CN117037084A - Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction - Google Patents
Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction Download PDFInfo
- Publication number
- CN117037084A CN117037084A CN202311019819.8A CN202311019819A CN117037084A CN 117037084 A CN117037084 A CN 117037084A CN 202311019819 A CN202311019819 A CN 202311019819A CN 117037084 A CN117037084 A CN 117037084A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- identified
- toll station
- abnormal behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 98
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 230000004927 fusion Effects 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 206010039203 Road traffic accident Diseases 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000012634 fragment Substances 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a toll station vehicle abnormal behavior recognition method and device based on track reconstruction, relates to the technical field of traffic informatization, and aims to solve the problems that in the prior art, abnormal behavior vehicles such as fee escaping, accidents and the like cannot be recognized in time, and the recognition and disposal efficiency of the abnormal behavior vehicles is low. Comprising the following steps: determining vehicle space position information based on vehicle information in corresponding lanes collected by a plurality of cameras in the lane monitoring equipment, and determining lanes to which the vehicles to be identified belong by combining with the constructed toll station BIM model; forming track information of the vehicle to be identified, which contains a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs; and identifying the abnormal behavior of the vehicle to be identified in the toll station by adopting the trained vehicle abnormal behavior identification model based on the track information. The method can realize rapid identification, accurate positioning and illegal evidence collection of abnormal vehicles in the expressway toll scene, and improves the efficiency of toll station operation and management and control.
Description
Technical Field
The invention relates to the technical field of traffic informatization, in particular to a toll station vehicle abnormal behavior identification method and device based on track reconstruction.
Background
The way of tolling on highways mainly has two modes, one is traditional MTC (manual semiautomatic tolling lane) and the other is ETC (electronic toll collection). ETC and MTC combined highway combined networking charging system is the preferred mode of highway charging management in China at present.
Due to the great popularization of ETC (Electronic Toll Collection) technology, automatic highway charging is realized, convenience is provided for highway management, but various novel fee evasion behaviors are layered. Such as: and rubbing ETC of other people to pay. Therefore, it is very important to identify an abnormal payment behavior for realizing a small payment of communication fees at a toll gate. Further, if an abnormal behavior such as an accident occurs, the efficiency of charging is also affected.
Accordingly, there is a need to provide a more reliable toll station vehicle abnormal behavior recognition scheme based on trajectory reconstruction. And identifying vehicles with abnormal behaviors such as fee evasion, accidents and the like in time and triggering corresponding treatment schemes.
Disclosure of Invention
The invention aims to provide a toll station vehicle abnormal behavior recognition method and device based on track reconstruction, which are used for solving the problems that in the prior art, abnormal behavior vehicles such as fee evasion, accidents and the like cannot be recognized in time, and the recognition and disposal efficiency of the abnormal behavior vehicles are low, so that the toll collection efficiency is low.
In order to achieve the above object, the present invention provides the following technical solutions:
in a first aspect, the present invention provides a method for identifying abnormal behavior of a toll station vehicle based on trajectory reconstruction, the method comprising:
acquiring vehicle information in a corresponding lane acquired by lane monitoring equipment; the lane monitoring equipment comprises a plurality of cameras at different positions;
determining vehicle space position information based on the vehicle information, and determining a lane to which a vehicle to be recognized belongs based on the vehicle space position information in combination with a constructed toll station BIM model;
forming track information of the vehicle to be identified, which contains a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs;
based on the track information of the vehicle to be identified, identifying by adopting a trained vehicle abnormal behavior identification model to obtain the state information of the vehicle to be identified; the state information at least comprises a vehicle lane changing speed, a lane changing position and a distance between the vehicle to be identified and a front vehicle of the vehicle to be identified;
identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents;
and outputting the vehicle track with abnormal behaviors, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of the BIM model and the video.
Compared with the prior art, the toll station vehicle abnormal behavior recognition scheme based on track reconstruction provided by the invention determines vehicle space position information based on vehicle information in corresponding lanes acquired by a plurality of cameras in lane monitoring equipment, and determines lanes to which vehicles to be recognized belong based on the vehicle space position information combined with a constructed toll station BIM model; forming track information of the vehicle to be identified, which contains a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs; the training-completed abnormal behavior recognition model is adopted to recognize based on the track information, so that the state information of the vehicle to be recognized is obtained; based on the state information, identifying the abnormal behavior of the vehicle to be identified in the toll station, outputting an abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of a BIM model and a video. The method can realize rapid identification, accurate positioning and illegal evidence collection of the fee-escaping vehicles, the abnormal driving vehicles and the accident vehicles in the expressway toll scene, and improves the efficiency of toll station operation and management and control.
