CN107194386A - A kind of intersection electric bicycle travel speed acquisition methods based on video - Google Patents
A kind of intersection electric bicycle travel speed acquisition methods based on video Download PDFInfo
- Publication number
- CN107194386A CN107194386A CN201710593862.3A CN201710593862A CN107194386A CN 107194386 A CN107194386 A CN 107194386A CN 201710593862 A CN201710593862 A CN 201710593862A CN 107194386 A CN107194386 A CN 107194386A
- Authority
- CN
- China
- Prior art keywords
- electric bicycle
- mrow
- msub
- video
- intersection
- 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
Classifications
-
- 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
-
- 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
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intersection electric bicycle travel speed acquisition methods based on video, comprise the following steps：1st, the vehicle traveling video of collection intersection, it is the region that a plurality of pavement is enclosed to set the detection zone in video；2nd, the video of collection is handled, the electric bicycle of intersection in recognition and tracking video, obtains driving trace coordinate points；3rd, the center-of-mass coordinate of electric bicycle on the video images is converted into actual two-dimensional plane coordinate, calculates its travel speed.This method can accurately obtain the travel speed of electric bicycle inside intersection.
Description
Technical field
The invention belongs to traffic monitoring field, and in particular to one kind obtains electrical salf-walking garage using computer vision technique
The method for sailing speed.
Background technology
In recent years, accounting of the electric bicycle in traffic trip structure increasingly increases.Electric bicycle is compared to walking
Muscle power is more saved in trip, and speed is faster；And compared with automobile, it have driven by power without discharge, it is environment-friendly pollution less,
It is not afraid of congestion and the low advantage of cost.Electric bicycle is this fast, cleaning and trip mode with low cost are very by people
Favor, be increasingly becoming the main traffic mode of the short-distance trip in city.
However, this trip mode of electric bicycle is also handed over while China is developed rapidly with popularizing to urban road
Prong adds congestion, security problems.Electric bicycle bicyclist ignores road safety laws and regulations, is such as passed through in intersection
Often occur that electric bicycle drives into the traveling spaces of motor vehicles, traffic signal violation, hypervelocity robs row and electronic car owner changes privately
Fill electric car and carry out the behaviors such as cargo transport, be the key factor for causing electric bicycle driving safety low.How rationally to divide
Analysis, specification electric bicycle also need to obtain the driving parameters of electric bicycle, including traveling speed in the driving behavior of intersection
Degree, safety traffic region and safe velocity.
The mathematics that the extraction both at home and abroad to the microcosmic traffic data of electric bicycle is predominantly obscured at present is calculated, this to adjust
The subjective initiative sexual intercourse for looking into mode and people is very big, and observation of the investigator to data has unstability, and that extrapolates is microcosmic
Often precision is relatively low for traffic data.
The content of the invention
Goal of the invention：For problems of the prior art, the invention provides a kind of intersection based on video
Mouth electric bicycle travel speed acquisition methods, this method can accurately obtain the traveling of electric bicycle inside intersection
Speed.
Technical scheme：The present invention is adopted the following technical scheme that：A kind of intersection electrical salf-walking garage based on video
Velocity acquiring method is sailed, is comprised the following steps：
(1) the vehicle traveling video of collection intersection, sets the detection zone in video to be enclosed for a plurality of pavement
Region；
(2) video of collection is handled, the electric bicycle of intersection in recognition and tracking video, obtains traveling
Trajectory coordinates point；
(3) center-of-mass coordinate of electric bicycle on the video images is converted into actual two-dimensional plane coordinate, calculates its row
Sail speed.
Step (2) comprises the following steps：
(2-1) sets up the background image model f (x, y) of gathered intersection video；Mixed Gaussian can be used
Background modeling method sets up background image model f (x, y)；
The background image model that t frames original image in video and step (2-1) are set up is made poor by (2-2), obtains t frames
Foreground moving object A (xt,yt)；Foreground moving object calculation formula is：
A(xt,yt)=f (xt,yt)-f(x,y)
Wherein, f (xt,yt) it is t frame original images, f (x, y) is background image；
Multiple image in (2-3) selecting video, to the foreground moving object in each two field picture for before electric bicycle
Scape agglomerate, calculates its agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle；
(2-4) sets up electric bicycle parameter model, and the parameter of the model is electric bicycle agglomerate area S, agglomerate
The length L of boundary rectangle, the width W of agglomerate boundary rectangle；The parameter obtained in (2-3) is counted, distribution probability is chosen
For η parameter codomain as electric bicycle parameter model span；
(2-5) obtains foreground moving object A for the i-th two field picture in video and jth two field pictureiAnd Aj, calculate corresponding
Prospect agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle, join according in electric bicycle parameter model
Number span, judges AiAnd AjWhether it is electric bicycle；
(2-6) is if AiAnd AjIt is electric bicycle, calculates AiAnd AjBarycenter piAnd pj, centroid distance dijIf, it is full
Sufficient condition：Then AiAnd AjFor same electric bicycle, piAnd pjAs described electric bicycle is in the i-th frame figure
Driving trace coordinate points in picture and jth two field picture.
Step (3) comprises the following steps：
Actual travel of (3-1) electric bicycle in a two field pictures and b two field pictures is apart from dabFor：
Wherein (ua,va) be a two field pictures in electric bicycle two-dimentional geographical coordinates；(ub,vb) in b two field pictures
The two-dimentional geographical coordinates of electric bicycle；
Average speed v of (3-2) electric bicycle between a two field pictures and b two field picturesabFor：
Wherein tabFor the time difference between a two field pictures and b two field pictures.
Instantaneous velocity Speed of the electric bicycle in f two field picturesfFor：
Wherein r is the frame per second of video, (uf,vf) be f two field pictures in electric bicycle two-dimentional geographical coordinates, (uf+1,
vf+1) be f+1 two field pictures in electric bicycle two-dimentional geographical coordinates.
Beneficial effect：Compared with prior art, the intersection electrical salf-walking garage disclosed by the invention based on video
Sailing velocity acquiring method has advantages below：1st, the driving trace for the electric bicycle that can be accurately obtained inside intersection and
Travel speed；2nd, repeatable detection method, accuracy rate height and parameter easily change to the video source captured by different intersections
Good characteristic, the traveling behavioural analysis to electric bicycle in intersection has great significance.
Brief description of the drawings
The flow chart for the method that Fig. 1 provides for the present invention；
Fig. 2 is the detail flowchart of electric bicycle tracking step；
Fig. 3 is original image and background image detection zone figure；
Fig. 4 is foreground image comparison diagram before and after foreground image noise reduction；
Fig. 5 is electric bicycle screening effect figure；
Fig. 6 is intersection electric car safety traffic areal map；
Fig. 7 is intersection electric bicycle maximum speed hour distribution map.
Embodiment
The present embodiment is retrieved as with the electric bicycle travel speed of Nanjing East Zhongshan Road-peace North Road intersection
Example, the present invention is furture elucidated.
As shown in figure 1, the present invention provides a kind of intersection electric bicycle travel speed acquisition side based on video
Method, comprises the following steps：
(1) the vehicle traveling video of collection intersection, sets the detection zone in video to be enclosed for a plurality of pavement
Region；
To overlook viewing angles East Zhongshan Road-peace North Road cross intersection；Setting detection zone 1 is the intersection
Polygonal region in the region that a plurality of pavement is enclosed, such as Fig. 3 (b).
(2) video of collection is handled, the electric bicycle of intersection in recognition and tracking video, obtains traveling
Trajectory coordinates point；As shown in Fig. 2 specifically including following steps：
(2-1) sets up the background image model f (x, y) of gathered intersection video；The present embodiment is using mixing
Gaussian Background modeling sets up background image model f (x, y)；
The background image model that t frames original image in video and step (2-1) are set up is made poor by (2-2), obtains t frames
Foreground moving object A (xt,yt)；Foreground moving object calculation formula is：
A(xt,yt)=f (xt,yt)-f(x,y)
Wherein, f (xt,yt) it is t frame original images, f (x, y) is background image；
Obtain foreground moving object A (xt,yt) after, to A (xt,yt) operation is filtered, to remove electric bicycle shade
To A (x in part and noise, the present embodimentt,yt) gaussian filtering, filter effect are carried out as shown in figure 4, wherein (a) is before filtering
Foreground image；(b) it is filtered foreground image.
Multiple image in (2-3) selecting video, to the foreground moving object in each two field picture for before electric bicycle
Scape agglomerate, calculates its agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle；
(2-4) sets up electric bicycle parameter model, and the parameter of the model is electric bicycle agglomerate area S, agglomerate
The length L of boundary rectangle, the width W of agglomerate boundary rectangle；The parameter obtained in step (2-3) is counted, distribution is chosen
Probability for 80% parameter codomain as electric bicycle parameter model span；
(2-5) obtains foreground moving object A for the i-th two field picture in video and jth two field pictureiAnd Aj, calculate corresponding
Prospect agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle, join according in electric bicycle parameter model
Number span, judges AiAnd AjWhether it is electric bicycle；As shown in figure 5, square frame is to be judged as before electric bicycle in figure
Scape image.
(2-6) is if AiAnd AjIt is electric bicycle, calculates AiAnd AjBarycenter piAnd pj, centroid distance dijIf, two
Electric bicycle in two field picture is same, then its distance travelled in very short time is minimum not over one
Numerical value, therefore the poor threshold value f of frame is setthCarry out control time, while setting distance threshold dthCarry out command range.Set in the present embodiment
Put dthFor 20 pixels, fthFor 20 frames.If meeting condition：Then AiAnd AjFor same electric bicycle, piWith
pjDriving trace coordinate points of the as described electric bicycle in the i-th two field picture and jth two field picture.
Centroid calculation formula is：
Wherein, mpqFor the p+q rank squares of image, (xc,yc) be image barycenter, A (x, y) is the electric bicycle that detects
Agglomerate image, N and M are respectively image length and width value.
It is apart from calculation formula between agglomerate barycenter in i-th two field picture and jth two field picture：
Wherein (xci,yci) be the i-th two field picture in electric bicycle agglomerate center-of-mass coordinate.
(3) center-of-mass coordinate of electric bicycle on the video images is converted into actual two-dimensional plane coordinate, calculates its row
Sail speed.
Pixel coordinate is converted into two-dimentional geographical coordinates with homogeneous coordinates conversion method in the present embodiment, conversion distance with
Actual range error analysis is as shown in table 1：
Table 1
In this four samples, all error rates of inspection are below 5%, and average error rate is 3%.The intersection is long
For 20 meters, the overall error that electric bicycle crosses the intersection is 60 centimetres, and the conflict analysis for electric bicycle can be neglected
Slightly.
It is the step of electric bicycle average speed between calculating two field pictures：
Actual travel of (3-1) electric bicycle in a two field pictures and b two field pictures is apart from dabFor：
Wherein (ua,va) be a two field pictures in electric bicycle two-dimentional geographical coordinates；(ub,vb) in b two field pictures
The two-dimentional geographical coordinates of electric bicycle；
Average speed v of (3-2) electric bicycle between a two field pictures and b two field picturesabFor：
Wherein tabFor the time difference between a two field pictures and b two field pictures.
Instantaneous velocity Speed of the electric bicycle in f two field picturesfFor：
Wherein r is the frame per second of video, (uf,vf) be f two field pictures in electric bicycle two-dimentional geographical coordinates, (uf+1,
vf+1) be f+1 two field pictures in electric bicycle two-dimentional geographical coordinates.
To being counted by the electric bicycle travel speed of intersection, it can obtain intraoral in the intersection
Safety traffic region and safe velocity, step is as follows：
Count electric bicycle pass through intersection maximum speed, the maximum speed of operation 20km/s of national regulation,
That is 5.5m/s, the accumulative figure of its driving trace is obtained to the electric bicycle do not driven over the speed limit, intersection internal security traveling is drawn
Administrative division map, as shown in Figure 6.
Count the maximum speed by intersection electric bicycle, maximum speed distribution situation such as table in the peak hour
Shown in 2, maximum speed distribution map is as shown in Figure 7.
Table 2
From table 2 and Fig. 7：Electric bicycle maximum speed is distributed in 5.5-6.5m/s, 6.5-7.5m/s, 7.5-
8.5m/s, more than 8.5m/s are the electric car driven over the speed limit in this four intervals, and its distribution probability is respectively 5%, 4%, 2%
With 0%, the electric car maximal rate overall distribution probability driven over the speed limit is 11%.
The electric bicycle maximum speed do not driven over the speed limit is concentrated the most between being distributed in 2.5-3.5m/s, and probability is
46%.By the ascending arrangement of the speed data not exceeded the speed limit, preceding 15% speed data and rear 15% speed data, choosing are removed
It is [2.5,5.0] to take residual velocity parameter distribution interval as safe velocity interval, and unit is m/s.
Claims (5)
1. a kind of intersection electric bicycle travel speed acquisition methods based on video, it is characterised in that including as follows
Step：
(1) the vehicle traveling video of collection intersection, it is the area that a plurality of pavement is enclosed to set the detection zone in video
Domain；
(2) video of collection is handled, the electric bicycle of intersection in recognition and tracking video, obtains driving trace
Coordinate points；
(3) center-of-mass coordinate of electric bicycle on the video images is converted into actual two-dimensional plane coordinate, calculates its traveling speed
Degree.
