CN102915640A - Safety belt detecting method based on Hough transform - Google Patents
Safety belt detecting method based on Hough transform Download PDFInfo
- Publication number
- CN102915640A CN102915640A CN2012104286615A CN201210428661A CN102915640A CN 102915640 A CN102915640 A CN 102915640A CN 2012104286615 A CN2012104286615 A CN 2012104286615A CN 201210428661 A CN201210428661 A CN 201210428661A CN 102915640 A CN102915640 A CN 102915640A
- Authority
- CN
- China
- Prior art keywords
- safety belt
- securing band
- detection
- straight
- hough transform
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a safety belt detecting method based on Hough transform, relating to the field of intelligent transportation. In the safety belt detecting method based on the Hough transform, two parallel straight lines on the edge of a safety belt are detected through the Hough transform of cumulative probability, and whether a driver and passengers wear the safety belts is determined by a geometrical way of shoulder and waist diagonal crossing of the safety belts. The safety belt detecting method based on the Hough transform comprises the following steps: extracting the edge of the safety belt; and performing straight line detection based on the Hough transform. Compared with other detection method, the safety belt detecting method based on the Hough transform has the advantages as follows: the detection rate of not wearing the safety belt is improved; for a motor vehicle picture with nonuniform illumination, the detection rate of not wearing the safety belt is improved; a detection scheme based on the Hough transform is provided for safety belt detection in an intelligent transportation system; the real-time performance is high; and the intelligent transportation system is easier to install and easy to maintain.
Description
Technical field
The present invention relates to intelligent transportation field, relate in particular to a kind of securing band detection method based on the Hough conversion.
Background technology
At intelligent transportation field, the securing band detection method is seldom mentioned; But be do not fasten the safety belt closely bound up with driver and crew's life security, so intelligent transportation is in order to give peaceful, the harmonious larger public security environment of social creativity, just the securing band detection method of processing based on image is risen soon.
Securing band detects and has following problem:
1, extract the proper vector of securing band and use the SVM(support vector machine) sorter that trains is less to the detection applicability of all vehicle window securing band;
2, to the even vehicle window picture of uneven illumination, its edge extracting is too intensive, and the securing band edge is diluted by background edge.
Summary of the invention
Purpose of the present invention just is to overcome the shortcoming and defect that prior art exists, and a kind of securing band detection method based on the Hough conversion is provided.The securing band that the method has mainly solved front-seat driver and crew in the automotive vehicle picture detects, and also can accurately and effectively detect front-seat driver and crew's seat belt status in the situation that uneven illumination is spared.
The object of the present invention is achieved like this:
Utilize two parallel lines at the Hough transfer pair securing band edge of accumulated probability to carry out straight-line detection, and the geometric ways that the shoulder waist that uses of seat belts is inclined cross judge whether driver and crew are with belt;
This method comprises the securing band edge extracting and based on the straight-line detection of Hough conversion:
1. securing band edge extracting
A, obtain the front-seat driver and crew gray value data of region above the waist;
B, utilize different height threshold value to carry out the Canny(shrewdness to selected areas) rim detection;
The pixel number ratio of the edge pixel point number of c, bianry image and selected areas image reaches certain threshold value, thereby obtains the securing band edge data;
2. based on the straight-line detection of Hough conversion
D, utilize eight neighborhood search algorithms, less and trickle zone is also removed in search, affects to remove the background area that produces straight-line detection when the Hough conversion;
E, use accumulated probability Hough conversion to carry out straight-line detection to the securing band edge image;
The geometric ways that securing band shoulder waist is inclined cross in f, the use motor vehicle windows is carried out the securing band straight line to detected straight line in the vehicle window and is confirmed;
Meet all conditions if g detects straight line, be judged as and fastened the safety belt; Otherwise, be judged as and do not fasten the safety belt.
The present invention has following advantages and good effect:
1. relative other detection method has improved the verification and measurement ratio of not fastening the safety belt;
2. for the even motor vehicle picture of uneven illumination, also improved the verification and measurement ratio of not fastening the safety belt;
3. the detection scheme that provides based on the Hough conversion is provided the securing band for intelligent transportation system, and real-time is good, and system installs simpler, and is easy to safeguard.