In a second aspect, the present invention provides a toll station vehicle abnormal behavior recognition apparatus based on trajectory reconstruction, the apparatus comprising:
the vehicle monitoring module is used for acquiring vehicle information in a corresponding lane acquired by the lane monitoring equipment; the lane monitoring equipment comprises a plurality of cameras at different positions;
the position positioning module is used for determining vehicle space position information based on the vehicle information and determining lanes to which the vehicle to be recognized belongs based on the vehicle space position information combined with the constructed toll station BIM model;
the vehicle track determining module is used for forming track information of the vehicle to be identified, which comprises a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs;
the abnormal behavior recognition module is used for recognizing by adopting a trained vehicle abnormal behavior recognition model based on the track information of the vehicle to be recognized to obtain the state information of the vehicle to be recognized; the state information at least comprises a vehicle lane changing speed, a lane changing position and a distance between the vehicle to be identified and a front vehicle of the vehicle to be identified; identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents;
the abnormal behavior vehicle track output module is used for outputting the abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of the BIM model and the video.
The technical effects achieved by the apparatus type scheme provided in the second aspect are the same as those of the method type scheme provided in the first aspect, and are not described herein.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a schematic flow chart of a toll station vehicle abnormal behavior recognition method based on track reconstruction;
fig. 2 is a schematic diagram of a toll station vehicle abnormal behavior recognition device based on track reconstruction.
Detailed Description
In order to clearly describe the technical solution of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same item or similar items having substantially the same function and effect. For example, the first threshold and the second threshold are merely for distinguishing between different thresholds, and are not limited in order. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ.
In the present invention, the words "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the present invention, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, a and b, a and c, b and c, or a, b and c, wherein a, b, c can be single or multiple.
In the management process of the toll station, a manual video inspection and post-inspection mode is adopted to collect the fee-escaping minivan. Each vehicle is driven away from the free channel, evidence of video images is stored, each vehicle is authenticated and checked manually, and the fee-escaping truck is pulled out for additional payment. Because the holiday freely passes through the lane, the traffic flow is huge, the workload of manual video check and settlement is huge, the efficiency is low, and the toll collection obligation of the truck owners cannot be informed in real time. In addition, the toll booth is very easy to generate illegal driving (illegal lane changing and card running) due to the fact that queuing payment is needed in many cases, traffic accidents can be seriously caused, and the toll booth is blocked and the toll collection efficiency is reduced due to delay time when waiting for a traffic police to arrive for processing.
By arranging the ETC portal at the expressway ramp in front of the toll station, ETC transactions are carried out from the exit lane to the ramp in advance, when vehicles with successful pre-transactions pass through the ETC lane, the system can check vehicle information, and the vehicles can quickly pass through by automatically lifting the rod, so that the passing efficiency of ETC vehicles is effectively improved.
The ETC ramp pre-transaction system deploys ETC transaction antennae, a high-definition license plate identifier, an information display board and other devices on the exit ramp of the toll station, so that normal ETC vehicle transactions are carried out on the toll station ramp in advance, the transaction flow of the vehicle on the ETC special lane is simplified, the transaction time is shortened, and the success rate of one-time ETC vehicle passing is improved. Meanwhile, aiming at ETC special condition vehicles (such as blacklists, insufficient balances and the like), after the ramp pre-transaction system is identified, special condition vehicle license plate numbers are displayed through an information board, the special condition vehicles are guided to enter a manual toll collection lane, and the problem of exit congestion of toll collection stations can be effectively relieved.
Therefore, the scheme can automatically identify the abnormal behaviors of fee escaping, abnormal lane changing, abnormal card running and traffic accidents, can realize quick identification, accurate positioning and illegal evidence taking of the fee escaping vehicles in the expressway toll scene, and improves the running and management and control efficiency of toll stations.
Next, the scheme provided by the embodiments of the present specification will be described with reference to the accompanying drawings:
as shown in fig. 1, the process may include the steps of:
step 110: acquiring vehicle information in a corresponding lane acquired by lane monitoring equipment; the lane monitoring apparatus includes a plurality of cameras at different positions.
Specifically, the vehicle information in the corresponding lane acquired by the lane monitoring device can be acquired, the lane monitoring device can comprise a plurality of cameras, and the shooting data of the same vehicle can be positioned by adopting the plurality of cameras; and then analyzing the running condition of the vehicle in the preset lane in the set time based on the vehicle information. Specifically, a high-point lane-level vehicle traffic state monitoring device may be provided to monitor vehicle information in a lane at a certain time interval, or may continuously monitor vehicle information in a lane. Through camera image recognition, information such as vehicle type, license plate number, driver and the like can be acquired and recorded.
Step 120: and determining vehicle space position information based on the vehicle information, and determining a lane to which the vehicle to be recognized belongs based on the vehicle space position information combined with the constructed toll station BIM model.
