CN107248290B - Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification - Google Patents
Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification Download PDFInfo
- Publication number
- CN107248290B CN107248290B CN201710573312.5A CN201710573312A CN107248290B CN 107248290 B CN107248290 B CN 107248290B CN 201710573312 A CN201710573312 A CN 201710573312A CN 107248290 B CN107248290 B CN 107248290B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- traffic conflict
- frame
- stc
- toll
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 241001269238 Data Species 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000003786 synthesis reaction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of hybrid mainline toll station traffic conflict evaluation methods based on automobile video frequency identification, include the following steps: 1, arrange camera, traveling video of the acquisition vehicle in toll plaza in the toll plaza of charge station;2, vehicle identification and tracking are carried out to collected vehicle driving video, obtains the position coordinates of vehicle in each frame image;3, using the M frame image data of vehicle, speed of the vehicle in each frame image is calculatedWith deceleration indexIn case of conflicting with speeding, the time index TTC of vehicle following-model is calculatedk;In case of lane change conflict, Vehicular turn model time index T is calculatedpet;5, willTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation index STC is unified for, the severity of traffic conflict is judged according to the value of STC.This method can quantify the severity of charge station's traffic conflict, have important application value to decisions such as charge station's Road Safety Evaluation, managed operation, road drainage measures.
Description
Technical field
The invention belongs to freeway management technical fields, and in particular to a kind of charge station's traffic conflict evaluation method.
Background technique
With the rapid development of China in Recent Years economy, the mileage of highway is also constantly increasing.And charge station's conduct
" throat " area of highway, it decides the traffic capacity and service level in the even entire section in section near charge station.
With the increase year by year of vehicle flowrate, the traffic loading that mainline toll station undertakes is also increasing.Charge station, China mostly uses greatly not
Mode of the parking automatic charging in conjunction with the semi automatic toll that stops.Although the congestion for alleviating charge station to a certain extent is asked
Topic, but this hidden danger that may also cause the accident.
With the development of traffic analysis technology, the traffic conflict technique theory at this stage be mainly used in urban road and
Intersection, it is less to the analysis of charge station's traffic conflict, and video processing is utilized to analyze charge station's traffic conflict with analytical technology
The research of problem is even more blank out.
Summary of the invention
Goal of the invention: aiming at the problems existing in the prior art, the present invention provides a kind of based on automobile video frequency identification
Hybrid mainline toll station traffic conflict evaluation method, this method can be to the severity amounts of progress of charge station's traffic conflict
Change, has important application value to decisions such as charge station's Road Safety Evaluation, managed operation, road drainage measures.
Technical solution: the present invention adopts the following technical scheme: the hybrid mainline toll station based on automobile video frequency identification is handed over
Logical conflict evaluation method, includes the following steps:
(1) camera is arranged in the toll plaza of charge station, the traveling using camera acquisition vehicle in toll plaza regards
Frequently;
(2) vehicle identification and tracking are carried out to collected vehicle driving video, obtains the position of vehicle in each frame image
Set coordinate;
(3) the M frame image data for utilizing vehicle calculates vehicle p in the speed of the i-th frame
WhereinFor vehicle p the i-th frame position coordinates,It is sat for vehicle p in the position of the i-th-M frame
Mark, △ t are the acquisition time interval of M frame image, i > M;
Vehicle p is calculated in the deceleration index of the i-th frame to i-M frame
(4) if vehicle p and vehicle q are clashed in kth frame, calculating refers in the time of the vehicle following-model of kth frame
Mark TTCk:
WhereinFor vehicle q kth frame position coordinates, vehicle q be in kth frame image vehicle p with vehicle of speeding;
Calculate the Vehicular turn model time index T in kth framepet:
Tpet=Fpe-Fdr
Wherein FdrPicture frame serial number when reducing speed now for front vehicle;FpeIt is the picture frame serial number that vehicle clashes;
(5) willTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation index STC is unified for, according to STC's
Value judges the severity of traffic conflict.
In the camera quantity N of toll plaza arrangement in step (1) are as follows:
Wherein m is toll collection lanes number, and I is the toll collection lanes number that camera can take;For the fortune that rounds up
It calculates.
Camera position are as follows: camera face charge station is arranged widening side road, will be imaged in non-side of widening
Head face road setting.
Vehicle identification is carried out to collected video in step (2) and tracking specifically includes:
(2.1) preliminary prospect is generated to the video image of shooting, binaryzation, dilation erosion processing is carried out, before generating detection
Scape;
(2.2) modeling and frame difference method are eliminated with BSM background, recognition and tracking is carried out to the moving vehicle in video;
(2.3) detection vehicle is extracted in the position coordinates and picture frame serial number of each frame.
The change in location of vehicle is very small in successive frame, is counted in step 3 using 6 frame image datas of automobile video frequency
It calculates, i.e. M=6.
Following equation is pressed in step (5) willTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation is unified for
Index S TC:
Wherein α, beta, gamma, μ are conversion coefficient, are constant.
The error of single index impacts judging result in order to prevent, willTTCkAnd TpetAfter at the same levelization processing
Traffic conflict evaluation index STCTTC、STCDRAnd STCTpetBe converted to comprehensive traffic conflict evaluation index R:
Wherein λ is weight coefficient;The severity of traffic conflict is judged according to R value.
As R > 1.15, it is determined as serious traffic conflict;As 0.9 < R < 1.15, it is determined as moderate traffic conflict;When 0.7
When < R < 0.9, it is determined as slight traffic conflict.
The utility model has the advantages that compared with prior art, the hybrid main line charge disclosed by the invention based on automobile video frequency identification
Traffic conflict evaluation method of standing has the advantage that 1, this method without artificial field research, and readily available data form network
Camera can get multi-faceted video data, amount of storage is big, can call at any time, and it is quick accurate to calculate;2, the present invention establishes
Charge station's traffic conflict evaluation model, calculate simple, comprehensively considered time class, speed class index to the serious journey of traffic conflict
The contribution degree of degree has important applying value to charge station's operation management, road drainage measure decision.
Detailed description of the invention
Fig. 1 is the hybrid mainline toll station traffic conflict characteristic research method flow chart being fitted based on video;
Fig. 2 is that charge station's camera arrangement schematic diagram is widened in unilateral transition;
Fig. 3 is the video foreground figure generated and treated video detection foreground picture;
Fig. 4 is moving vehicle recognition and tracking figure.
Specific embodiment
With reference to the accompanying drawings and detailed description, the present invention is furture elucidated.
The present embodiment is to acquire the shooting of hybrid mainline toll station morning 8:30-8:34 on Shanghai-Hangzhou-Ningbo S2 highway
The video of totally 3 points of 50 seconds durations, to the charge station, traffic conflict problem is analyzed.
The present invention provides it is a kind of based on automobile video frequency identification hybrid mainline toll station traffic conflict evaluation method,
As shown in Figure 1, including the following steps:
Step 1 arranges camera in the toll plaza of charge station, the traveling using camera acquisition vehicle in toll plaza
Video;
In the camera quantity N of toll plaza arrangement are as follows:
Wherein m is toll collection lanes number, and I is the toll collection lanes number that camera can take, and is had with camera parameter
It closes, generally 4-6, camera used in the present embodiment can take 6 toll collection lanes;For the operation that rounds up.This
Charge station's one direction shares 10 toll collection lanes in embodiment, needs to arrange
It (is widened substantially without transition, unilateral transition is widened, bilateral according to the 3 of charge station toll plaza kinds of road widening forms
Transition is widened, in order to avoid road widening make it is unsighted cause vehicle identification incomplete, widening side road for camera just
Charge station is arranged, in non-side of widening by the setting of camera face road.Charge station's unilateral direction toll plaza form is
Form is widened in unilateral side, and face charge station arranges camera at widening road.Fig. 2 is two cameras of charge station in the present embodiment
Arrangement schematic diagram, wherein 1 face charge station of camera places, and 2 face road of camera is placed.