2. the intersection electric bicycle travel speed acquisition methods according to claim 1 based on video, it is special
Levy and be, step (2) comprises the following steps：
(2-1) sets up the background image model f (x, y) of gathered intersection video；
The background image model that t frames original image in video and step (2-1) are set up is made poor by (2-2), obtains t frame prospects
Moving target A (xt,yt)；Foreground moving object calculation formula is：
A(xt,yt)=f (xt,yt)-f(x,y)
Wherein, f (xt,yt) it is t frame original images, f (x, y) is background image；
Multiple image in (2-3) selecting video, to the prospect group that the foreground moving object in each two field picture is electric bicycle
Block, calculates its agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle；
(2-4) sets up electric bicycle parameter model, and the parameter of the model is electric bicycle agglomerate area S, and agglomerate is external
The length L of rectangle, the width W of agglomerate boundary rectangle；The parameter obtained in (2-3) is counted, it is η's to choose distribution probability
Parameter codomain as electric bicycle parameter model span；
(2-5) obtains foreground moving object A for the i-th two field picture in video and jth two field pictureiAnd Aj, calculate corresponding prospect
Agglomerate area, the length of agglomerate boundary rectangle, the width of agglomerate boundary rectangle, take according to parameter in electric bicycle parameter model
It is worth scope, judges AiAnd AjWhether it is electric bicycle；
(2-6) is if AiAnd AjIt is electric bicycle, calculates AiAnd AjBarycenter piAnd pj, centroid distance dijIf meeting bar
Part：Then AiAnd AjFor same electric bicycle, piAnd pjAs described electric bicycle in the i-th two field picture and
Driving trace coordinate points in jth two field picture.
3. the intersection electric bicycle travel speed acquisition methods according to claim 1 based on video, it is special
Levy and be, step (3) comprises the following steps：
Actual travel of (3-1) electric bicycle in a two field pictures and b two field pictures is apart from dabFor：
<mrow>
<msub>
<mi>d</mi>
<mrow>
<mi>a</mi>
<mi>b</mi>
</mrow>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>u</mi>
<mi>a</mi>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>b</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>a</mi>
</msub>
<mo>-</mo>
<msub>
<mi>v</mi>
<mi>b</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
Wherein (ua,va) be a two field pictures in electric bicycle two-dimentional geographical coordinates；(ub,vb) be b two field pictures in it is electronic from
The two-dimentional geographical coordinates of driving；
Average speed v of (3-2) electric bicycle between a two field pictures and b two field picturesabFor：
<mrow>
<msub>
<mi>v</mi>
<mrow>
<mi>a</mi>
<mi>b</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>d</mi>
<mrow>
<mi>a</mi>
<mi>b</mi>
</mrow>
</msub>
<msub>
<mi>t</mi>
<mrow>
<mi>a</mi>
<mi>b</mi>
</mrow>
</msub>
</mfrac>
</mrow>
Wherein tabFor the time difference between a two field pictures and b two field pictures.
4. the intersection electric bicycle travel speed acquisition methods according to claim 1 based on video, it is special
Levy and be, instantaneous velocity Speed of the electric bicycle in f two field picturesfFor：
<mrow>
<msub>
<mi>Speed</mi>
<mi>f</mi>
</msub>
<mo>=</mo>
<mi>r</mi>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>u</mi>
<mi>f</mi>
</msub>
<mo>-</mo>
<msub>
<mi>u</mi>
<mrow>
<mi>f</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>f</mi>
</msub>
<mo>-</mo>
<msub>
<mi>v</mi>
<mrow>
<mi>f</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
Wherein r is the frame per second of video, (uf,vf) be f two field pictures in electric bicycle two-dimentional geographical coordinates, (uf+1,vf+1) be
The two-dimentional geographical coordinates of electric bicycle in f+1 two field pictures.
5. the intersection electric bicycle travel speed acquisition methods according to claim 2 based on video, it is special
Levy and be, step (2-1) sets up background image model f (x, y) using mixed Gaussian background modeling method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710593862.3A CN107194386A (en) | 2017-07-20 | 2017-07-20 | A kind of intersection electric bicycle travel speed acquisition methods based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710593862.3A CN107194386A (en) | 2017-07-20 | 2017-07-20 | A kind of intersection electric bicycle travel speed acquisition methods based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107194386A true CN107194386A (en) | 2017-09-22 |
Family
ID=59884101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710593862.3A Pending CN107194386A (en) | 2017-07-20 | 2017-07-20 | A kind of intersection electric bicycle travel speed acquisition methods based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107194386A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615862A (en) * | 2018-12-29 | 2019-04-12 | 南京市城市与交通规划设计研究院股份有限公司 | Road vehicle movement of traffic state parameter dynamic acquisition method and device |
| CN113380035A (en) * | 2021-06-16 | 2021-09-10 | 山东省交通规划设计院集团有限公司 | Road intersection traffic volume analysis method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592454A (en) * | 2012-02-29 | 2012-07-18 | 北京航空航天大学 | Intersection vehicle movement parameter measuring method based on detection of vehicle side face and road intersection line |
| CN103971521A (en) * | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
| CN105786895A (en) * | 2014-12-25 | 2016-07-20 | 日本电气株式会社 | Calculating method and device of discharge amount of road intersection |
-
2017
- 2017-07-20 CN CN201710593862.3A patent/CN107194386A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592454A (en) * | 2012-02-29 | 2012-07-18 | 北京航空航天大学 | Intersection vehicle movement parameter measuring method based on detection of vehicle side face and road intersection line |
| CN103971521A (en) * | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
| CN105786895A (en) * | 2014-12-25 | 2016-07-20 | 日本电气株式会社 | Calculating method and device of discharge amount of road intersection |
Non-Patent Citations (1)
| Title |
|---|
| 盛能: "混合交通流中的自行车识别及参数提取", 《计算机应用研究》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615862A (en) * | 2018-12-29 | 2019-04-12 | 南京市城市与交通规划设计研究院股份有限公司 | Road vehicle movement of traffic state parameter dynamic acquisition method and device |
| CN113380035A (en) * | 2021-06-16 | 2021-09-10 | 山东省交通规划设计院集团有限公司 | Road intersection traffic volume analysis method and system |
| CN113380035B (en) * | 2021-06-16 | 2022-11-11 | 山东省交通规划设计院集团有限公司 | Road intersection traffic volume analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105005771B (en) | A kind of detection method of the lane line solid line based on light stream locus of points statistics | |
| CN107590438A (en) | A kind of intelligent auxiliary driving method and system | |
| CN107577996A (en) | A kind of recognition methods of vehicle drive path offset and system | |
| CN103778429B (en) | Automatic extraction method for road information in a kind of Vehicle-borne Laser Scanning point cloud | |
| CN105632186A (en) | Method and device for detecting vehicle queue jumping behavior | |
| CN103473762B (en) | A kind of method for detecting lane lines and device | |
| CN101789123B (en) | Method for creating distance map based on monocular camera machine vision | |
| CN106127137A (en) | A kind of target detection recognizer based on 3D trajectory analysis | |
| CN110992676B (en) | Road traffic capacity and internet automatic driving vehicle equivalent coefficient estimation method | |
| CN104008645A (en) | Lane line predicating and early warning method suitable for city road | |
| CN103413325B (en) | A kind of speed of a motor vehicle authentication method based on vehicle body positioning feature point | |
| CN103313039B (en) | A kind of freeway tunnel entrance security prompt device on daytime and reminding method | |
| CN111539303B (en) | Monocular vision-based vehicle driving deviation early warning method | |
| CN104574544B (en) | Method for communicating with OBU and RSU | |
| CN105427620B (en) | A kind of illegal operation vehicle identification method based on taxi service data | |
| CN103544489A (en) | Device and method for locating automobile logo | |
| CN107145825A (en) | Ground level fitting, camera calibration method and system, car-mounted terminal | |
| CN104504364A (en) | Real-time stop line recognition and distance measurement method based on temporal-spatial correlation | |
| CN107967804A (en) | A kind of more rotors carry the vehicle cab recognition and vehicle speed measurement device and method of laser radar | |
| CN106548628A (en) | The road condition analyzing method that a kind of view-based access control model space transition net is formatted | |
| CN104574993A (en) | Road monitoring method and device | |
| CN107194386A (en) | A kind of intersection electric bicycle travel speed acquisition methods based on video | |
| CN110705484A (en) | Method for recognizing illegal behavior of continuously changing lane by using driving track | |
| CN106991804A (en) | A kind of city bus operating mode construction method coupled based on multi-line | |
| CN105761507A (en) | Vehicle counting method based on three-dimensional trajectory clustering |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170922 |
|
| RJ01 | Rejection of invention patent application after publication |