Description of drawings
Fig. 1 is the block diagram of intelligent network camera;
Fig. 2 is the workflow diagram of this method;
Among the figure:
The A-intelligent network camera;
The 1-LENS optical lens;
2-CCD (Charge Coupled Device, charge-coupled image sensor) imageing sensor;
3-signals collecting converter;
4-HV signal driver;
5-FPGA (Field-Programmable Gate Array, field programmable gate array) programmable logic processor;
6-SDRAM (Synchronous Dynamic Random Access Memory, synchronous DRAM) storer;
7-H264 scrambler of recording a video;
8-ARM (Advanced RISC Machines) center processor;
9-DSP(Signal Processor, digital signal processing) image processor.
English to Chinese:
Hough conversion: utilize the point of image two-dimensional space and parameter polar coordinate space-line duality, the test problems in the image two-dimensional space is transformed into the parameter polar coordinate space.By in the parameter polar coordinate space, carrying out the cumulative statistics of simple polar coordinates point number, then seek the method detection of straight lines of totalizer peak value in the parameter polar coordinate space.
Embodiment
Describe in detail below in conjunction with drawings and Examples:
One, intelligent network camera A
1, overall
Such as Fig. 1, intelligent network camera A comprises LENS optical lens 1, ccd image sensor 2, signals collecting converter 3, HV signal driver 4, FPGA programmable logic processor 5, SDRAM storer 6, H264 video recording scrambler 7 and ARM center processor 8;
Be provided with DSP image processor 9;
Its annexation is:
1. LENS optical lens 1, ccd image sensor 2, signals collecting converter 3, FPGA programmable logic processor 5, SDRAM storer 6, DSP image processor 9 and ARM center processor are connected successively and are connected, and realize image acquisition, storage, analysis and processing;
2. FPGA programmable logic processor 5, HV signal driver 4 are connected with ccd image sensor successively and are connected, and realize the control to ccd image sensor 2;
3. FPGA programmable logic processor 5, H264 video recording scrambler 7 is connected with the ARM center processor and is connected successively, realizes video monitoring and processing.
2, functional part
1) LENS optical lens 1, ccd image sensor 2, signals collecting converter 3, HV signal driver 4, FPGA programmable logic processor 5, SDRAM storer 6, H264 video recording scrambler 7 and ARM center processor 8 are general-purpose device.
2) DSP image processor 9 is a kind of high performance image processing devices, and its dominant frequency is up to 800Mhz;
Can select the DSP image processor of the series such as TMS320DM64X, TMS320DM81X, it is embedded in the special software (back introduction) of this method;
DSP image processor 9 mainly by the analyzing and processing of picture, carries out securing band to the front-seat driver and crew of motor vehicle and detects, and ARM center processor 8 exported in the record of then will whether fastening the safety belt.
3, principle of work
FPGA programmable logic processor 5 is pressed the information of intelligent network camera A visual field on the speed acquisition of 25fps by LENS optical lens 1, ccd image sensor 2, signals collecting converter 3, leaves in the SDRAM storer 6 again; DSP image processor 9 obtains the real time picture sequence successively according to time sequencing from SDRAM storer 6, real-time analysis and detection moving vehicle.
FPGA programmable logic processor 5 is by 2 controls of 4 pairs of ccd image sensors of HV signal driver, time shutter, gain and the white balance of regulating ccd image sensor.
In the moving vehicle driving process, during candid photograph position that the system of entering sets in advance, automatically trigger and capture the vehicle pass-through picture; DSP image processor 9 carries out the securing band detection obtain to capture picture from SDRAM storer 6 after, and the record of then whether the front-seat driver and crew of motor vehicle being fastened the safety belt is passed to ARM center processor 8 and carried out respective handling;
The H264 scrambler 7 of recording a video can be encoded to real-time video the H264 video file, realizes the road monitoring function, passes to ARM center processor 8 again and carries out respective handling.