Step 2 carries out vehicle identification and tracking to collected vehicle driving video, obtains vehicle in each frame image
Position coordinates specifically comprise the following steps:
(2.1) preliminary prospect is generated to the video image of shooting, binaryzation, dilation erosion processing is carried out, before generating detection
Scape, if Fig. 3 (a) show preliminary prospect schematic diagram, Fig. 3 (b) is to pass through pretreated detection prospect schematic diagram;
(2.2) modeling and frame difference method are eliminated with BSM background, recognition and tracking, such as Fig. 4 is carried out to the moving vehicle in video
Driving vehicle that is shown, being identified in box;
(2.3) extracting detection vehicle in the position coordinates and picture frame serial number of each frame is as shown in table 1 the 3 of acquisition
The position coordinates of vehicle and the picture frame serial number in acquired video.
Table 1
Step 3, the M frame image data using vehicle calculate vehicle p in the speed of the i-th frame
WhereinFor vehicle p the i-th frame position coordinates,It is sat for vehicle p in the position of the i-th-M frame
Mark, △ t are the acquisition time interval of M frame image, i > M;
Vehicle p is calculated in the deceleration index of the i-th frame to i-M frame
The change in location of vehicle is very small in successive frame, and the value of M is too small, and the position of vehicle is almost unchanged, calculated
Velocity accuracy is not high, if value is too big, vehicle location variation is too many, and time interval is also big, possibly can not reflect vehicle
The details of change in location, also influences whether computational accuracy.Frequency is used to regard for the camera of 24Hz using vehicle in the present embodiment
6 frame image datas of frequency are calculated, i.e. M=6, and the △ t in such above-mentioned formula is 0.25 second.
(4) if vehicle p and vehicle q are clashed in kth frame, calculating refers in the time of the vehicle following-model of kth frame
Mark TTCk:
WhereinFor vehicle q kth frame position coordinates, vehicle q be in kth frame image vehicle p with vehicle of speeding;
Calculate the Vehicular turn model time index T in kth framepet:
Tpet=Fpe-Fdr
Wherein FdrPicture frame serial number when reducing speed now for front vehicle;FpeIt is the picture frame serial number that vehicle clashes;
Traffic conflict analysis indexes, calculated result such as 2 institute of table are calculated to more traffic conflicts in video and the vehicle being related to
Show, wherein DR is front vehicle deceleration index when traffic conflict occurs.
Table 2
With the serial number that conflicts of speeding | Conflict car number | TTC(s) | DR(m/s2) |
1 | 32-33 | 4.09 | 1.36 |
2 | 66-73 | 2.81 | 0.32 |
3 | 73-79 | 4.82 | 0.44 |
4 | 79-80 | 7.11 | 1.67 |
Lane change conflict serial number | Conflict car number | Tpet(s) | DR(m/s2) |
1 | 1-4 | 1.76 | 0.64 |
2 | 66-70 | 2.13 | — |
3 | 101-102 | 0.75 | — |
Step 5 is incited somebody to actionTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation index STC is unified for, according to
The value of STC judges the severity of traffic conflict.
It will by following equationTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation index STC is unified for:
Wherein α, beta, gamma, μ are conversion coefficient, are constant.In the present embodiment, α=2, β=0.491, γ=2, μ=
0.36, concrete outcome is as shown in table 3.
Table 3
TTC | 0-3s | 3-5s | 5-8s | >8s |
STCTTC | >1.15 | 0.9-1.15 | 0.7-0.9 | 0-0.7 |
Severity | Seriously | Moderate | Slightly | Nothing |
Tpet | 0-1.5s | 1.5-2.5s | 2.5-4s | >4s |
STCTpet | >1.15 | 0.9 | 0.7-0.9 | 0-0.7 |
Severity | Seriously | Moderate | Slightly | Nothing |
DR | >5m/s2 | 3-5m/s2 | 2-3m/s2 | <2m/s2 |
STCDR | >1.15 | 0.9 | 0.7-0.9 | <0.7 |
Severity | Seriously | Moderate | Slightly | Nothing |
According to STCTTC、STCDRAnd STCTpetTraffic conflict degree can be judged, in order to prevent the mistake of single index
Difference impacts judging result, willTTCkAnd TpetPeerization treated traffic conflict evaluation index STCTTC、STCDR
And STCTpetComprehensive traffic conflict evaluation index R is converted to quantify to traffic conflict degree, judges that traffic is rushed according to R value
The calculating of prominent severity, R is as follows:
Wherein λ is weight coefficient, and value range is 0.1~0.9, and specific value can be according to road conditions, vehicle, charge station place
Equal objective informations determine, λ value is bigger when general saturation degree is lower;λ value is smaller when saturation degree is higher;The present embodiment period receives
It is smaller to take station saturation degree, taking λ is 0.75, calculates and the final result of judgement is as shown in table 4.As R > 1.15, it is determined as serious
Traffic conflict;As 0.9 < R < 1.15, it is determined as moderate traffic conflict;As 0.7 < R < 0.9, it is determined as slight traffic conflict.