The toll station queuing area can be divided in the BIM model, and the lane to which the vehicle to be recognized belongs can be determined by mapping the division condition of the toll station queuing area in the BIM model and the vehicle space position information. The abnormal behavior of the vehicle can be judged by carrying out continuous monitoring analysis of time sequences according to lane information of each vehicle acquired by the cameras. Specifically, the toll station queuing area can be divided in the constructed toll station BIM model; determining the vehicle space position of a vehicle to be identified, projecting the vehicle space position of the vehicle to be identified on a constructed toll station BIM model, and determining a lane to which the vehicle to be identified belongs according to the ground projection position of the vehicle to be identified.
Step 130: and forming track information of the vehicle to be identified, which comprises a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs.
The multi-channel monitoring video can be acquired by a plurality of cameras, and the cameras are continuously monitored, so that the vehicle running track of the vehicle to be identified containing the time stamp can be obtained according to the time sequence monitoring data of the multi-channel monitoring video and the lanes to which the vehicle to be identified belongs.
Step 140: based on the track information of the vehicle to be identified, identifying by adopting a trained vehicle abnormal behavior identification model to obtain the state information of the vehicle to be identified; the state information at least comprises a vehicle lane change speed, a lane change position of the vehicle to be identified and a distance between the vehicle to be identified and a front vehicle.
The vehicle abnormal behavior recognition model can calculate the information such as the vehicle lane changing speed and the lane changing position of the vehicle to be recognized, the distance between the vehicle to be recognized and the front vehicle and the like according to the track information of the vehicle acquired by the camera.
Two scenarios are embodied in step 140:
(1) For a toll station scene provided with a ramp entrance pre-transaction facility:
(1.1) for toll stations provided with ramp mouth pre-transaction facilities, the pre-transaction is successful, and vehicles are identified as multiple types: ETC vehicles are transacted, ETC vehicle blacklists or non-transacted, non-ETC vehicles, and different colors, attributes and time stamps are marked on different types of vehicles;
(1.2) giving different colors according to different lane attributes in a BIM model, wherein the colors comprise ETC lanes, non-ETC lanes and mixed lanes 3, the ETC lanes only allow vehicles provided with ETC to pass, the mixed lanes refer to lanes allowing ETC vehicles and non-ETC vehicles to pass, the non-ETC lanes refer to lanes suggesting vehicles not provided with ETC to pass, and corresponding regular passing rules are set;
(1.3) only the fee evasion recognition is performed for vehicles that do not pass the pre-transaction (transaction unsuccessful ETC vehicles, non-ETC vehicles). When a non-ETC vehicle is driven into an ETC lane, the non-ETC vehicle is recognized in the vehicle lane in advance, namely, a special event is triggered;
(2) For a toll station scene provided with a ramp entrance pre-transaction facility: and based on the vehicle to be identified, identifying by using the trained vehicle abnormal behavior identification model to obtain the state information of the vehicle to be identified.
By the method, ETC vehicles, non-ETC vehicles and blacklist vehicles can be identified in advance, and pre-screening is performed, so that the workload of subsequent abnormal behavior identification is reduced, and the identification efficiency is improved.
Step 150: identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents.
For the following ETC vehicles, setting a time sequence following distance in a lane as an evaluation parameter, sampling the distance between each vehicle in the lane and the front vehicle at a certain time interval, calculating the sampling distance for a plurality of times in a continuous period, if the distance average value is smaller than a certain threshold value, marking the vehicles as important attention vehicles, marking the vehicles as following vehicles, and dispatching the nearest ball machine for automatic following and enhanced evidence obtaining.
Step 160: and outputting the vehicle track with abnormal behaviors, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of the BIM model and the video.
The method in FIG. 1 is that vehicle space position information is determined based on vehicle information in corresponding lanes collected by a plurality of cameras in a lane monitoring device, and a lane to which a vehicle to be identified belongs is determined based on the vehicle space position information in combination with a constructed toll station BIM model; forming track information of the vehicle to be identified, which contains a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs; the training-completed abnormal behavior recognition model is adopted to recognize based on the track information, so that the state information of the vehicle to be recognized is obtained; based on the state information, identifying the abnormal behavior of the vehicle to be identified in the toll station, outputting an abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of a BIM model and a video. The method can realize rapid identification, accurate positioning and illegal evidence collection of the fee-escaping vehicles, the abnormal driving vehicles and the accident vehicles in the expressway toll scene, and improves the efficiency of toll station operation and management and control.
Based on the method of fig. 1, the examples of the present specification also provide some specific implementations of the method, as described below.
In a specific application process, the scheme only carries out fee evasion recognition on vehicles which do not pass through the pre-transaction (transaction unsuccessful ETC vehicles and non-ETC vehicles). Specifically, for a toll station provided with a ramp port pre-transaction facility, pre-transaction is successful, and ETC vehicles marked on attributes of vehicle objects are identified to be transacted, ETC vehicle blacklists or non-transacted and non-ETC vehicles; the fee evasion recognition is performed for vehicles that do not pass the pre-transaction (transaction unsuccessful ETC vehicles, non-ETC vehicles).
Aiming at different vehicle object attributes, passing vehicles are classified into ETC vehicles which are transacted, ETC vehicle blacklists or non-transacted and non-ETC vehicles, different colors, attributes and time stamps are respectively marked, different colors (ETC vehicles, mixed vehicles and non-ETC lanes) are also given to lane areas divided in the BIM model, and corresponding passing rules are set.
Determining vehicle space position information based on the vehicle information, and before determining a lane to which the vehicle to be recognized belongs based on the vehicle space position information and the constructed toll station BIM model, the method further comprises the following steps:
and constructing a toll station BIM model, wherein the coverage area of the lane monitoring equipment and the queuing areas of different lanes are marked in the toll station BIM model.
Further, constructing a toll station BIM model may specifically include:
in an initialization modeling scene, generating an initial BIM model and a toll station monitoring equipment model based on the initial BIM model file and the toll station monitoring equipment model file;
acquiring structural tree node data of the initial BIM model and monitoring data corresponding to the toll station monitoring equipment model;
and the structural tree node data are corresponding to the monitoring data, the attribute is input, and the construction of the BIM model is completed through Revit or CATIA software.
Optionally, based on the track information of the vehicle to be identified, the identifying by using the trained abnormal vehicle behavior identification model may further include:
constructing a vehicle running state track sample library based on historical monitoring data, and dividing the sample library into a training sample and a test sample; the sample library comprises track information of vehicles containing time stamps of a large number of vehicles; the history monitoring data comprise the lane changing speed, the lane changing position and the distance between the vehicle and the front vehicle;
inputting the training sample into an initial vehicle abnormal behavior recognition model to obtain initial state information;
comparing the initial state information with the known vehicle state information to obtain an error value;
and carrying out parameter adjustment on the initial vehicle abnormal behavior recognition model based on the error value until the error value meets a preset condition, so as to obtain the trained vehicle abnormal behavior recognition model.
In the actual implementation process, the abnormal behavior recognition model of the vehicle can be a neural network model, and the abnormal behavior AI training library of the vehicle is constructed according to the characteristics of the lane changing speed, the lane changing position, the distance between the vehicle and the front vehicle and the like, and based on the trained model, the abnormal behavior judgment program of the vehicle based on artificial intelligence can be realized. And the automatic identification of the abnormal track vehicle is realized.
For step 160, outputting an abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and performing visual presentation in a manner of three-dimensional fusion of a BIM model and a video, which specifically comprises the following steps:
calibrating pose information and internal and external parameters of each lane monitoring device in a BIM scene, and calculating through a projection matrix of the lane monitoring devices in a BIM model to form a two-dimensional vector boundary map of a lane monitoring device coverage area of a toll station;
outputting complete track information of the vehicles running in the toll station scene for the identified abnormal behavior vehicles, and fitting a track curve; intersecting the fitted track curve with a two-dimensional vector boundary diagram of the coverage area of the monitoring equipment, and outputting a corresponding data sequence; the data sequence comprises a data sequence of the equipment number of the lane monitoring equipment, a data sequence of the driving-in time and a data sequence of the driving-out time;
inquiring the time stamp of each intersection point to form all data sequences corresponding to the lane monitoring equipment, and sequencing the overlapping areas according to the driving-in time;
transmitting all data sequences corresponding to the lane monitoring equipment to a network video recorder management system corresponding to the charging scene monitoring equipment, requesting and returning the monitoring videos of the time intervals corresponding to different monitoring equipment;
performing space-time registration on track data of the abnormal behavior vehicle and video data tracked by the lane monitoring equipment in a BIM scene to form an abnormal vehicle evidence obtaining data chain comprising a completed track and corresponding monitoring video;
and carrying out topological three-dimensional fusion on video data tracked by the lane monitoring equipment and the BIM model through fragment texturing and projection calculation, so as to realize three-dimensional visual presentation of the abnormal behavior vehicle in the whole process of passing through the toll station.
Finally, after identifying the abnormal behavior of the toll station vehicle based on the status information, it may further include:
judging whether the vehicle to be identified has abnormal behaviors or not based on the vehicle lane changing speed and lane changing position of the vehicle to be identified and the distance between the vehicle to be identified and the front vehicle;
if the vehicle to be identified has abnormal behaviors, automatically triggering alarm linkage, extracting and storing abnormal track vehicle information corresponding to the vehicle with the abnormal behaviors according to time, and implementing corresponding management and control measures.
Specifically, when it is recognized that the vehicle is not paying or other driving violations are generated, the corresponding brake lever can be closed to avoid driving out of the vehicle against the rules. If a vehicle runs into the vehicle, the related units can be reported in time, and evidence is reserved. And transferring the evidence information such as the video of the illegal vehicle and the vehicle to a toll station manager, assisting a worker in processing, automatically generating an evidence chain containing time, and providing evidence support for law enforcement personnel to judge.
In addition, as one of the embodiments, when mainly recognizing the behavior of the non-ETC vehicle moving along the ETC lane, the non-ETC vehicle is recognized in advance in the lane, that is, the special duty event is triggered, and the special duty personnel is prompted to process.
The distance between other vehicles trailing the ETC can be set, a plurality of time points are sampled, and vehicles with continuous following distances smaller than a preset threshold value in the dense time points are stored. Specifically: for the following ETC vehicles, setting time sequence following distance in the lane as an evaluation parameter, and sampling the distance between each vehicle in the lane and the front vehicle at a certain time interval;
calculating a plurality of sampling distances within a continuous specific time period based on the sampling data;
and marking the vehicle with the average value of the sampling distances smaller than the preset threshold value as an ETC following vehicle, and dispatching the nearest lane monitoring equipment to perform automatic tracking and enhanced evidence obtaining.
Based on the same thought, the invention also provides a toll station vehicle abnormal behavior recognition device based on track reconstruction, as shown in fig. 2, the device can comprise:
the vehicle monitoring module 210 is configured to obtain vehicle information in a corresponding lane acquired by the lane monitoring device; the lane monitoring equipment comprises a plurality of cameras at different positions;
the position locating module 220 is configured to determine vehicle spatial position information based on the vehicle information, and determine a lane to which a vehicle to be identified belongs based on the vehicle spatial position information in combination with the constructed toll station BIM model;
the vehicle track determining module 230 is configured to form track information of the vehicle to be identified including a time stamp based on the multi-channel monitoring video time sequence monitoring data and a lane to which the vehicle to be identified belongs;
the abnormal behavior recognition module 240 is configured to recognize by using a trained vehicle abnormal behavior recognition model based on the track information of the vehicle to be recognized, so as to obtain state information of the vehicle to be recognized; the state information at least comprises a vehicle lane changing speed, a lane changing position and a distance between the vehicle to be identified and a front vehicle of the vehicle to be identified; identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents.
The abnormal behavior vehicle track output module 250 is used for outputting an abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and performing visual presentation in a mode of three-dimensional fusion of a BIM model and a video.
Based on the apparatus in fig. 2, some specific implementation units may also be included:
optionally, the apparatus may further include:
the toll station BIM model construction module is used for generating an initial BIM model and a toll station monitoring equipment model based on the initial BIM model file and the toll station monitoring equipment model file in an initial modeling scene; acquiring structural tree node data of the initial BIM model and monitoring data corresponding to the toll station monitoring equipment model; the node data of the structural tree is corresponding to the monitoring data, the attribute is input, and the construction of a BIM model is completed through Revit or CATIA software; and the coverage area of the lane monitoring equipment and the queuing areas of different lanes are marked in the toll station BIM model.
Optionally, the apparatus may further include:
the vehicle abnormal behavior recognition model recognition module is used for constructing a vehicle running state track sample library based on historical monitoring data and dividing the sample library into a training sample and a test sample; the sample library comprises track information of vehicles containing time stamps of a large number of vehicles; the history monitoring data comprise the lane changing speed, the lane changing position and the distance between the vehicle and the front vehicle;
inputting the training sample into an initial vehicle abnormal behavior recognition model to obtain initial state information;
comparing the initial state information with the known vehicle state information to obtain an error value;
and carrying out parameter adjustment on the initial vehicle abnormal behavior recognition model based on the error value until the error value meets a preset condition, so as to obtain the trained vehicle abnormal behavior recognition model.
Optionally, the apparatus may further include:
the alarm linkage treatment module is used for judging whether the vehicle to be identified has abnormal behaviors or not based on the vehicle lane changing speed and lane changing position of the vehicle to be identified and the distance between the vehicle to be identified and the front vehicle;
if the vehicle to be identified has abnormal behaviors, automatically triggering alarm linkage, extracting and storing abnormal track vehicle information corresponding to the vehicle with the abnormal behaviors according to time, and implementing corresponding management and control measures.
Optionally, the position location module 220 may specifically be configured to:
dividing the queuing area of the toll station in the constructed BIM model of the toll station;
determining the vehicle space position of a vehicle to be identified, projecting the vehicle space position of the vehicle to be identified on a constructed toll station BIM model, and determining a lane to which the vehicle to be identified belongs according to the ground projection position of the vehicle to be identified.
According to the invention, through the combination of multi-channel monitoring video and cross-camera tracking, abnormal behavior vehicles such as fee evasion, accidents and the like are timely identified and corresponding disposal schemes are triggered, and the identification and disposal efficiency of the abnormal behavior vehicles in the expressway toll station business scene is improved. Through the modules in the figure 2, a toll station BIM model is correspondingly constructed, the coverage area of a monitoring camera and queuing areas of different lanes are calibrated in the model in advance, information such as the type of a vehicle, a license plate number, a lane to which the vehicle belongs is quickly identified based on a monitoring video, track information of the vehicle including a time stamp is formed based on time sequence monitoring data of multiple monitoring videos and identification results, and data such as the lane changing speed, the lane changing position, the distance between the front vehicles and the like of the vehicle are calculated. And constructing a vehicle running state track sample library based on the history monitoring data, and constructing a vehicle abnormal behavior recognition model based on machine learning, so as to realize rapid recognition, alarm and evidence collection of the abnormal track vehicle. Based on the identification result, the alarm linkage is automatically triggered, and corresponding control measures are implemented. The invention realizes the rapid identification, accurate positioning and illegal evidence collection of the fee-escaping vehicles in the expressway toll scene, and improves the efficiency of toll station operation and management and control.
The above description has been presented mainly in terms of interaction between the modules, and the solution provided by the embodiment of the present invention is described. It is understood that each module, in order to implement the above-mentioned functions, includes a corresponding hardware structure and/or software unit for performing each function. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The embodiment of the invention can divide the functional modules according to the method example, for example, each functional module can be divided corresponding to each function, or two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present invention, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.
Although the invention is described herein in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
Although the invention has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the invention. Accordingly, the specification and drawings are merely exemplary illustrations of the present invention as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the invention. It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The toll station vehicle abnormal behavior identification method based on track reconstruction is characterized by comprising the following steps:
acquiring vehicle information in a corresponding lane acquired by lane monitoring equipment; the lane monitoring equipment comprises a plurality of cameras at different positions;
determining vehicle space position information based on the vehicle information, and determining a lane to which a vehicle to be recognized belongs based on the vehicle space position information in combination with a constructed toll station BIM model;
forming track information of the vehicle to be identified, which contains a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs;
based on the track information of the vehicle to be identified, identifying by adopting a trained vehicle abnormal behavior identification model to obtain the state information of the vehicle to be identified; the state information at least comprises a vehicle lane changing speed, a lane changing position and a distance between the vehicle to be identified and a front vehicle of the vehicle to be identified;
identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents;
and outputting the vehicle track with abnormal behaviors, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of the BIM model and the video.
2. The method for recognizing abnormal behavior of a toll booth vehicle based on trajectory reconstruction according to claim 1, wherein before determining vehicle spatial position information based on the vehicle information and determining a lane to which a vehicle to be recognized belongs based on the vehicle spatial position information in combination with the constructed toll booth BIM model, further comprises:
for a toll station provided with a ramp port pre-transaction facility, pre-transaction is successful, and identifying ETC vehicles which are transacted, ETC vehicle blacklists, non-transacted ETC vehicles and non-ETC vehicles on the attributes of the vehicle objects;
constructing a toll station BIM model, marking coverage areas of lane monitoring equipment and queuing areas of different lanes in the toll station BIM model, marking different colors, attributes and time stamps in the toll station BIM model according to different vehicle object attributes, and setting corresponding passing rules;
constructing a toll station BIM model, which specifically comprises the following steps:
in an initialization modeling scene, generating an initial BIM model and a toll station monitoring equipment model based on the initial BIM model file and the toll station monitoring equipment model file;
acquiring structural tree node data of the initial BIM model and monitoring data corresponding to the toll station monitoring equipment model;
and the structural tree node data are corresponding to the monitoring data, the attribute is input, and the construction of the BIM model is completed through Revit or CATIA software.
3. The method for identifying abnormal behavior of a toll station vehicle based on track reconstruction according to claim 1, wherein the method for identifying abnormal behavior of the toll station vehicle is characterized in that the abnormal behavior vehicle track is output, a cross-camera video evidence obtaining data chain is automatically generated through space-time calibration, and visual presentation is performed in a manner of three-dimensional fusion of a BIM model and a video, and specifically comprises the following steps:
calibrating pose information and internal and external parameters of each lane monitoring device in a BIM scene, and calculating through a projection matrix of the lane monitoring devices in a BIM model to form a two-dimensional vector boundary map of a lane monitoring device coverage area of a toll station;
outputting complete track information of the vehicles running in the toll station scene for the identified abnormal behavior vehicles, and fitting a track curve; intersecting the fitted track curve with a two-dimensional vector boundary diagram of the coverage area of the monitoring equipment, and outputting a corresponding data sequence; the data sequence comprises a data sequence of the equipment number of the lane monitoring equipment, a data sequence of the driving-in time and a data sequence of the driving-out time;
inquiring the time stamp of each intersection point to form all data sequences corresponding to the lane monitoring equipment, and sequencing the overlapping areas according to the driving-in time;
transmitting all data sequences corresponding to the lane monitoring equipment to a network video recorder management system corresponding to the charging scene monitoring equipment, requesting and returning the monitoring videos of the time intervals corresponding to different monitoring equipment;
performing space-time registration on track data of the abnormal behavior vehicle and video data tracked by the lane monitoring equipment in a BIM scene to form an abnormal vehicle evidence obtaining data chain comprising a completed track and corresponding monitoring video;
and carrying out topological three-dimensional fusion on video data tracked by the lane monitoring equipment and the BIM model through fragment texturing and projection calculation, so as to realize three-dimensional visual presentation of the abnormal behavior vehicle in the whole process of passing through the toll station.