Two, based on the securing band detection method of Hough conversion
Such as Fig. 2, this method implementation procedure is as follows:
1. securing band edge extracting
A, obtain the front-seat driver and crew gray value data of region above the waist
A1) prerequisite in this step is that people's face positions in 9 pairs of vehicle windows of DSP image processor;
A2) according to above the waist and the general ratio of people's face driver and crew are positioned above the waist, and intercept out driver and crew region upper part of the body image and be for further processing;
B, utilize different height threshold values to carry out the Canny rim detection to selected areas
B1) ratio of selected height threshold value use 1:N in the Canny operator, then with [0,1/N] interval division M equal portions as the probable value i/ (M*N) of low threshold value, wherein 0＜=i＜=M-1 processes gray level image in the circulation substitution Canny edge detection operator;
B2) if the institute bianry image edge pixel point sum that obtains less than certain threshold value, then jump out circulation, and enter next step processing.
The pixel number ratio of the edge pixel point number of c, bianry image and selected areas image reaches certain threshold value, thereby obtains the securing band edge data;
Until the pixel number ratio of the contained edge pixel point number of bianry image and selected areas image reaches certain threshold value, namely obtain the obvious edge image that distributes;
(2) based on the straight-line detection of Hough conversion
D: utilize eight neighborhood search algorithms, less and trickle zone is also removed in search, affects to remove the background area that produces straight-line detection when the Hough conversion;
E: use accumulated probability Hough conversion to carry out straight-line detection to the securing band edge image;
The geometric ways that securing band shoulder waist is inclined cross in f, the use motor vehicle windows is carried out the securing band straight line to detected straight line in the vehicle window and is confirmed;
Because what securing band used generally is that the shoulder waist is inclined cross formula, so:
F1) judge in straight line that main driver's compartment domain search the goes out direction about 45 degree whether that the straight line that the copilot range searching goes out is the direction about 135 degree whether, in order to reduce the straight line number that searches out, carries out next step judgement;
F2) judge whether two parallel lines exist, whether its distance is within an interval range;
Whether the distance of f3) judging two straight line central points only has when three conditions all satisfy less than certain threshold value, just is defined as the securing band edge line, and namely defining driver and crew has been securing band; Otherwise be judged as be not;
Meet all conditions if g detects straight line, be judged as and fastened the safety belt; Otherwise, be judged as and do not fasten the safety belt;
H, flow process finish.
Claims (1)
1. securing band detection method based on the Hough conversion is characterized in that:
Utilize two parallel lines at the Hough transfer pair securing band edge of accumulated probability to carry out straight-line detection, and the geometric ways that the shoulder waist that uses of seat belts is inclined cross judge whether driver and crew are with belt;
Comprise the securing band edge extracting and based on the straight-line detection of Hough conversion:
1. securing band edge extracting
A, obtain the front-seat driver and crew gray value data of region above the waist;
B, utilize different height threshold values to carry out the Canny rim detection to selected areas;
The pixel number ratio of the edge pixel point number of c, bianry image and selected areas image reaches certain threshold value, thereby obtains the securing band edge data;
2. based on the straight-line detection of Hough conversion
D, utilize eight neighborhood search algorithms, less and trickle zone is also removed in search, affects to remove the background area that produces straight-line detection when the Hough conversion;
E, use accumulated probability Hough conversion to carry out straight-line detection to the securing band edge image;
The geometric ways that securing band shoulder waist is inclined cross in f, the use motor vehicle windows is carried out the securing band straight line to detected straight line in the vehicle window and is confirmed;
Meet all conditions if g detects straight line, be judged as and fastened the safety belt; Otherwise, be judged as and do not fasten the safety belt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210428661.5A CN102915640B (en) | 2012-10-30 | 2012-10-30 | Safety belt detecting method based on Hough transform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210428661.5A CN102915640B (en) | 2012-10-30 | 2012-10-30 | Safety belt detecting method based on Hough transform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102915640A true CN102915640A (en) | 2013-02-06 |
| CN102915640B CN102915640B (en) | 2015-06-17 |
Family
ID=47613986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210428661.5A Active CN102915640B (en) | 2012-10-30 | 2012-10-30 | Safety belt detecting method based on Hough transform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102915640B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103522982A (en) * | 2013-10-25 | 2014-01-22 | 公安部第三研究所 | Vehicle safety belt detection method and device based on image analysis |
| CN103986906A (en) * | 2014-05-08 | 2014-08-13 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN104077566A (en) * | 2014-06-19 | 2014-10-01 | 武汉烽火众智数字技术有限责任公司 | Intersection picture face detection method based on color differences |
| CN104417489A (en) * | 2013-08-29 | 2015-03-18 | 同观科技（深圳）有限公司 | Automobile safety belt detection method and automobile safety belt detection device |
| CN104700066A (en) * | 2013-12-11 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting whether driver wears safety belt or not |
| CN105373779A (en) * | 2015-11-10 | 2016-03-02 | 北京汉王智通科技有限公司 | Intelligent vehicle safety belt detection method and intelligent detection system |
| CN105550656A (en) * | 2015-12-23 | 2016-05-04 | 天津天地伟业数码科技有限公司 | Bayonet picture-based driver safety belt detection method |
| CN107330367A (en) * | 2017-05-27 | 2017-11-07 | 湖北天业云商网络科技有限公司 | A kind of Safe belt detection method and system positioned based on trunk |
| WO2018058957A1 (en) * | 2016-09-30 | 2018-04-05 | 广州大正新材料科技有限公司 | Intelligent vehicle-road cooperation traffic control system |
| CN107919019A (en) * | 2017-11-28 | 2018-04-17 | 武汉万集信息技术有限公司 | Peccancy detection method and system, safety belt based on RFID electronic label |
| CN111141208A (en) * | 2019-01-09 | 2020-05-12 | 银河水滴科技（北京）有限公司 | Parallel line detection method and device |
| CN111344750A (en) * | 2017-11-11 | 2020-06-26 | 邦迪克斯商用车***有限责任公司 | System and method for monitoring driver behavior using driver-oriented imaging devices for vehicle fleet management in a fleet of vehicles |
| CN111523583A (en) * | 2020-04-16 | 2020-08-11 | 国网河北省电力有限公司石家庄市栾城区供电分公司 | Method for automatically identifying and classifying equipment nameplate photos by using unmanned aerial vehicle |
| CN111582077A (en) * | 2020-04-23 | 2020-08-25 | 广州亚美智造科技有限公司 | Safety belt wearing detection method and device based on artificial intelligence software technology |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750544A (en) * | 2012-06-01 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Detection system and detection method of rule-breaking driving that safety belt is not fastened and based on plate number recognition |
-
2012
- 2012-10-30 CN CN201210428661.5A patent/CN102915640B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750544A (en) * | 2012-06-01 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Detection system and detection method of rule-breaking driving that safety belt is not fastened and based on plate number recognition |
Non-Patent Citations (3)
| Title |
|---|
| 曲延云 等: "基于支持向量机的机场检测算法", 《西安交通大学学报》, vol. 40, no. 6, 30 June 2006 (2006-06-30), pages 709 - 713 * |
| 柯剑光 等: "基于图像处理的盲道识别算法", 《计算机工程》, vol. 35, no. 1, 31 January 2009 (2009-01-31) * |
| 骆玉荣: "《安全带识别***的研究与实现》", 27 March 2009, article "第4章 特征提取的研究", pages: 29~36 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104417489A (en) * | 2013-08-29 | 2015-03-18 | 同观科技（深圳）有限公司 | Automobile safety belt detection method and automobile safety belt detection device |
| CN103522982A (en) * | 2013-10-25 | 2014-01-22 | 公安部第三研究所 | Vehicle safety belt detection method and device based on image analysis |
| CN104700066B (en) * | 2013-12-11 | 2018-02-16 | 杭州海康威视数字技术股份有限公司 | It is a kind of detect driver whether wear safety belt method and apparatus |
| CN104700066A (en) * | 2013-12-11 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting whether driver wears safety belt or not |
| CN103986906B (en) * | 2014-05-08 | 2017-05-10 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN103986906A (en) * | 2014-05-08 | 2014-08-13 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN104077566B (en) * | 2014-06-19 | 2017-07-21 | 武汉烽火众智数字技术有限责任公司 | Bayonet socket picture method for detecting human face based on color difference |
| CN104077566A (en) * | 2014-06-19 | 2014-10-01 | 武汉烽火众智数字技术有限责任公司 | Intersection picture face detection method based on color differences |
| CN105373779A (en) * | 2015-11-10 | 2016-03-02 | 北京汉王智通科技有限公司 | Intelligent vehicle safety belt detection method and intelligent detection system |
| CN105373779B (en) * | 2015-11-10 | 2018-09-28 | 北京数字智通科技有限公司 | A kind of vehicle safety belt intelligent detecting method and intelligent checking system |
| CN105550656A (en) * | 2015-12-23 | 2016-05-04 | 天津天地伟业数码科技有限公司 | Bayonet picture-based driver safety belt detection method |
| WO2018058957A1 (en) * | 2016-09-30 | 2018-04-05 | 广州大正新材料科技有限公司 | Intelligent vehicle-road cooperation traffic control system |
| CN107330367A (en) * | 2017-05-27 | 2017-11-07 | 湖北天业云商网络科技有限公司 | A kind of Safe belt detection method and system positioned based on trunk |
| CN111344750A (en) * | 2017-11-11 | 2020-06-26 | 邦迪克斯商用车***有限责任公司 | System and method for monitoring driver behavior using driver-oriented imaging devices for vehicle fleet management in a fleet of vehicles |
| CN107919019A (en) * | 2017-11-28 | 2018-04-17 | 武汉万集信息技术有限公司 | Peccancy detection method and system, safety belt based on RFID electronic label |
| CN111141208A (en) * | 2019-01-09 | 2020-05-12 | 银河水滴科技（北京）有限公司 | Parallel line detection method and device |
| CN111523583A (en) * | 2020-04-16 | 2020-08-11 | 国网河北省电力有限公司石家庄市栾城区供电分公司 | Method for automatically identifying and classifying equipment nameplate photos by using unmanned aerial vehicle |
| CN111523583B (en) * | 2020-04-16 | 2022-06-24 | 国网河北省电力有限公司石家庄市栾城区供电分公司 | Method for automatically identifying and classifying equipment nameplate photos by using unmanned aerial vehicle |
| CN111582077A (en) * | 2020-04-23 | 2020-08-25 | 广州亚美智造科技有限公司 | Safety belt wearing detection method and device based on artificial intelligence software technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102915640B (en) | 2015-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102915640B (en) | Safety belt detecting method based on Hough transform | |
| CN103942959B (en) | A kind of lane detection method and device | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| US9558412B2 (en) | Vehicle exterior environment recognition device | |
| KR101240469B1 (en) | Object recognition system, sysetm for recognizing obstacle for a vehicle and method thereof | |
| CN102231236B (en) | Method and device for counting vehicles | |
| CN107516423B (en) | Video-based vehicle driving direction detection method | |
| CN103310231A (en) | Auto logo locating and identifying method | |
| CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
| CN104835147A (en) | Method for detecting crowded people flow in real time based on three-dimensional depth map data | |
| CN103985182A (en) | Automatic public transport passenger flow counting method and system | |
| JP2012160165A (en) | Baseline band video monitoring system and method | |
| CN103870806B (en) | Safety belt detection method combining with steering wheel detection | |
| CN104239847B (en) | Driving warning method and electronic device for vehicle | |
| CN103021179B (en) | Based on the Safe belt detection method in real-time monitor video | |
| CN103049788B (en) | Based on space number for the treatment of object detection system and the method for computer vision | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN102610104B (en) | Onboard front vehicle detection method | |
| CN107729814A (en) | A kind of method and device for detecting lane line | |
| CN105139391A (en) | Edge detecting method for traffic image in fog-and-haze weather | |
| CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
| Premachandra et al. | Image based automatic road surface crack detection for achieving smooth driving on deformed roads | |
| CN111062319B (en) | Driver call detection method based on active infrared image | |
| CN106097725A (en) | A kind of vehicle classification flow rate testing methods extracted based on behavioral characteristics | |
| CN103854293A (en) | Vehicle tracking method and device based on feature point matching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181015 Address after: 510663 the 3 floor of block A, No. 101 Ting Yue Road, Guangzhou hi tech Industrial Development Zone, Guangdong. Patentee after: Guangzhou Fiberhome Zhongzhi Digital Technology Co. Ltd. Address before: 430074, No. 88, postal academy road, Hongshan District, Hubei, Wuhan Patentee before: Wuhan Fiberhome Digtal Technology Co., Ltd. |
|
| TR01 | Transfer of patent right |