Table 4
Traffic conflict serial number | Conflict car number | R | Severity |
1 | 1-4 | 1.07 | Moderate |
2 | 32-33 | 0.99 | Moderate |
3 | 66-70 | 0.97 | Moderate |
4 | 66-73 | 1.19 | Seriously |
5 | 73-79 | 0.91 | Moderate |
6 | 79-80 | 0.75 | Slightly |
7 | 101-102 | 1.63 | Seriously |
Claims (5)
1. the hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification, which is characterized in that including as follows
Step:
(1) camera is arranged in the toll plaza of charge station, the traveling video using camera acquisition vehicle in toll plaza;
(2) vehicle identification and tracking are carried out to collected vehicle driving video, the position for obtaining vehicle in each frame image is sat
Mark;
(3) the M frame image data for utilizing vehicle calculates vehicle p in the speed of the i-th frame
WhereinFor vehicle p the i-th frame position coordinates,For vehicle p the i-th-M frame position coordinates,
△ t is the acquisition time interval of M frame image, i > M;
Vehicle p is calculated in the deceleration index of the i-th frame to i-M frame
(4) if vehicle p and vehicle q are clashed in kth frame, the time index in the vehicle following-model of kth frame is calculated
TTCk:
WhereinFor vehicle q kth frame position coordinates, vehicle q be in kth frame image vehicle p with vehicle of speeding;
Calculate the Vehicular turn model time index T in kth framepet:
Tpet=Fpe-Fdr
Wherein FdrPicture frame serial number when reducing speed now for front vehicle;FpeIt is the picture frame serial number that vehicle clashes;
(5) willTTCkAnd TpetPeerization processing is carried out, traffic conflict evaluation index STC is unified for, is sentenced according to the value of STC
The severity of disconnected traffic conflict;It will by following equationTTCkAnd TpetPeerization processing is carried out, traffic conflict is unified for
Evaluation index STC:
Wherein α, beta, gamma, μ are conversion coefficient, are constant;
It willTTCkAnd TpetPeerization treated traffic conflict evaluation index STCTTC、STCDRAnd STCTpetBe converted to synthesis
Traffic conflict evaluation index R:
Wherein λ is weight coefficient;
The severity of traffic conflict is judged according to R value;
As R > 1.15, it is determined as serious traffic conflict;As 0.9 < R < 1.15, it is determined as moderate traffic conflict;When 0.7 < R <
When 0.9, it is determined as slight traffic conflict.
2. the hybrid mainline toll station traffic conflict evaluation method according to claim 1 based on automobile video frequency identification,
It is characterized in that, in the camera quantity N of toll plaza arrangement in step (1) are as follows:
Wherein m is toll collection lanes number, and I is the toll collection lanes number that camera can take;For the operation that rounds up.
3. the hybrid mainline toll station traffic conflict evaluation method according to claim 1 based on automobile video frequency identification,
It is characterized in that, the camera position that toll plaza is arranged in step (1) are as follows: camera face is charged widening side road
It stands setting, widens side non-camera face road is arranged.
4. the hybrid mainline toll station traffic conflict evaluation method according to claim 1 based on automobile video frequency identification,
It is characterized in that, step (2) specifically includes:
(2.1) preliminary prospect is generated to the video image of shooting, carries out binaryzation, dilation erosion processing, generates detection prospect;
(2.2) modeling and frame difference method are eliminated with BSM background, recognition and tracking is carried out to the moving vehicle in video;
(2.3) detection vehicle is extracted in the position coordinates and picture frame serial number of each frame.
