU (32), before the memory module triggers the event Data storage after preset time and event triggering in preset time is deposited into vehicle-mounted memory, or through In-vehicle networking ECU It stores up to cloud.
5. vehicle mounted traffic unlawful practice identification according to any one of claim 1-3 and processing system, which is characterized in that The system also includes output module violating the regulations (4), after obtaining the judgement result that traffic rules are breached, output module of breaking rules and regulations (4) violation information is shown.
6. a kind of vehicle mounted traffic unlawful practice identification and processing method, which comprises the following steps:
S1, traffic rules library pre-establish, and by traffic violations behavior modeling and are added in traffic rules library;
The extraction and fusion of S2, information, information of vehicles and ambient condition information are persistently recorded, and by the information of vehicles of record and Ambient condition information is extracted and is merged, necessary input information needed for obtaining traffic rules judgement;
The verifying and decision of S3, traffic rules carry out logic judgment to the necessary input information, obtain under current scene The conclusion whether traffic rules are breached and how to be breached;
If the traffic rules under S4, current scene are breached, data relevant to event are stored.
7. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that in step S1 The unlawful practice include illegally overtake other vehicles, illegal lane change, one of front truck car slipping and blackmail behavior or a variety of.
8. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that if in step S1 Unlawful practice include illegally overtake other vehicles, necessary input information described in step 2 include present road lane line information, when The movement state information of the speed-limiting messages and this vehicle in preceding road current lane and side lane, side lane state of motion of vehicle The movement state information of information or vehicle of jumping a queue;The logic judgment in step S3 includes comparing side lane vehicle or jumping a queue The speed of vehicle whether be more than the affiliated lane of present road speed limit;Data relevant to event include thing described in step S4 The speed limit, the speed of illegal passing vehicle in lane where the front and back video of preset time, this vehicle speed, this vehicle occur for part and non- The speed limit in lane where method passing vehicle.
9. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that if in step S1 Unlawful practice include illegal lane change, necessary input information described in step 2 include present road lane line information, when Speed-limiting messages, the motion state for vehicle of jumping a queue, the motion state of this vehicle and the Ben Che in the preceding each lane of road and front truck away from From information;The logic judgment in step S3 includes whether judgement vehicle of jumping a queue is compacted line, yellow line, or when jumping a queue this vehicle with Whether the distance of front truck is greater than the length of a vehicle body;Data relevant to event described in step S4 include before event occurs The lane line information of the video, present road of preset time, the speed-limiting messages in each lane of present road, vehicle of jumping a queue afterwards The range information of motion state, the motion state of this vehicle and Ben Che and front truck.
10. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that if step S1 In unlawful practice include front truck car slipping, necessary input information described in step 2 includes the motion state of front truck;Step S3 In the logic judgment include the velocity and acceleration for judging front truck and whether having backward;It is related to event described in step S4 Data include that the front and back video of the preset time and motion state of front truck occurs for event.
11. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that if step S1 In unlawful practice include blackmail behavior, necessary input information described in step 2 includes the type of current object, current object Body is at a distance from this vehicle, the vertically and horizontally acceleration change of the vertically and horizontally velocity variations of current object and current object;In step S3 The logic judgment include judge current object leave current object in the time of danger zone movement state information whether It mutates;Data relevant to event described in step S4 include that event occurs the video of front and back preset time, refers to currently The type of object, current object are at a distance from this vehicle, vertically and horizontally velocity variations and vertically and horizontally acceleration change.
12. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that the vehicle Information include this vehicle speed, this vehicle yaw acceleration, this vehicle acceleration, his vehicle speed, his vehicle acceleration, Ta Che and this vehicle away from From, the azimuth information of Ta Che and this vehicle;The ambient condition information includes grade, length, curvature, width, the gradient of road Information and carriageway type, lane line, lane speed limit and lane width information.
13. vehicle mounted traffic unlawful practice identification according to claim 12 and processing method, which is characterized in that in step S2 The described information of vehicles of record and ambient condition information are extracted and merged includes: information of vehicles and the week for extracting record Environmental information is enclosed, and extracted information of vehicles and ambient condition information are merged, to obtain this vehicle motion state letter Breath, his vehicle movement state information, road information and lane information, wherein described vehicle movement state information is by the Ben Cheche Speed, this vehicle yaw acceleration and Ben Che acceleration information fusion gained;His vehicle movement state information by his vehicle speed, Vehicle acceleration, Ta Che are at a distance from this vehicle and Ta Che merges gained with the azimuth information of this vehicle for he;The road information is by institute State the grade, length, curvature, width, grade information fusion gained of road;The lane information is by the carriageway type, lane Line, lane speed limit, lane width information fusion gained.
14. vehicle mounted traffic unlawful practice identification according to claim 6 and processing method, which is characterized in that the method Further include step S5: data relevant to event in step S4 are done by teletransmission operation by In-vehicle networking.
15. a kind of computer readable storage medium, for storing computer instruction, which is characterized in that described instruction is by a meter The step of calculation machine or processor realize the method as described in any claim in claim 6 to 14 when executing.
16. a kind of electronic equipment, including processor and memory, which is characterized in that computer instruction is stored in memory, it should Processor realizes the step of method as described in any claim in claim 6 to 14 when executing described instruction.
CN201710399848.XA 2017-05-31 2017-05-31 Vehicle mounted traffic unlawful practice identification and processing system and method Pending CN108986473A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710399848.XA CN108986473A (en) 2017-05-31 2017-05-31 Vehicle mounted traffic unlawful practice identification and processing system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710399848.XA CN108986473A (en) 2017-05-31 2017-05-31 Vehicle mounted traffic unlawful practice identification and processing system and method

Publications (1)

Publication Number Publication Date
CN108986473A true CN108986473A (en) 2018-12-11

Family

ID=64501353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710399848.XA Pending CN108986473A (en) 2017-05-31 2017-05-31 Vehicle mounted traffic unlawful practice identification and processing system and method

Country Status (1)

Country Link
CN (1) CN108986473A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110135418A (en) * 2019-04-15 2019-08-16 深圳壹账通智能科技有限公司 Traffic accident fix duty method, apparatus, equipment and storage medium based on picture
CN111243292A (en) * 2020-01-13 2020-06-05 天地伟业技术有限公司 Method for automatically detecting motor vehicle jam by intelligent traffic camera
CN111460988A (en) * 2020-03-31 2020-07-28 国网河北省电力有限公司沧州供电分公司 Illegal behavior identification method and device
CN111768651A (en) * 2020-05-11 2020-10-13 吉利汽车研究院(宁波)有限公司 Early warning method and device for preventing vehicle collision
WO2021135879A1 (en) * 2020-09-07 2021-07-08 平安科技(深圳)有限公司 Vehicle data monitoring method and apparatus, computer device, and storage medium
CN113254336A (en) * 2021-05-24 2021-08-13 公安部道路交通安全研究中心 Method and system for simulation test of traffic regulation compliance of automatic driving automobile
CN113362592A (en) * 2021-05-27 2021-09-07 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending traffic participant
CN113724416A (en) * 2020-11-12 2021-11-30 广东利通科技投资有限公司 Vehicle-mounted video processing method and device based on vehicle-road cooperative system and storage medium
CN115331428A (en) * 2022-07-05 2022-11-11 成利吉(厦门)智能股份有限公司 Traffic signal optimization method based on rule base
CN116331206A (en) * 2023-04-06 2023-06-27 上海交通大学 Decision method and system for intelligent automobile safe driving

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203825818U (en) * 2013-12-10 2014-09-10 安徽皖通科技股份有限公司 System for collecting information of urban traffic violation based on video monitoring
CN105427619A (en) * 2015-12-24 2016-03-23 上海新中新猎豹交通科技股份有限公司 Vehicle following distance automatic recording system and method
CN105469102A (en) * 2014-07-29 2016-04-06 小米科技有限责任公司 Vehicle driving information recording method and vehicle driving information recording device
CN106446856A (en) * 2016-09-30 2017-02-22 北京中星微电子有限公司 Vehicle lane-occupation driving intelligent monitoring method and system
CN106683530A (en) * 2017-02-21 2017-05-17 南京多伦科技股份有限公司 Computerized judging system and method based on three-dimensional laser vision and high-precision lane model

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203825818U (en) * 2013-12-10 2014-09-10 安徽皖通科技股份有限公司 System for collecting information of urban traffic violation based on video monitoring
CN105469102A (en) * 2014-07-29 2016-04-06 小米科技有限责任公司 Vehicle driving information recording method and vehicle driving information recording device
CN105427619A (en) * 2015-12-24 2016-03-23 上海新中新猎豹交通科技股份有限公司 Vehicle following distance automatic recording system and method
CN106446856A (en) * 2016-09-30 2017-02-22 北京中星微电子有限公司 Vehicle lane-occupation driving intelligent monitoring method and system
CN106683530A (en) * 2017-02-21 2017-05-17 南京多伦科技股份有限公司 Computerized judging system and method based on three-dimensional laser vision and high-precision lane model

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110135418A (en) * 2019-04-15 2019-08-16 深圳壹账通智能科技有限公司 Traffic accident fix duty method, apparatus, equipment and storage medium based on picture
CN111243292A (en) * 2020-01-13 2020-06-05 天地伟业技术有限公司 Method for automatically detecting motor vehicle jam by intelligent traffic camera
CN111460988B (en) * 2020-03-31 2023-08-22 国网河北省电力有限公司沧州供电分公司 Illegal behavior recognition method and device
CN111460988A (en) * 2020-03-31 2020-07-28 国网河北省电力有限公司沧州供电分公司 Illegal behavior identification method and device
CN111768651A (en) * 2020-05-11 2020-10-13 吉利汽车研究院(宁波)有限公司 Early warning method and device for preventing vehicle collision
CN111768651B (en) * 2020-05-11 2022-07-12 吉利汽车研究院(宁波)有限公司 Early warning method and device for preventing vehicle collision
WO2021135879A1 (en) * 2020-09-07 2021-07-08 平安科技(深圳)有限公司 Vehicle data monitoring method and apparatus, computer device, and storage medium
CN113724416A (en) * 2020-11-12 2021-11-30 广东利通科技投资有限公司 Vehicle-mounted video processing method and device based on vehicle-road cooperative system and storage medium
CN113254336A (en) * 2021-05-24 2021-08-13 公安部道路交通安全研究中心 Method and system for simulation test of traffic regulation compliance of automatic driving automobile
CN113362592A (en) * 2021-05-27 2021-09-07 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending traffic participant
CN115331428A (en) * 2022-07-05 2022-11-11 成利吉(厦门)智能股份有限公司 Traffic signal optimization method based on rule base
CN115331428B (en) * 2022-07-05 2023-10-17 成利吉(厦门)智能股份有限公司 Traffic signal optimization method based on rule base
CN116331206A (en) * 2023-04-06 2023-06-27 上海交通大学 Decision method and system for intelligent automobile safe driving
CN116331206B (en) * 2023-04-06 2023-10-20 上海交通大学 Decision method and system for intelligent automobile safe driving

Similar Documents

Publication Publication Date Title
CN108986473A (en) Vehicle mounted traffic unlawful practice identification and processing system and method
CN107380164B (en) Driver assistance system based on computer vision and support system
US11380193B2 (en) Method and system for vehicular-related communications
KR102387240B1 (en) Risk handling for vehicles with autonomous driving capabilities
CN110400478A (en) A kind of road condition notification method and device
US8379924B2 (en) Real time environment model generation system
US9984331B2 (en) Automated vehicular accident detection
CN106133805B (en) Driving assistance method and system for collision elimination
Saiprasert et al. Driver behaviour profiling using smartphone sensory data in a V2I environment
CN110349405A (en) It is monitored using the real-time traffic of networking automobile
US11836985B2 (en) Identifying suspicious entities using autonomous vehicles
WO2017153979A1 (en) Running vehicle alerting system and method
CN105243701B (en) A kind of running information report method and driving recording terminal
EP2107504A1 (en) Method and device for generating a real time environment model for vehicles
US11003925B2 (en) Event prediction system, event prediction method, program, and recording medium having same recorded therein
US11350242B2 (en) Detecting device movement and/or device usage within a vehicle
CN106740476A (en) A kind of car steering environment control method, device and automobile
CN109671006A (en) Traffic accident treatment method, apparatus and storage medium
CN103337179A (en) System and method for reminding bad driving behaviors
CN106920293A (en) The automatic log analysis methodology of car accident
CN115877343B (en) Man-car matching method and device based on radar target tracking and electronic equipment
US11235734B2 (en) Proximity based vehicle security system
US10977882B1 (en) Driver health profile
US11170650B2 (en) System for vehicle monitoring and alerting
Aliane et al. Traffic violation alert and management

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
TA01 Transfer of patent application right

Effective date of registration: 20200730

Address after: Susong Road West and Shenzhen Road North, Hefei Economic and Technological Development Zone, Anhui Province

Applicant after: Weilai (Anhui) Holding Co., Ltd

Address before: Room 502, Bank of America Center, Cecil Harcourt Road, central, Hongkong, China, 12

Applicant before: NIO NEXTEV Ltd.

TA01 Transfer of patent application right
RJ01 Rejection of invention patent application after publication

Application publication date: 20181211

RJ01 Rejection of invention patent application after publication