4. The method for identifying abnormal behavior of a toll station vehicle based on track reconstruction according to claim 1, wherein based on track information of the vehicle to be identified, the method further comprises, before identifying by using a trained vehicle abnormal behavior identification model, obtaining state information of the vehicle to be identified:
constructing a vehicle running state track sample library based on historical monitoring data, and dividing the sample library into a training sample and a test sample; the sample library comprises track information of vehicles containing time stamps of a large number of vehicles; the history monitoring data comprise the lane changing speed, the lane changing position and the distance between the vehicle and the front vehicle;
inputting the training sample into an initial vehicle abnormal behavior recognition model to obtain initial state information;
comparing the initial state information with the known vehicle state information to obtain an error value;
and carrying out parameter adjustment on the initial vehicle abnormal behavior recognition model based on the error value until the error value meets a preset condition, so as to obtain the trained vehicle abnormal behavior recognition model.
5. The method for identifying abnormal behavior of a toll station vehicle based on track reconstruction according to claim 1, wherein determining vehicle space position information based on the vehicle information and determining a lane to which a vehicle to be identified belongs based on the vehicle space position information in combination with a constructed toll station BIM model, comprises:
dividing the queuing area of the toll station in the constructed BIM model of the toll station; marking different colors for different lanes;
determining the vehicle space position of a vehicle to be identified, projecting the vehicle space position of the vehicle to be identified on a constructed toll station BIM model, and determining a lane to which the vehicle to be identified belongs according to the ground projection position of the vehicle to be identified.
6. The method for identifying abnormal behavior of a toll station vehicle based on trajectory reconstruction according to claim 1, wherein the identifying abnormal behavior of the toll station vehicle based on the state information specifically comprises:
for the following ETC vehicles, setting time sequence following distance in the lane as an evaluation parameter, and sampling the distance between each vehicle in the lane and the front vehicle at a certain time interval;
calculating a plurality of sampling distances within a continuous specific time period based on the sampling data;
marking the vehicles with the average value of the sampling distances smaller than a preset threshold value as ETC following vehicles, and dispatching the nearest lane monitoring equipment to perform automatic tracking and enhanced evidence obtaining;
after identifying the abnormal behavior of the toll station vehicle based on the state information, the method further comprises the following steps:
judging whether the vehicle to be identified has abnormal behaviors or not based on the vehicle lane changing speed and lane changing position of the vehicle to be identified and the distance between the vehicle to be identified and the front vehicle;
if the vehicle to be identified has abnormal behaviors, automatically triggering alarm linkage, extracting and storing abnormal track vehicle information corresponding to the vehicle with the abnormal behaviors according to time, and implementing corresponding management and control measures.
7. The utility model provides a toll station vehicle abnormal behavior recognition device based on orbit rebuilds which characterized in that, the device includes:
the vehicle monitoring module is used for acquiring vehicle information in a corresponding lane acquired by the lane monitoring equipment; the lane monitoring equipment comprises a plurality of cameras at different positions;
the position positioning module is used for determining vehicle space position information based on the vehicle information and determining lanes to which the vehicle to be recognized belongs based on the vehicle space position information combined with the constructed toll station BIM model;
the vehicle track determining module is used for forming track information of the vehicle to be identified, which comprises a time stamp, based on the multi-channel monitoring video time sequence monitoring data and the lane to which the vehicle to be identified belongs;
the abnormal behavior recognition module is used for recognizing by adopting a trained vehicle abnormal behavior recognition model based on the track information of the vehicle to be recognized to obtain the state information of the vehicle to be recognized; the state information at least comprises a vehicle lane changing speed, a lane changing position and a distance between the vehicle to be identified and a front vehicle of the vehicle to be identified; identifying abnormal behaviors of the vehicle to be identified at the toll station based on the state information; the abnormal behavior comprises fee evasion, abnormal lane change, abnormal card break and traffic accidents;
the abnormal behavior vehicle track output module is used for outputting the abnormal behavior vehicle track, automatically generating a cross-camera video evidence obtaining data chain through space-time calibration, and carrying out visual presentation in a mode of three-dimensional fusion of the BIM model and the video.
8. The toll booth vehicle abnormal behavior recognition apparatus based on trajectory reconstruction according to claim 7, wherein the apparatus further comprises:
the toll station BIM model construction module is used for generating an initial BIM model and a toll station monitoring equipment model based on the initial BIM model file and the toll station monitoring equipment model file in an initial modeling scene;
acquiring structural tree node data of the initial BIM model and monitoring data corresponding to the toll station monitoring equipment model;
the node data of the structural tree is corresponding to the monitoring data, the attribute is input, and the construction of a BIM model is completed through Revit or CATIA software; and the coverage area of the lane monitoring equipment and the queuing areas of different lanes are marked in the toll station BIM model.
9. The toll booth vehicle abnormal behavior recognition apparatus based on trajectory reconstruction according to claim 7, wherein the apparatus further comprises:
the vehicle abnormal behavior recognition model recognition module is used for constructing a vehicle running state track sample library based on historical monitoring data and dividing the sample library into a training sample and a test sample; the sample library comprises track information of vehicles containing time stamps of a large number of vehicles; the history monitoring data comprise the lane changing speed, the lane changing position and the distance between the vehicle and the front vehicle;
inputting the training sample into an initial vehicle abnormal behavior recognition model to obtain initial state information;
comparing the initial state information with the known vehicle state information to obtain an error value;
and carrying out parameter adjustment on the initial vehicle abnormal behavior recognition model based on the error value until the error value meets a preset condition, so as to obtain the trained vehicle abnormal behavior recognition model.
10. The toll booth vehicle abnormal behavior recognition apparatus based on trajectory reconstruction according to claim 7, wherein the apparatus further comprises:
the alarm linkage treatment module is used for judging whether the vehicle to be identified has abnormal behaviors or not based on the vehicle lane changing speed and lane changing position of the vehicle to be identified and the distance between the vehicle to be identified and the front vehicle;
if the vehicle to be identified has abnormal behaviors, automatically triggering alarm linkage, extracting and storing abnormal track vehicle information corresponding to the vehicle with the abnormal behaviors according to time, and implementing corresponding management and control measures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311019819.8A CN117037084A (en) | 2023-08-14 | 2023-08-14 | Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311019819.8A CN117037084A (en) | 2023-08-14 | 2023-08-14 | Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117037084A true CN117037084A (en) | 2023-11-10 |
Family
ID=88642673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311019819.8A Pending CN117037084A (en) | 2023-08-14 | 2023-08-14 | Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117037084A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117763945A (en) * | 2023-11-14 | 2024-03-26 | 安徽交控信息产业有限公司 | Digital twinning-based vehicle fee evasion behavior analysis method and lane charging system |
| CN117912252A (en) * | 2024-01-26 | 2024-04-19 | 安徽汉高信息科技有限公司 | Special vehicle guiding system based on expressway toll station |
-
2023
- 2023-08-14 CN CN202311019819.8A patent/CN117037084A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117763945A (en) * | 2023-11-14 | 2024-03-26 | 安徽交控信息产业有限公司 | Digital twinning-based vehicle fee evasion behavior analysis method and lane charging system |
| CN117912252A (en) * | 2024-01-26 | 2024-04-19 | 安徽汉高信息科技有限公司 | Special vehicle guiding system based on expressway toll station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xing et al. | Examining traffic conflicts of up stream toll plaza area using vehicles’ trajectory data | |
| CN117037084A (en) | Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction | |
| CN108320553B (en) | Road condition prediction method based on road driving event | |
| CN105590454A (en) | Vehicle violation behavior proof-providing method and system thereof | |
| CN111833598B (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
| CN110853391A (en) | Intelligent shared parking system | |
| CN110070061A (en) | A kind of passengers quantity projectional technique and device | |
| EP4020428A1 (en) | Method and apparatus for recognizing lane, and computing device | |
| CN106056451A (en) | Vehicle OBD sensor-based remote unmanned loss assessment system | |
| CN113851017A (en) | Pedestrian and vehicle identification and early warning multifunctional system based on road side RSU | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN108932850B (en) | Method and device for recording low-speed driving illegal behaviors of motor vehicle | |
| CN113487877A (en) | Road vehicle illegal parking monitoring method | |
| CN114612860A (en) | Computer vision-based passenger flow identification and prediction method in rail transit station | |
| CN112509325A (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| Chen et al. | Lane-based Distance-Velocity model for evaluating pedestrian-vehicle interaction at non-signalized locations | |
| CN114078319A (en) | Method and device for detecting potential hazard site of traffic accident | |
| CN109934161B (en) | Vehicle identification and detection method and system based on convolutional neural network | |
| CN116935659B (en) | High-speed service area bayonet vehicle auditing system and method thereof | |
| CN117456482B (en) | Abnormal event identification method and system for traffic monitoring scene | |
| CN114038075A (en) | New-generation lane charging and auditing integrated system | |
| CN117612364A (en) | Method and device for detecting motor vehicle violation, electronic equipment and storage medium | |
| CN116343493A (en) | Method and device for identifying violation of non-motor vehicle, electronic equipment and storage medium | |
| Zaki et al. | Comprehensive safety diagnosis using automated video analysis: Applications to an urban intersection in Edmonton, Alberta, Canada | |
| CN115407704A (en) | Intelligent traffic marking control method, system and equipment |
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 |