5. the hybrid mainline toll station traffic conflict evaluation method according to claim 1 based on automobile video frequency identification,
It is characterized in that, being calculated in step 3 using 6 frame image datas of automobile video frequency, i.e. M=6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710573312.5A CN107248290B (en) | 2017-07-14 | 2017-07-14 | Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710573312.5A CN107248290B (en) | 2017-07-14 | 2017-07-14 | Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107248290A CN107248290A (en) | 2017-10-13 |
CN107248290B true CN107248290B (en) | 2019-07-12 |
Family
ID=60014650
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710573312.5A Active CN107248290B (en) | 2017-07-14 | 2017-07-14 | Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107248290B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108986457B (en) * | 2018-07-02 | 2020-12-11 | 东南大学 | ETC lane layout scheme evaluation method based on traffic conflict analysis |
CN114926984A (en) * | 2022-05-17 | 2022-08-19 | 华南理工大学 | Real-time traffic conflict collection and road safety evaluation method |
CN116151619A (en) * | 2023-02-03 | 2023-05-23 | 合肥工业大学智能制造技术研究院 | Video analysis-based road parking safety evaluation method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521438B (en) * | 2011-12-02 | 2013-12-04 | 东南大学 | Traffic conflict simulation two-stage parameter calibrating method |
CN102592448A (en) * | 2012-01-18 | 2012-07-18 | 河海大学 | Method for testing safety performance of unsignalized intersection by utilizing equivalent traffic conflict |
CN105243876B (en) * | 2015-11-06 | 2017-05-24 | 东南大学 | Traffic conflict severity analysis method used for interchange |
CN106780272B (en) * | 2016-12-05 | 2020-10-30 | 南通大学 | Method for calculating length of rhombic overpass deceleration ramp by utilizing traffic conflict |
-
2017
- 2017-07-14 CN CN201710573312.5A patent/CN107248290B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107248290A (en) | 2017-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
CN103700174B (en) | A kind of bus passenger flow data acquisition based on WIFI identification and OD analytical approach | |
CN107248290B (en) | Hybrid mainline toll station traffic conflict evaluation method based on automobile video frequency identification | |
CN108550261B (en) | Urban traffic OD (origin-destination) calculation method based on RFID (radio frequency identification) electronic license plate | |
CN102646332B (en) | Traffic state estimation device and method based on data fusion | |
CN104392610B (en) | Expressway based on distributed video traffic events coverage dynamic monitoring and controlling method | |
CN103531031B (en) | It is a kind of that the current control method that blocks by nothing is realized based on the identification of urban traffic trunk line pliable-closure area video detection | |
CN108921956A (en) | A kind of curb parking charge management method based on Video Analysis Technology | |
CN101941449B (en) | Method and system for analyzing outlet/inlet section line capacity of urban railway system | |
CN111402613B (en) | Method for selecting lane of toll station for automatically driving vehicle | |
CN106710215B (en) | Bottleneck upstream lane grade traffic status prediction system and implementation method | |
CN104504364B (en) | Stop line Real time identification and distance-finding method based on space time correlation | |
CN109389826A (en) | A kind of real-time computing technique of signalized intersections saturation volume rate | |
CN103714363A (en) | Motor vehicle exhaust smoke video identification system | |
CN108597219A (en) | A kind of section pedestrian's street crossing control method based on machine vision | |
CN103198713A (en) | Traffic accident reduction vehicle regulation and control method based on traffic data and weather data | |
CN109278758B (en) | Intelligent vehicle personalized driving learning system based on intelligent mobile phone | |
CN111243338A (en) | Vehicle acceleration-based collision risk evaluation method | |
CN103679214B (en) | Vehicle checking method based on online Class area estimation and multiple features Decision fusion | |
CN103164958B (en) | Method and system for vehicle monitoring | |
CN109118787A (en) | A kind of car speed prediction technique based on deep neural network | |
CN110444015A (en) | Intelligent network based on no signal crossroad subregion joins car speed decision-making technique | |
CN109215141A (en) | A kind of road parking field fence management and Internet payment system | |
CN112907955A (en) | Evaluation method of vehicle-road cooperative system based on information fusion | |
CN103778790B (en) | A kind of vehicle flowrate square wave statistic law based on video sequence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |