CN106023623A - Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision - Google Patents
Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision Download PDFInfo
- Publication number
- CN106023623A CN106023623A CN201610609176.6A CN201610609176A CN106023623A CN 106023623 A CN106023623 A CN 106023623A CN 201610609176 A CN201610609176 A CN 201610609176A CN 106023623 A CN106023623 A CN 106023623A
- Authority
- CN
- China
- Prior art keywords
- pixel point
- image
- traffic
- parameter
- pixel
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/09623—Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle
-
- 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
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- 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
Abstract
The present invention provides a recognition and early warning method of a vehicle-borne traffic signal and symbol based on machine vision. The method comprises a step of combining electronic map information, starting vehicle-borne camera, and detecting the video information of an intersection signal lamp, a step of carrying out framing processing on video information captured by the camera, and obtaining an image set sequence, a step of carrying out preprocessing on the image, wherein the preprocessing comprises the preprocessing compression, the gray processing, and the binarization processing of the image, a step of determining an alternative detection area through rectangle scanning, counting the red, green, yellow and black pixels of the area, and judging whether a current area is a traffic lamp and the state of the traffic lamp according to the counting result, a step of carrying out circle and triangle detection at the same time, and matching and judging traffic sign information, and a step of displaying a recognition result in a voice broadcasting or screen displaying manner, and thus carrying out early warning of the driver. The method has the advantages of low cost, convenient implementation, a chromatopsia driver can be assisted to identify traffic signals and traffic signs, and the range of application is wide.
Description
Technical field
The present invention relates to intelligent transportation early warning technology field, a kind of vehicle mounted traffic signal based on machine vision and mark
The identification of will and method for early warning.
Background technology
Along with the development of transportation, achromatopsia is driven problem and is increasingly caused the concern of people.At home, achromatopsia cannot
Obtain the right of operating motor vehicles.This is the most convenient for achromate, thereby increases and it is possible to force achromate to use dishonest method
Obtain and drive qualification, be unfavorable for the stable of society.Create a kind of driving eye that can assist achromatopsia at present
Mirror, is by the achromatopsia side view application complementary color principle of constant brightness ratio is carried out conversion identification.In view of current vision skill
Art is the most immature, and is affected very big, so the drive routine effect to achromatopsia friend is not very big by light.On the other hand,
For normal driver, bring to a halt and the idling of vehicle travels the main cause being to consume gasoline during urban transportation travels.
Abroad, in order to make achromate carry out safe driving, signal lights carries out some and has arranged or change, added
Color or the shape of change signal lights, change with the color that this reminds achromate signal lights;Countries has traffic
The centralized control system of signal, it is achieved that with the interconnection of car-mounted device, the vehicle-mounted system that company of Audi of Germany develops based on this
System, directly can carry out " interactive " with local traffic light, thus the state of look-ahead signal lights changes.
But, existing technology is required for changing traffic signal equipment to a certain extent, has cost height, implements
The shortcomings such as difficulty is big, range of application is limited, it is difficult to meet the demand of current domestic vast achromatopsia colony.
Summary of the invention
Present invention aim at a kind of low cost being provided, implementing convenient, based on machine vision the vehicle-mounted friendship of applied range
The identification of messenger and mark and method for early warning, can assist achromatopsia driver to identify traffic signal and traffic mark board.
The technical solution realizing the object of the invention is: a kind of vehicle mounted traffic signal based on machine vision and the knowledge of mark
And method for early warning, do not comprise the following steps:
Step 1, combine electronic map information, open vehicle-mounted vidicon, detect the video information of Intersections in real time;
Step 2, the video information photographed by video camera carry out sub-frame processing, obtain an image collection sequence;
Step 3, image being carried out pretreatment, pretreatment includes the compression process of image, gray proces, binary conversion treatment;
Step 4, based on pretreated image, determine alternative detection region by rectangle frame scanning, to this region red,
Pixel green, yellow, black is added up, and judges that whether current region is the shape of traffic lights and traffic lights according to statistical result
State;It is simultaneously based on pretreated image and carries out circle and triangle detection, mate traffic mark board, and judge traffic mark
Will board information;
Step 5, by the recognition result of traffic lights in step 4 and traffic mark board, shown by voice broadcast or screen
Mode present, thus driver is carried out early warning.
Further, described in step 1, detect the video information of Intersections in real time, particularly as follows: examine every 3s~5s
Survey once, until crossing crossing completely.
Further, the video information photographed by video camera described in step 2 carries out sub-frame processing, particularly as follows: video is big
Little it is set as N minute, video information uses frame per second f be divided into image collection sequence that size is N*60*f,
Described frame per second f is set as 30FTPS or 60FTPS.
Further, described in step 3, image is carried out pretreatment, pretreatment include the compression process of image, gray proces,
Binary conversion treatment, specific as follows:
Compression processes: the image after video sub-frame processing is jpeg format, and compression has four steps, color mould when processing
Formula conversion and sampling, rgb color system will be converted to YcbCr color system;Dct transform, will light intensity data
Be converted to frequency data;Quantify, integer will be converted into by floating number by frequency data;Coding, is i.e. compiled by Huffman
Code completes compression;
Gray proces: the image of pretreatment is true color image, the color of each pixel in coloured image by R, G,
Tri-components of B determine, by obtaining the meansigma methods of tri-components of R, G, B of each pixel, then this are put down
Average is given to three components of this pixel to complete gray proces;
Binary conversion treatment: the gray scale of the point on image is set to 0 or 255, all gray scales are more than or equal to the pixel of threshold value
Gray value represents with 255, and otherwise gray value is 0.
Further, based on pretreated image described in step 4, determine alternative detection region by rectangle frame scanning,
The pixel red, green, yellow, black in this region is added up, judges whether current region is traffic lights according to statistical result
And the state of traffic lights;It is simultaneously based on pretreated image and carries out circle and triangle detection, mate traffic mark board,
And judge traffic mark board information, specific as follows:
A) based on pretreated image, it is (5~7) by length-width ratio: the rectangle frame of 2 is from left to right, carry out from top to bottom
Scanning, determines alternative detection region by rectangle frame scanning, is primarily based on the HSV color space of image and carries out color and sentence
Disconnected: when the H parameter of pixel, < in the range of 14, < in the range of 255, S parameter exists V parameter 50 < V 0 < H
43 < S < then regard as red pixel point in the range of 255;When the H parameter of pixel 105 < H < in the range of 135, V
Parameter 50 < V < in the range of 255, S parameter < in the range of 255, then regard as green pixel point 30 < S;Work as pixel
H parameter < in the range of 75, < in the range of 255, S parameter is in 46 < S < 255 scopes 50 < V for V parameter 45 < H
The most then regard as yellow pixel point;When the H parameter of pixel, < in the range of 255, V parameter is at 0 < V < 80 model 0 < H
Enclose interior, S parameter and < in the range of 255, then regard as black pixel point 0 < S;
Secondly, pixel quantity red, green, yellow, black in adding up alternative detection region, judge to work as proparea according to statistical result
Whether territory is the state of traffic lights and traffic lights:
When meeting following condition, then regard as red light:
1. black pixel point quantity is more than or equal to 10000;
2. red pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
3. red pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. red pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as green light:
1. black pixel point quantity is more than or equal to 10000;
2. green pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. green pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. green pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as amber light:
1. black pixel point quantity is more than or equal to 10000;
2. yellow pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. yellow pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
4. yellow pixel point and black pixel point quantitative proportion are more than 0.05;
When being unsatisfactory for any of the above condition, it is determined that current region is not traffic lights;
B) simultaneously, carry out circular and triangle detection and carry out the detection coupling of traffic mark board, sentencing according to matching result
Disconnected traffic mark board information, if matching factor is more than 0.8, assert that the match is successful.
Compared with prior art, its remarkable advantage is the present invention: (1) is applied widely: either for everyday driver
Or blind driver, can drive, detection traffic lights and traffic signs the most in real time, it is achieved voice reminder,
Safe early warning, it is ensured that the safe driving of driver;(2) present system is one and assists in identifying system, it is not necessary to advise greatly
Mould ground changes existing traffic signal lamp apparatus;(3) reliability is high, safety is good: image recognition technology is the most very
Ripe, so utilizing image recognition technology, there is higher reliability and safety.
Accompanying drawing explanation
Fig. 1 is present invention vehicle mounted traffic based on machine vision signal and the identification of mark and the flow chart of method for early warning.
Fig. 2 is the workflow diagram of picture recognition module in the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings and the present invention is described in further detail by specific embodiment.
As it is shown in figure 1, the identification of present invention vehicle mounted traffic based on machine vision signal and mark and method for early warning, in fact
Now comprise the following steps:
Step 1, combine electronic map information, open vehicle-mounted vidicon, detect the video information of Intersections in real time,
Particularly as follows: (3S-5S) detects once until crossing crossing completely at regular intervals, utilize vehicle-mounted camera collection
The video information of Intersections.
Step 2, the video information photographed by video camera carry out sub-frame processing, obtain an image collection sequence, specifically
For: video size is set as N minute, and it is the image of N*60*f that video information uses frame per second f be divided into a size
Sequence of sets, described frame per second f is set as 30FTPS or 60FTPS.
Step 3, image being carried out pretreatment, pretreatment includes the compression process of image, gray proces, binary conversion treatment,
Specific as follows:
Compression processes: the image after video sub-frame processing is jpeg format, and compression mainly has four steps, face when processing
Color patten transformation and sampling, rgb color system will be converted to YcbCr color system;Dct transform, will light intensity
Data are converted to frequency data;Quantify, integer will be converted into by floating number by frequency data;Coding, i.e. passes through Huffman
Encode compression;
Gray proces: the image of pretreatment is true color image, the color of each pixel in coloured image have R, G,
Tri-components of B determine, and each component has 255 intermediate values desirable, and such a pixel can have more than 1,600 ten thousand
(255*255*255) excursion of color, by obtaining the average of tri-components of R, G, B of each pixel
Value, is then given to three components of this pixel to complete gray proces, the picture of such as image point by this meansigma methods
Element value is (R:232, G:142, B:166), becomes (R:180, G:180, B:180) after gray proces;
Binary conversion treatment: the binary conversion treatment of image is exactly that the gray scale of the point on image is set to 0 or 255, namely will
Whole image presents obvious black and white effect.All gray scales are judged as belonging to individually defined thing more than or equal to the pixel of threshold value
Body, its gray value represents with 255, and otherwise these pixels are excluded beyond object area, and gray value is 0, represents
The gray value of background or the object area of exception, such as image point is 180, it is assumed that threshold value is 142, then by this point
Gray value is set to 255.
Step 4, based on pretreated image, determine alternative detection region by rectangle frame scanning, to this region red,
Pixel green, yellow, black is added up, and judges that whether current region is the shape of traffic lights and traffic lights according to statistical result
State;It is simultaneously based on pretreated image and carries out circle and triangle detection, mate traffic mark board, and judge traffic mark
Will board information, specific as follows:
A) based on pretreated image, it is (5~7) by length-width ratio: the rectangle frame of 2 is from left to right, carry out from top to bottom
Scanning, determines alternative detection region by rectangle frame scanning, is primarily based on the HSV color space of image and carries out color and sentence
Disconnected: when the H parameter of pixel, < in the range of 14, < in the range of 255, S parameter exists V parameter 50 < V 0 < H
43 < S < then regard as red pixel point in the range of 255;When the H parameter of pixel 105 < H < in the range of 135, V
Parameter 50 < V < in the range of 255, S parameter < in the range of 255, then regard as green pixel point 30 < S;Work as pixel
H parameter < in the range of 75, < in the range of 255, S parameter is in 46 < S < 255 scopes 50 < V for V parameter 45 < H
The most then regard as yellow pixel point;When the H parameter of pixel, < in the range of 255, V parameter is at 0 < V < 80 model 0 < H
Enclose interior, S parameter and < in the range of 255, then regard as black pixel point 0 < S;
Secondly, pixel quantity red, green, yellow, black in adding up alternative detection region, judge to work as proparea according to statistical result
Whether territory is the state of traffic lights and traffic lights:
When meeting following condition, then regard as red light:
1. black pixel point quantity is more than or equal to 10000;
2. red pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
3. red pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. red pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as green light:
1. black pixel point quantity is more than or equal to 10000;
2. green pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. green pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. green pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as amber light:
1. black pixel point quantity is more than or equal to 10000;
2. yellow pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. yellow pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
4. yellow pixel point and black pixel point quantitative proportion are more than 0.05;
When being unsatisfactory for any of the above condition, it is determined that current region is not traffic lights;
B) simultaneously, carry out circular and triangle detection and carry out the detection coupling of traffic mark board, sentencing according to matching result
Disconnected traffic mark board information, if matching factor is more than 0.8, assert that the match is successful.
Step 5, by the recognition result of traffic lights in step 4 and traffic mark board, shown by voice broadcast or screen
Mode present, thus driver is carried out early warning.
Although the present invention is disclosed above with preferred embodiment, so it is not limited to the present invention.Technology belonging to the present invention
Field has usually intellectual, without departing from the spirit and scope of the present invention, when being used for a variety of modifications and variations.
Therefore, protection scope of the present invention is when being as the criterion depending on those as defined in claim.
Claims (5)
1. the identification of a vehicle mounted traffic signal based on machine vision and mark and method for early warning, it is characterised in that bag
Include following steps:
Step 1, combine electronic map information, open vehicle-mounted vidicon, detect the video information of Intersections in real time;
Step 2, the video information photographed by video camera carry out sub-frame processing, obtain an image collection sequence;
Step 3, image being carried out pretreatment, pretreatment includes the compression process of image, gray proces, binary conversion treatment;
Step 4, based on pretreated image, determine alternative detection region by rectangle frame scanning, to this region red,
Pixel green, yellow, black is added up, and judges that whether current region is the shape of traffic lights and traffic lights according to statistical result
State;It is simultaneously based on pretreated image and carries out circle and triangle detection, mate traffic mark board, and judge traffic mark
Will board information;
Step 5, by the recognition result of traffic lights in step 4 and traffic mark board, shown by voice broadcast or screen
Mode present, thus driver is carried out early warning.
The identification of vehicle mounted traffic signal based on machine vision the most according to claim 1 and mark and method for early warning,
It is characterized in that, described in step 1, detect the video information of Intersections in real time, particularly as follows: detect every 3s~5s
Once, until crossing crossing completely.
The identification of vehicle mounted traffic signal based on machine vision the most according to claim 1 and mark and method for early warning,
It is characterized in that, the video information photographed by video camera described in step 2 carries out sub-frame processing, particularly as follows: video size
It is set as N minute, video information uses frame per second f be divided into image collection sequence that size is N*60*f, institute
State frame per second f and be set as 30FTPS or 60FTPS.
The identification of vehicle mounted traffic signal based on machine vision the most according to claim 1 and mark and method for early warning,
It is characterized in that, described in step 3, image is carried out pretreatment, pretreatment include the compression process of image, gray proces,
Binary conversion treatment, specific as follows:
Compression processes: the image after video sub-frame processing is jpeg format, and compression has four steps, color mould when processing
Formula conversion and sampling, rgb color system will be converted to YcbCr color system;Dct transform, will light intensity data
Be converted to frequency data;Quantify, integer will be converted into by floating number by frequency data;Coding, is i.e. compiled by Huffman
Code completes compression;
Gray proces: the image of pretreatment is true color image, the color of each pixel in coloured image by R, G,
Tri-components of B determine, by obtaining the meansigma methods of tri-components of R, G, B of each pixel, then this are put down
Average is given to three components of this pixel to complete gray proces;
Binary conversion treatment: the gray scale of the point on image is set to 0 or 255, all gray scales are more than or equal to the pixel of threshold value
Gray value represents with 255, and otherwise gray value is 0.
The identification of vehicle mounted traffic signal based on machine vision the most according to claim 1 and mark and method for early warning,
It is characterized in that, based on pretreated image described in step 4, determine alternative detection region by rectangle frame scanning, right
The pixel red, green, yellow, black in this region is added up, according to statistical result judge current region be whether traffic lights with
And the state of traffic lights;It is simultaneously based on pretreated image and carries out circle and triangle detection, mate traffic mark board,
And judge traffic mark board information, specific as follows:
A) based on pretreated image, it is (5~7) by length-width ratio: the rectangle frame of 2 is from left to right, carry out from top to bottom
Scanning, determines alternative detection region by rectangle frame scanning, is primarily based on the HSV color space of image and carries out color and sentence
Disconnected: when the H parameter of pixel, < in the range of 14, < in the range of 255, S parameter exists V parameter 50 < V 0 < H
43 < S < then regard as red pixel point in the range of 255;When the H parameter of pixel 105 < H < in the range of 135, V
Parameter 50 < V < in the range of 255, S parameter < in the range of 255, then regard as green pixel point 30 < S;Work as pixel
H parameter < in the range of 75, < in the range of 255, S parameter is in 46 < S < 255 scopes 50 < V for V parameter 45 < H
The most then regard as yellow pixel point;When the H parameter of pixel, < in the range of 255, V parameter is at 0 < V < 80 model 0 < H
Enclose interior, S parameter and < in the range of 255, then regard as black pixel point 0 < S;
Secondly, pixel quantity red, green, yellow, black in adding up alternative detection region, judge to work as proparea according to statistical result
Whether territory is the state of traffic lights and traffic lights:
When meeting following condition, then regard as red light:
1. black pixel point quantity is more than or equal to 10000;
2. red pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
3. red pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. red pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as green light:
1. black pixel point quantity is more than or equal to 10000;
2. green pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. green pixel point quantity is more than yellow pixel point quantity, and the two quantity difference is more than 1500;
4. green pixel point and black pixel point quantitative proportion are more than 0.05;
When meeting following condition, then regard as amber light:
1. black pixel point quantity is more than or equal to 10000;
2. yellow pixel point quantity is more than red pixel point quantity, and the two quantity difference is more than 1500;
3. yellow pixel point quantity is more than green pixel point quantity, and the two quantity difference is more than 1500;
4. yellow pixel point and black pixel point quantitative proportion are more than 0.05;
When being unsatisfactory for any of the above condition, it is determined that current region is not traffic lights;
B) simultaneously, carry out circular and triangle detection and carry out the detection coupling of traffic mark board, sentencing according to matching result
Disconnected traffic mark board information, if matching factor is more than 0.8, assert that the match is successful.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610609176.6A CN106023623A (en) | 2016-07-28 | 2016-07-28 | Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610609176.6A CN106023623A (en) | 2016-07-28 | 2016-07-28 | Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106023623A true CN106023623A (en) | 2016-10-12 |
Family
ID=57114832
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610609176.6A Pending CN106023623A (en) | 2016-07-28 | 2016-07-28 | Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106023623A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106781521A (en) * | 2016-12-30 | 2017-05-31 | 东软集团股份有限公司 | The recognition methods of traffic lights and device |
CN106803064A (en) * | 2016-12-26 | 2017-06-06 | 广州大学 | A kind of traffic lights method for quickly identifying |
CN107025796A (en) * | 2017-04-28 | 2017-08-08 | 北京理工大学珠海学院 | Automobile assistant driving vision early warning system and its method for early warning |
CN107506760A (en) * | 2017-08-04 | 2017-12-22 | 西南大学 | Traffic signals detection method and system based on GPS location and visual pattern processing |
CN107978165A (en) * | 2017-12-12 | 2018-05-01 | 南京理工大学 | Intersection identifier marking and signal lamp Intellisense method based on computer vision |
CN108305475A (en) * | 2017-03-06 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of traffic lights recognition methods and device |
CN108764216A (en) * | 2018-07-11 | 2018-11-06 | 天津天瞳威势电子科技有限公司 | A kind of traffic lights recognition methods of view-based access control model and device |
CN109118477A (en) * | 2018-07-20 | 2019-01-01 | 长安大学 | It is a kind of open air sign board depending on recognizing reasonable evaluation method |
CN109636777A (en) * | 2018-11-20 | 2019-04-16 | 广州方纬智慧大脑研究开发有限公司 | A kind of fault detection method of traffic lights, system and storage medium |
CN109782364A (en) * | 2018-12-26 | 2019-05-21 | 中设设计集团股份有限公司 | Traffic mark board based on machine vision lacks detection method |
CN110335486A (en) * | 2019-07-08 | 2019-10-15 | 盐城工学院 | A kind of novel colour blindness DAS (Driver Assistant System) |
CN110660254A (en) * | 2018-06-29 | 2020-01-07 | 北京市商汤科技开发有限公司 | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment |
CN111045889A (en) * | 2019-11-30 | 2020-04-21 | 北京浪潮数据技术有限公司 | Closed network equipment state monitoring system, method and device and readable storage medium |
CN112053578A (en) * | 2020-09-15 | 2020-12-08 | 福建振杭机器人装备制造有限责任公司 | Traffic light early warning method based on machine vision technology and detection device thereof |
WO2022037693A1 (en) * | 2020-08-20 | 2022-02-24 | 华为技术有限公司 | Traffic signal identification method and apparatus |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2026313A1 (en) * | 2007-08-17 | 2009-02-18 | MAGNETI MARELLI SISTEMI ELETTRONICI S.p.A. | A method and a system for the recognition of traffic signs with supplementary panels |
CN101395645A (en) * | 2006-03-06 | 2009-03-25 | 丰田自动车株式会社 | Image processing system and method |
CN101681557A (en) * | 2007-04-27 | 2010-03-24 | 爱信艾达株式会社 | Driving support system |
CN102176287A (en) * | 2011-02-28 | 2011-09-07 | 无锡中星微电子有限公司 | Traffic signal lamp identifying system and method |
US20130033601A1 (en) * | 2011-08-02 | 2013-02-07 | Yongsung Kim | Terminal and method for outputting signal information of a signal light in the terminal |
CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
CN103345766A (en) * | 2013-06-21 | 2013-10-09 | 东软集团股份有限公司 | Method and device for identifying signal light |
CN103854503A (en) * | 2012-12-06 | 2014-06-11 | 通用汽车环球科技运作有限责任公司 | A traffic light detection system |
US20150227801A1 (en) * | 2014-02-12 | 2015-08-13 | Robert Bosch Gmbh | Method and device for determining a distance of a vehicle from a traffic-regulating object |
CN105144260A (en) * | 2012-11-20 | 2015-12-09 | 罗伯特·博世有限公司 | Method and device for detecting variable-message signs |
CN105453153A (en) * | 2013-08-20 | 2016-03-30 | 哈曼国际工业有限公司 | Traffic light detection |
CN105809138A (en) * | 2016-03-15 | 2016-07-27 | 武汉大学 | Road warning mark detection and recognition method based on block recognition |
CN106133803A (en) * | 2014-03-31 | 2016-11-16 | 株式会社电装 | Vehicle display control unit |
-
2016
- 2016-07-28 CN CN201610609176.6A patent/CN106023623A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101395645A (en) * | 2006-03-06 | 2009-03-25 | 丰田自动车株式会社 | Image processing system and method |
CN101681557A (en) * | 2007-04-27 | 2010-03-24 | 爱信艾达株式会社 | Driving support system |
EP2026313A1 (en) * | 2007-08-17 | 2009-02-18 | MAGNETI MARELLI SISTEMI ELETTRONICI S.p.A. | A method and a system for the recognition of traffic signs with supplementary panels |
CN102176287A (en) * | 2011-02-28 | 2011-09-07 | 无锡中星微电子有限公司 | Traffic signal lamp identifying system and method |
US20130033601A1 (en) * | 2011-08-02 | 2013-02-07 | Yongsung Kim | Terminal and method for outputting signal information of a signal light in the terminal |
CN105144260A (en) * | 2012-11-20 | 2015-12-09 | 罗伯特·博世有限公司 | Method and device for detecting variable-message signs |
CN103854503A (en) * | 2012-12-06 | 2014-06-11 | 通用汽车环球科技运作有限责任公司 | A traffic light detection system |
CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
CN103345766A (en) * | 2013-06-21 | 2013-10-09 | 东软集团股份有限公司 | Method and device for identifying signal light |
CN105453153A (en) * | 2013-08-20 | 2016-03-30 | 哈曼国际工业有限公司 | Traffic light detection |
US20150227801A1 (en) * | 2014-02-12 | 2015-08-13 | Robert Bosch Gmbh | Method and device for determining a distance of a vehicle from a traffic-regulating object |
CN106133803A (en) * | 2014-03-31 | 2016-11-16 | 株式会社电装 | Vehicle display control unit |
CN105809138A (en) * | 2016-03-15 | 2016-07-27 | 武汉大学 | Road warning mark detection and recognition method based on block recognition |
Non-Patent Citations (1)
Title |
---|
EMMANOUIL KOUKOUMIDIS,ETC,: "Leveraging Smartphone Cameras for Collaborative Road Advisories", 《IEEE TRANSACTIONS ON MOBILE COMPUTING》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106803064B (en) * | 2016-12-26 | 2020-05-19 | 广州大学 | Traffic light rapid identification method |
CN106803064A (en) * | 2016-12-26 | 2017-06-06 | 广州大学 | A kind of traffic lights method for quickly identifying |
CN106781521A (en) * | 2016-12-30 | 2017-05-31 | 东软集团股份有限公司 | The recognition methods of traffic lights and device |
CN108305475A (en) * | 2017-03-06 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of traffic lights recognition methods and device |
CN107025796A (en) * | 2017-04-28 | 2017-08-08 | 北京理工大学珠海学院 | Automobile assistant driving vision early warning system and its method for early warning |
CN107506760A (en) * | 2017-08-04 | 2017-12-22 | 西南大学 | Traffic signals detection method and system based on GPS location and visual pattern processing |
CN107506760B (en) * | 2017-08-04 | 2020-06-05 | 西南大学 | Traffic signal detection method and system based on GPS positioning and visual image processing |
CN107978165A (en) * | 2017-12-12 | 2018-05-01 | 南京理工大学 | Intersection identifier marking and signal lamp Intellisense method based on computer vision |
KR20200128145A (en) | 2018-06-29 | 2020-11-11 | 베이징 센스타임 테크놀로지 디벨롭먼트 컴퍼니 리미티드 | Methods and devices, vehicles, and electronic devices for traffic light detection and intelligent driving |
CN110660254A (en) * | 2018-06-29 | 2020-01-07 | 北京市商汤科技开发有限公司 | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment |
CN110660254B (en) * | 2018-06-29 | 2022-04-08 | 北京市商汤科技开发有限公司 | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment |
CN108764216A (en) * | 2018-07-11 | 2018-11-06 | 天津天瞳威势电子科技有限公司 | A kind of traffic lights recognition methods of view-based access control model and device |
CN109118477A (en) * | 2018-07-20 | 2019-01-01 | 长安大学 | It is a kind of open air sign board depending on recognizing reasonable evaluation method |
CN109118477B (en) * | 2018-07-20 | 2022-04-19 | 长安大学 | Outdoor signboard visual recognition rationality evaluation method |
CN109636777A (en) * | 2018-11-20 | 2019-04-16 | 广州方纬智慧大脑研究开发有限公司 | A kind of fault detection method of traffic lights, system and storage medium |
CN109782364A (en) * | 2018-12-26 | 2019-05-21 | 中设设计集团股份有限公司 | Traffic mark board based on machine vision lacks detection method |
CN110335486A (en) * | 2019-07-08 | 2019-10-15 | 盐城工学院 | A kind of novel colour blindness DAS (Driver Assistant System) |
CN111045889A (en) * | 2019-11-30 | 2020-04-21 | 北京浪潮数据技术有限公司 | Closed network equipment state monitoring system, method and device and readable storage medium |
WO2022037693A1 (en) * | 2020-08-20 | 2022-02-24 | 华为技术有限公司 | Traffic signal identification method and apparatus |
CN112053578A (en) * | 2020-09-15 | 2020-12-08 | 福建振杭机器人装备制造有限责任公司 | Traffic light early warning method based on machine vision technology and detection device thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106023623A (en) | Recognition and early warning method of vehicle-borne traffic signal and symbol based on machine vision | |
Omachi et al. | Detection of traffic light using structural information | |
CN102298693B (en) | Expressway bend detection method based on computer vision | |
CN102496282B (en) | Traffic intersection signal light state identification method based on RGB color transformation | |
CN109299674B (en) | Tunnel illegal lane change detection method based on car lamp | |
CN103034843B (en) | Method for detecting vehicle at night based on monocular vision | |
CN103345766A (en) | Method and device for identifying signal light | |
US10824885B2 (en) | Method and apparatus for detecting braking behavior of front vehicle of autonomous vehicle | |
CN109460715A (en) | A kind of traffic lights automatic identification implementation method based on machine learning | |
JP4577153B2 (en) | Environment recognition device | |
CN109858459A (en) | System and method based on police vehicle-mounted video element information realization intelligently parsing processing | |
CN103020613A (en) | Method and device for identifying signal lamps on basis of videos | |
Sathiya et al. | Real time recognition of traffic light and their signal count-down timings | |
CN102364560B (en) | Traffic sign convenient for electronic identification and method for identifying traffic sign | |
Wen et al. | A rear-vehicle detection system for static images based on monocular vision | |
CN113053152A (en) | Vehicle-mounted traffic sign real-time display method and system | |
CN107506777A (en) | A kind of real-time more licence plate recognition methods and device based on Wavelet transformation and SVMs | |
Liu et al. | Real-time speed limit sign detection and recognition from image sequences | |
CN103680148B (en) | A kind of taxi recognition methods | |
Aldoski et al. | Impact of Traffic Sign Diversity on Autonomous Vehicles: A Literature Review | |
Sari et al. | Traffic sign detection and recognition system for autonomous RC cars | |
Panda et al. | Application of Image Processing In Road Traffic Control | |
Iftikhar et al. | Traffic Light Detection: A cost effective approach | |
Yamamoto et al. | Speed traffic sign recognition algorithm for real-time driving assistant system | |
CN115601717B (en) | Deep learning-based traffic offence behavior classification detection method and SoC chip |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |