CN107945174A - Fastlink visibility measuring method based on video - Google Patents
Fastlink visibility measuring method based on video Download PDFInfo
- Publication number
- CN107945174A CN107945174A CN201711314039.0A CN201711314039A CN107945174A CN 107945174 A CN107945174 A CN 107945174A CN 201711314039 A CN201711314039 A CN 201711314039A CN 107945174 A CN107945174 A CN 107945174A
- Authority
- CN
- China
- Prior art keywords
- trusted area
- fastlink
- video
- measuring method
- visibility
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of fastlink visibility measuring method based on video.Step S1：The image information in video capture fastlink region to be measured, and choose the original data that key frame is calculated as follow-up identification.Step S2：The first trusted area group is selected in original data according to preset trusted area feature templates.Step S3：The characteristic value of the first trusted area group is generated using image recognition technology, and second-order correction is carried out to generate the second trusted area group for the characteristic value of above-mentioned first trusted area group.Step S4：Second trusted area group is compared with preset trusted area feature templates, choose the second trusted area group in the most similar optimal trusted area of preset trusted area feature templates.Fastlink visibility measuring method disclosed by the invention based on video, precisely chooses trusted area, improves antijamming capability, and adverse effect caused by vehicle, barrier is evaded during measuring and calculating.
Description
Technical field
The invention belongs to Vehicle Detection technical field, and in particular to a kind of fastlink visibility measuring and calculating side based on video
Method.
Background technology
Application No. 201610227754.X, subject name are the traffic haze based on dark channel prior Yu minimum image entropy
The application for a patent for invention of visibility detecting method, the height based on dark channel prior and deep learning disclosed in the application for a patent for invention
Fast highway greasy weather visibility detecting method, has preferable accuracy of detection in the range of error permission.
It is worth noting that, the visibility detecting method of foregoing invention patent application publication, has certain limitation, specifically
It is embodied in and is difficult to realize the scape group of trusted area and precisely chooses.In practical operation, usually by super expressway track actual situation line
Realize target of the length as trusted area, this is also one step of key for calculating visibility.Foregoing invention patent application publication
Trusted area setting delineation, fixed in video camera and without other barriers in the case of realize, without practical operation
Feasibility.
In real fastlink, especially in the case where wagon flow is intensive, video camera camera site and angle change often
Become, be unfavorable for setting the target analyte detection of trusted area so that target analyte detection does not conform to the actual conditions or error is far more than permission
Scope, causes final detection result insincere, it is also difficult to which input is actual into practical application.
The content of the invention
The present invention is directed to the situation of the prior art, for above-mentioned technical problem, there is provided a kind of.
The present invention uses following technical scheme, and the fastlink visibility measuring method based on video includes following step
Suddenly：
Step S1：The image information in video capture fastlink region to be measured, and choose key frame and know as follow-up
The original data not calculated；
Step S2：The first trusted area group is selected in original data according to preset trusted area feature templates；
Step S3：The characteristic value of the first trusted area group is generated by image recognition, and for above-mentioned first confidence region
The characteristic value of domain group carries out second-order correction to generate the second trusted area group；
Step S4：Second trusted area group is compared with preset trusted area feature templates, chooses the second confidence region
In the group of domain with the most similar optimal trusted area of preset trusted area feature templates.
According to above-mentioned technical proposal, in step s 2, preset trusted area feature templates include track line slope, track
Line pixel, track line length.
According to above-mentioned technical proposal, in step s 4, preset trusted area feature templates further include track solid line and car
The length ratio of road dotted line.
According to above-mentioned technical proposal, the fastlink visibility measuring method based on video further includes step S5, step
Rapid S5 is located at after step S4：
Step S5：The t1 and t2 at lane line both ends in optimal trusted area are obtained, according to depth information calculation formulaDraw extinction coefficient β.
According to above-mentioned technical proposal, the fastlink visibility measuring method based on video further includes step S6, step
Rapid S6 is located at after step S5：
Step S6：According to visibility formula V=3/ β, range of visibility V is calculated.
According to above-mentioned technical proposal, in step sl, step S11 and step S12 are further included：
Step S11：It is mutually symmetrical upper half range and lower half range by key frame cutting；
Step S12：The original data that the lower half range of key frame is calculated as follow-up identification.
According to above-mentioned technical proposal, in step s3, image recognition includes perspective and becomes with anti-perspective, edge detection and Hough
Change.
According to above-mentioned technical proposal, the fastlink visibility measuring method based on video further includes step S7, step
Rapid S7 is located at after step S6：
Step S7：Preset trusted area feature templates are corrected according to optimal trusted area.
Fastlink visibility measuring method disclosed by the invention based on video, its advantage are, precisely choose
Trusted area, improves antijamming capability, and adverse effect caused by vehicle, barrier is evaded during measuring and calculating.
Brief description of the drawings
Fig. 1 is the flow diagram of the preferred embodiment of the present invention.
Fig. 2 is the process step figure of the preferred embodiment of the present invention.
Embodiment
The invention discloses a kind of fastlink visibility measuring method based on video, with reference to preferred embodiment,
The embodiment of the present invention is further described.
Referring to Fig. 1 and Fig. 2 of attached drawing, the tool of the fastlink visibility measuring method based on video is respectively illustrated
Body flow.Preferably, the fastlink visibility measuring method based on video comprises the following steps：
Step S1：The image information in video capture fastlink region to be measured, and choose key frame and know as follow-up
The original data not calculated；
Step S2：The first trusted area group is selected in original data according to preset trusted area feature templates；
Step S3：The characteristic value of the first trusted area group is generated by image recognition, and for above-mentioned first confidence region
The characteristic value of domain group carries out second-order correction to generate the second trusted area group；
Step S4：Second trusted area group is compared with preset trusted area feature templates, chooses the second confidence region
In the group of domain with the most similar optimal trusted area of preset trusted area feature templates.
Wherein, in step sl, step S11 and step S12 are further included：
Step S11：It is mutually symmetrical upper half range and lower half range by key frame cutting；
Step S12：The original data that the lower half range of key frame is calculated as follow-up identification.
Wherein, in step s 2, preset trusted area feature templates include track line slope, lane line pixel, track
Line length.
Wherein, in step s3, image recognition includes perspective and anti-perspective, edge detection and Hough transformation.
Wherein, in step s 4, preset trusted area feature templates further include the length of track solid line and track dotted line
Than.
Further, the fastlink visibility measuring method based on video further includes step S5, and step S5 is located at
After step S4：
Step S5：The t1 and t2 at lane line both ends in optimal trusted area are obtained, according to depth information calculation formulaDraw extinction coefficient β.
Further, the fastlink visibility measuring method based on video further includes step S6, and step S6 is located at
After step S5：
Step S6：According to visibility formula V=3/ β, range of visibility V is calculated.
Further, the fastlink visibility measuring method based on video further includes step S7, and step S7 is located at
After step S6：
Step S7：Preset trusted area feature templates are corrected according to optimal trusted area, to improve follow-up identification meter
The matching degree of calculation.
Wherein, according to the atmospheric transmissivity calculation formula of dark channel prior theoretical (Dark Channel Prior)：Wherein, I (x) is input picture, and A is sky brightness, and A mainly uses most bright in image
0.1% point of average replace, t (x) is atmospheric transmissivity.
For a person skilled in the art, the technical solution described in foregoing embodiments can still be repaiied
Change, or equivalent substitution is carried out to which part technical characteristic, within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in protection scope of the present invention.
Claims (8)
1. a kind of fastlink visibility measuring method based on video, it is characterised in that comprise the following steps：
Step S1：The image information in video capture fastlink region to be measured, and choose key frame and counted as follow-up identification
The original data of calculation；
Step S2：The first trusted area group is selected in original data according to preset trusted area feature templates；
Step S3：The characteristic value of the first trusted area group is generated by image recognition, and for above-mentioned first trusted area group
Characteristic value carry out second-order correction to generate the second trusted area group；
Step S4：Second trusted area group is compared with preset trusted area feature templates, chooses the second trusted area group
In with the most similar optimal trusted area of preset trusted area feature templates.
2. the fastlink visibility measuring method according to claim 1 based on video, it is characterised in that in step S2
In, preset trusted area feature templates include track line slope, lane line pixel, track line length.
3. the fastlink visibility measuring method according to claim 2 based on video, it is characterised in that in step S4
In, preset trusted area feature templates further include the length ratio of track solid line and track dotted line.
4. the fastlink visibility measuring method according to claim 1 based on video, it is characterised in that described to be based on
The fastlink visibility measuring method of video further includes step S5, and step S5 is located at after step S4：
Step S5：The t1 and t2 at lane line both ends in optimal trusted area are obtained, according to depth information calculation formulaDraw extinction coefficient β.
5. the fastlink visibility measuring method according to claim 4 based on video, it is characterised in that
The fastlink visibility measuring method based on video further includes step S6, and step S6 is located at after step S5：
Step S6：According to visibility formula V=3/ β, range of visibility V is calculated.
6. the fastlink visibility measuring method according to claim 1 based on video, it is characterised in that in step S1
In, further include step S11 and step S12：
Step S11：It is mutually symmetrical upper half range and lower half range by key frame cutting；
Step S12：The original data that the lower half range of key frame is calculated as follow-up identification.
7. the fastlink visibility measuring method according to claim 1 based on video, it is characterised in that in step S3
In, image recognition includes perspective and anti-perspective, edge detection and Hough transformation.
8. the fastlink visibility measuring method according to claim 5 based on video, it is characterised in that described to be based on
The fastlink visibility measuring method of video further includes step S7, and step S7 is located at after step S6：
Step S7：Preset trusted area feature templates are corrected according to optimal trusted area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711314039.0A CN107945174A (en) | 2017-12-12 | 2017-12-12 | Fastlink visibility measuring method based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711314039.0A CN107945174A (en) | 2017-12-12 | 2017-12-12 | Fastlink visibility measuring method based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107945174A true CN107945174A (en) | 2018-04-20 |
Family
ID=61945625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711314039.0A Pending CN107945174A (en) | 2017-12-12 | 2017-12-12 | Fastlink visibility measuring method based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107945174A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826412A (en) * | 2019-10-10 | 2020-02-21 | 江苏理工学院 | Highway visibility detection system and method |
| CN111476761A (en) * | 2020-03-18 | 2020-07-31 | 河北科技大学 | Visibility measuring method and system based on system identification |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2050644A1 (en) * | 2007-10-18 | 2009-04-22 | Renault S.A.S. | Methods for measuring the visibility of an automobile driver and calculating speed instructions for the vehicle, and method for implementing same |
| CN105931220A (en) * | 2016-04-13 | 2016-09-07 | 南京邮电大学 | Dark channel experience and minimal image entropy based traffic smog visibility detection method |
-
2017
- 2017-12-12 CN CN201711314039.0A patent/CN107945174A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2050644A1 (en) * | 2007-10-18 | 2009-04-22 | Renault S.A.S. | Methods for measuring the visibility of an automobile driver and calculating speed instructions for the vehicle, and method for implementing same |
| CN105931220A (en) * | 2016-04-13 | 2016-09-07 | 南京邮电大学 | Dark channel experience and minimal image entropy based traffic smog visibility detection method |
Non-Patent Citations (1)
| Title |
|---|
| 王雷: "一种基于双曲线模型的车道线跟踪检测算法设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826412A (en) * | 2019-10-10 | 2020-02-21 | 江苏理工学院 | Highway visibility detection system and method |
| CN111476761A (en) * | 2020-03-18 | 2020-07-31 | 河北科技大学 | Visibility measuring method and system based on system identification |
| CN111476761B (en) * | 2020-03-18 | 2023-07-21 | 河北科技大学 | Visibility measurement method and system based on system identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11398097B2 (en) | Target detection method based on fusion of prior positioning of millimeter-wave radar and visual feature | |
| US10970566B2 (en) | Lane line detection method and apparatus | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN105931220B (en) | Traffic haze visibility detecting method based on dark channel prior Yu minimum image entropy | |
| US9576367B2 (en) | Object detection method and device | |
| Bertozzi et al. | Pedestrian detection in infrared images | |
| CN105678285B (en) | A kind of adaptive road birds-eye view transform method and road track detection method | |
| Hautière et al. | Real-time disparity contrast combination for onboard estimation of the visibility distance | |
| CN109299674B (en) | Tunnel illegal lane change detection method based on car lamp | |
| US20190139449A1 (en) | Method, computer readable storage medium and electronic equipment for analyzing driving behavior | |
| CN108388641B (en) | Traffic facility map generation method and system based on deep learning | |
| CN112215306B (en) | Target detection method based on fusion of monocular vision and millimeter wave radar | |
| CN108280450A (en) | A kind of express highway pavement detection method based on lane line | |
| US20130141520A1 (en) | Lane tracking system | |
| US20200160561A1 (en) | Vehicle-mounted camera pose estimation method, apparatus, and system, and electronic device | |
| CN104036246B (en) | Lane line positioning method based on multi-feature fusion and polymorphism mean value | |
| KR101240499B1 (en) | Device and method for real time lane recogniton and car detection | |
| CN103577809B (en) | A kind of method that traffic above-ground mark based on intelligent driving detects in real time | |
| Liu et al. | Development of a vision-based driver assistance system with lane departure warning and forward collision warning functions | |
| CN103196418A (en) | Measuring method of vehicle distance at curves | |
| US8559727B1 (en) | Temporal coherence in clear path detection | |
| US8331623B2 (en) | Method for tracking and processing image | |
| US10235579B2 (en) | Vanishing point correction apparatus and method | |
| US20120212615A1 (en) | Far-infrared pedestrian detection device | |
| Tsai et al. | Horizontal roadway curvature computation algorithm using vision technology |
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: 20180420 |
|
| RJ01 | Rejection of invention patent application after publication |