CN106980855A - Traffic sign quickly recognizes alignment system and method - Google Patents
Traffic sign quickly recognizes alignment system and method Download PDFInfo
- Publication number
- CN106980855A CN106980855A CN201710213257.9A CN201710213257A CN106980855A CN 106980855 A CN106980855 A CN 106980855A CN 201710213257 A CN201710213257 A CN 201710213257A CN 106980855 A CN106980855 A CN 106980855A
- Authority
- CN
- China
- Prior art keywords
- traffic sign
- video
- traffic
- module
- image
- 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
Classifications
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- 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
Abstract
Alignment system and method are quickly recognized the present invention relates to a kind of traffic sign, including：Video flowing acquisition module, video flowing acquisition module at least includes high-definition camera and locating module, for shooting roadside video and captured video being positioned；Traffic Sign Recognition module, Traffic Sign Recognition module is used to come out the Traffic Sign Recognition in roadside video captured by video flowing acquisition module and record location information；And, traffic sign map location module, the traffic sign that traffic sign map location module is used to be recognized Traffic Sign Recognition module navigates to map.Also include Data Post module, Data Post module is used to count the quantity and correspondence position of roadside traffic sign, go out figure intercepted including video flowing key frame and traffic sign position on the electronic map general view.The present invention can quick and precisely position road traffic sign on the way, and instrument is provided for traffic accident investigation.
Description
Technical field
Alignment system and method are quickly recognized the present invention relates to a kind of traffic sign, belongs to vehicle assistant drive technology neck
Domain.
Background technology
China's road traffic accident is taken place frequently, and road traffic accident fatal rate can be in any more.As shown by data, only 2014, I
Kuomintang-Communist is informed of a case road traffic accident 6,760,000, is related to the road traffic accident 196812 of casualties, is caused 58523 people dead
Die, 10.8 hundred million yuan of direct property loss.Wherein, the accident that bend, ramp, curved slope combination section occur occupies more than 20% ratio
Example, death toll accounts for 30%.The traffic sign facility of curved section is particularly important, and can point out driver's road conditions,
Effectively reduce accident frequency.
However, still suffering from the situation of part curved section road signs missing at present, and repeatedly cause serious friendship
Interpreter's event.The investigation of the species and quantity of traffic sign is an important tune in particularly serious traffic accident investigation along accident section
Look into content.In recent years, correlative study person has been fully recognized that importance of the road signs in traffic safety, and should
The identification and positioning of traffic sign are carried out with means such as image procossing, remote sensing image, global location, pattern-recognitions a series of
Analysis and research.
The A of Chinese patent application CN 102609702 disclose a kind of method for rapidly positioning of road fingerpost and are
System, the system includes acquiring unit, cutting unit, area acquisition unit and positioning unit.This method is to obtain road first
Image, then by the Road image segmentation of acquisition into upper and lower two parts image, and then using the blueness based on RGB color model
Detection model, the acquisition of effective candidate region is carried out to upper parts of images, finally carries out level to effective candidate region of acquisition
Long straight-line detection, and then position fingerpost.Traditional rectangular shape is substituted because the patent application is detected using linear feature
Feature detection, therefore, it is possible to greatly shorten the time for carrying out this process of positioning fingerpost, and robustness is greatly improved.
The patent application is widely used in Traffic Sign Recognition neck as the method for rapidly positioning and system of a kind of road fingerpost
In domain.But, the patent application is directed to single image and not video stream file, need to manually be operated when taking pictures, and can not
The species of traffic sign is recognized, it is traffic sign that can only identify it.In addition, application image Processing Algorithm positioning precision is not high,
It is difficult to meet actual demand.
The A of Chinese patent application CN 105718860 provide a kind of based on driving safety map and binocular Traffic Sign Recognition
Localization method and system, it to the vehicle in driving using alignment system in high-precision map by carrying out primary positioning；
Collection vehicle forward image, is detected and is recognized to the traffic sign in image simultaneously；And obtained in high-precision Map recognition
The coordinate of traffic sign, the spacing between measurement vehicle and mark, the coordinate of contrast traffic sign calculates the position of vehicle, real
Existing vehicle location.The patent application adds the collection of road signs, using road on the basis of conventional navigation data
Indicate that the positioning to vehicle carries out booster action, the marker coordinates and size identified by left and right lens camera enter driving
Distance between traffic sign is calculated, and is calculated according to the locus coordinate that oneself has traffic sign in high-precision map
The position of vehicle, so as to provide the coordinate setting of sub-meter grade, foundation can the topological network based on track.Before the patent application
It is the purpose for needing to know that the elements of a fix of traffic sign realize traffic sign positioning to confirm the coordinate of this car, not to carry.
The A of Chinese patent application CN 104361350 provide a kind of traffic mark identifying system, it is characterised in that：It is described
Identifying system be included in rear-viewing mirror in vehicle position high dynamic camera, the traffic mark information on collection road ahead road surface be installed
Recognize traffic marking, traffic lights, traffic sign from road environment image respectively afterwards and set up corresponding space time correlation mould
Type；Due to using above-mentioned structures and methods, the patent application binding time and spatial relationship, traffic mark recognition result is set up
Space time correlation criterion, a variety of traffic marks are recognized in same image, a variety of traffic mark recognition results are merged, obtained
Believable output result is taken, the influence caused by traffic mark recognizes that mistake is travelled to intelligent vehicle is reduced.The Traffic Sign Recognition
System is mainly used in building traffic sign space correlation information, the traveling for commanding intelligent vehicle.And traffic sign can only be recognized
Its seven frameworks, and specific species can not be recognized.
Three patent applications of the above are directed to Traffic Sign Recognition, the A of patent application CN 102609702 and patent application CN
105718860 A further relate to positioning.At present, the Traffic Sign Recognition based on camera is only applicable to single width still photo, and uncomfortable
For the Traffic Sign Recognition in dynamic video stream file；In addition, current road signs are typically only capable to identify traffic
The contour feature of mark, and can not fine-resolution traffic sign species；Finally, the positioning of traffic sign is inaccurate.Existing rank
Section also needs further research on the quick identification and being accurately positioned of traffic sign, to meet the relevant road of China's traffic accident
Traffic Sign Recognition and the demand of positioning.
The content of the invention
The purpose of the present invention is to overcome the deficiencies in the prior art quickly to recognize positioning system there is provided a kind of traffic sign
System and method, can rapidly and accurately identify the traffic sign of roadside, and be located to electronic map, with good
Good operability and precision.
The technical scheme provided according to the present invention, the traffic sign quickly recognizes alignment system, it is characterized in that, including：
Video flowing acquisition module, video flowing acquisition module at least includes high-definition camera and locating module, for shooting
Curb line video is simultaneously positioned to captured video；
Traffic Sign Recognition module, Traffic Sign Recognition module is used to regard roadside captured by video flowing acquisition module
Traffic Sign Recognition in frequency comes out and record location information；
And, traffic sign map location module, traffic sign map location module is used for Traffic Sign Recognition module
The traffic sign recognized is navigated on map.
Further, in addition to Data Post module, Data Post module be used to counting road section traffic volume mark quantity,
Export traffic sign location map.
Further, the video flowing acquisition module uses the electronics movement with high-definition camera and locating module to set
It is standby.
Further, the course of work of the Traffic Sign Recognition module includes traffic sign profile knowledge in moving camera
Not, traffic sign content recognition and the traffic sign to identification are classified.
Further, the process of traffic sign profile identification is in the moving camera：First according to existing traffic mark
Will sets up sample image set, and extracts the sample of traffic sign in sample image, sets up sample feature set, passes through machine
Study obtains the disaggregated model of traffic sign；Then video sequence image is decomposed from video flowing, scanning window image set is set up
Close, the feature of traffic sign is obtained from video image, and obtain the characteristic vector in image；Then by characteristic vector and classification
Model carries out similarity mode, and judgement draws testing result；Meanwhile, the traffic sign characteristic vector input classification mould having confirmed that
After type, this feature vector feedback to sample feature set, is proceeded to learn Optimum Classification model by disaggregated model；
Further, the course of work of the traffic sign map location module is：Clapped using diverse location in video flowing
The picture frame for the traffic sign identified taken the photograph, reconstructs the measurable threedimensional model of traffic sign in video, and calculate
Coordinate under the center of the three-dimensional traffic mark to camera coordinate system where each two field picture, with reference to above-mentioned shooting figure
As the location information of frame, you can obtain the location information of same traffic sign in each two field picture, based on least-squares algorithm, profit
The final location information of the traffic sign is determined with these location informations.
The quick recognition positioning method of traffic sign, it is characterized in that, comprise the following steps：
Step S1：Shoot the video of roadside and captured video is positioned；
Step S2：The step S1 video sequences obtained are resolved into single-frame images, and carry out storehouse, each stack figure is recorded
As corresponding location information；Take out the image of stack top, extract the characteristic vector in the two field picture, and with the sample in disaggregated model
Characteristic set is analyzed, and detects in the two field picture whether there is traffic sign, if nothing, is abandoned the two field picture, is taken again from stack top
Go out a two field picture replicate analysis；If so, the traffic sign to be carried out to new storehouse together with the two field picture, the stack is used for depositing figure
Picture, and continue to be analyzed from the new image of image stack top taking-up, until all frames containing the traffic sign are detected；I.e.
N frames can be obtained and carry the traffic indication map of the machine location information, while will identify that the traffic sign establishing criteria come is divided
Class, data are provided for follow-up data statistics；After the identification and classification of a traffic sign is completed, for depositing detection traffic
No. ID increase by 1 of stack of mark, reenters next testing process；
Step S3：, can be based on all in the stack for depositing same traffic sign after the identification and classification that complete traffic sign
N two field pictures, build the threedimensional model of the traffic sign, with reference to the location information of this n two field picture, traffic sign can be obtained
Location information；Now, the traffic sign should have n location information, using the least square method of foregoing description, obtain the traffic
The best orientation information of mark.
Further, with reference to electronic map and the traffic sign classification divided, you can output contains traffic sign distribution
Electronic map.
The advantage of the invention is that：The present invention can fast and accurately orient the traffic sign of roadside, and by its
On positioning to electronic map, traffic sign positioning distribution map can intuitively show the various marks of roadside, in road traffic thing
Therefore investigation in have good flexibility and operability.Integrated application image recognition of the present invention, feature detection, navigation are fixed
The technical methods such as position, multiview three-dimensional positioning, with good operability and precision, and can be particularly serious traffic accident road
The investigation of traffic sign facility provides effective tool.
Brief description of the drawings
Fig. 1 is the structured flowchart that traffic sign of the present invention quickly recognizes alignment system.
Fig. 2 is the operating diagram of the Traffic Sign Recognition module.
Fig. 3 is the operating diagram of the traffic sign map location module.
Fig. 4 is the schematic diagram of exportable traffic sign distribution map.
Fig. 5 is the workflow diagram that traffic sign of the present invention quickly recognizes alignment system.
Embodiment
With reference to specific accompanying drawing, the invention will be further described.
As shown in figure 1, traffic sign of the present invention quickly recognizes that alignment system includes video flowing acquisition module, traffic mark
Will identification module, traffic sign map location module and data post-processing module.
The video flowing acquisition module is based on electronic mobile device, and the APP used cooperatively is installed in electronic mobile device
Using, start the APP application, call the camera that electronic mobile device is carried at APP interfaces, the electronic mobile device be fixed on
On vehicle, you can shoot the video flowing of road on the way with car, while video is shot, carving copy when each frame picture is shot with video-corder is recorded
The location information of machine.Electronic mobile device can at least continue smooth shooting video 30 minutes, and video quality is not moved by electronics
The influence of the environmental factors such as dynamic equipment heating, shake, to ensure that video stream file is applied to the analyzing and processing in later stage.
The course of work of the Traffic Sign Recognition module includes the identification of traffic sign profile, traffic sign in moving camera
Content recognition and traffic sign to identification are classified.Because the video flowing of shooting is HD video, thus mobile video
In Traffic Sign Recognition come out after, can continue that the content in image on traffic sign is identified, the traffic to identifying
Mark is classified, and for the traffic sign of None- identified content, can be carried out according to the contour shape of the traffic sign identified
Rough sort.The classification foundation reference of road signs《Road signs and graticule part 2：Road signs (GB
5768.2-2009)》。
The Traffic Sign Recognition module is integrated with image processing algorithm, can recognize the characteristic target in moving camera, and
The traffic sign identified is based on《Road signs and graticule part 2：Road signs (GB5768.2-
2009)》Classified.The Traffic Sign Recognition module employs the moving object detection algorithm of feature based classification, original
Feature based classification moving object detection algorithm require camera fix, target to be detected movement, the present invention in due to known
The movement velocity and movement locus of camera, thus camera coordinates system can will be set up, be converted to the phase for setting up camera and traffic sign
To movement relation.Under the coordinate system, camera geo-stationary, and road and roadside feature relative motion, thus can be used and be based on
The moving object detection algorithm of tagsort.As shown in Fig. 2 the moving object detection of feature based classification is treated comprising two
Journey, i.e. learning process and decision process.The basic thought of learning process is to choose or construct a kind of target to paying close attention to type to retouch
Favourable characteristics of image is stated, by feature extraction algorithm, a set of marked image pattern is mapped to feature space and forms spy
Levy sample set；Recycle sample set as input, exercise supervision training to corresponding pattern recognition classifier device, finally gives
One detection grader for having trained.The basic thought of decision process is to list to be possible in present image comprising pass first
The region of type target is noted, the detection grader trained is reused, quantifies these regions and there is target, finally make
The output of grader is assessed with mode decision scheme, the detection to target is realized.Present in the moving object detection of feature based classification
Two core points be that characteristics of image and disaggregated model, the wherein construction of disaggregated model and the dimension of characteristic vector are closely bound up.
In the present invention, traffic sign belongs to the less characteristics of image of dimension, mainly includes color histogram, color moment, HOG, LBP etc.
Feature, thus the decision-making technique of distance metric can be used, i.e., calculate optimal using the inter- object distance of training objective sample characteristics
Linear decision threshold value, then the distance of decision-making characteristics of image and target sample average characteristics is treated by comparing, realize to mesh in scene
Target is detected.
Complete after Traffic Sign Recognition, the location information of traffic sign need to be determined.And the object in two dimensional image is that do not have
Standby location information, but in the present invention, when camera shoots video stream file, the positioning letter of the machine when have recorded every frame picture photographing
Breath.As shown in figure 3, in video flowing, from diverse location (position1, position2 ..., positionn) photograph it is same
One traffic sign, and identified via the Traffic Sign Recognition module of the present invention, meanwhile, this n two field picture all have recorded the machine
Location information.The three-dimensional rebuilding method based on multi views can be thus used, based on above-mentioned n two field pictures, is built in the image
The threedimensional model of traffic sign, and based on position1, position2 ..., positionn and the threedimensional model arrive
Position1, position2 ..., positionn distance the location information of the traffic sign is determined, using a most young waiter in a wineshop or an inn
Multiplication, determines the most accurate location information of the traffic sign from this n location information, and ranging formula is shown in formula 1.
In formula (1), PsignFor the location information of traffic sign, PkFor the corresponding location information of traffic sign in single-frame images.
After the identification and positioning that complete traffic sign, you can carry out the Data Analysis Services work of next step.Institute of the present invention
State traffic sign and quickly recognize that one of function of alignment system is to draw traffic sign distribution electronic map, realize original
The distributed intelligence of traffic sign is added on electronic map.As shown in figure 4, the base map of traffic sign distribution electronic map is certain high speed
The electronic map of highway, Traffic Sign Recognition function and the positioning of alignment system are quickly recognized with reference to traffic sign of the present invention
Function, it is " misty rain weather slow down " warning mark to identify the traffic sign, and place is located at expressway K1386+700 roads
Section.Traffic sign of the present invention quickly recognizes that alignment system can complete distribution and the display letter of all traffic signs in the section
Breath.
Before traffic sign of the present invention quickly recognizes the workflow of alignment system as shown in figure 5, starting working, need
Electronic mobile device is fixed on to the somewhere of vehicle, it is ensured that the camera of electronic mobile device is unobstructed, clear, the coherent shooting of energy
Roadside video, checks the continuation of the journey situation and internal memory situation of electronic mobile device, it is ensured that can shoot and store more than 30 minutes
HD video.After the completion of preparation, start electronic mobile device, open and be arranged on special in the electronic mobile device
APP, starts vehicle, opens up the video sequence file for shooting roadside.After the completion of video capture, video file is exported to work
Stand, the work station is integrated with image processing algorithm.Video sequence can be resolved into single-frame images first, and carry out storehouse, remembered
Record the corresponding the machine location information of each stack image.The image of stack top is taken out, the characteristic vector in the two field picture is extracted, and with dividing
Sample feature set in class model is analyzed, and detects in the two field picture whether there is traffic sign, if nothing, abandons the frame figure
Picture, takes out a two field picture replicate analysis from stack top again；If so, the traffic sign is carried out to new storehouse together with the two field picture,
The stack is used for depositing image, and continues to be analyzed from the new image of image stack top taking-up, until the institute containing the traffic sign
There is frame to be detected.N frames can be obtained and carry the traffic indication map of the machine location information, while will identify that the traffic sign come
Establishing criteria is classified, and data are provided for follow-up data statistics.After the identification and classification of a traffic sign is completed, use
To deposit No. ID increase by 1 of stack of detection traffic sign, next testing process is reentered.Complete the identification of traffic sign and divide
After class, it can build the threedimensional model of the traffic sign based on n two field pictures all in the stack for depositing same traffic sign, tie
The location information of this n two field picture is closed, the location information of traffic sign can be obtained.Now, the traffic sign should have n positioning
Information, using the least square method of foregoing description, obtains the best orientation information of the traffic sign.With reference to electronic map and divide
Good traffic sign classification, you can export the electronic map being distributed containing traffic sign.At the same time it can also be carried out to traffic sign
Statistics, analyses whether to meet related roads standard and specification.
Claims (8)
1. a kind of traffic sign quickly recognizes alignment system, it is characterized in that, including：
Video flowing acquisition module, video flowing acquisition module at least includes high-definition camera and locating module, for shooting road edge
Line video is simultaneously positioned to captured video；
Traffic Sign Recognition module, Traffic Sign Recognition module is used in roadside video captured by video flowing acquisition module
Traffic Sign Recognition come out and record location information；
And, traffic sign map location module, traffic sign map location module is used to be known Traffic Sign Recognition module
Other traffic sign is navigated on map.
2. traffic sign as claimed in claim 1 quickly recognizes alignment system, it is characterized in that：Also include Data Post mould
Block, Data Post module is used to count road section traffic volume mark quantity, export traffic sign location map.
3. traffic sign as claimed in claim 1 or 2 quickly recognizes alignment system, it is characterized in that：The video flowing gathers mould
Block uses the electronic mobile device with high-definition camera and locating module.
4. traffic sign as claimed in claim 1 or 2 quickly recognizes alignment system, it is characterized in that：The Traffic Sign Recognition
The course of work of module includes the identification of traffic sign profile, traffic sign content recognition and the friendship to identification in moving camera
Logical mark is classified.
5. traffic sign as claimed in claim 4 quickly recognizes alignment system, it is characterized in that：Traffic mark in the moving camera
Will profile identification process be：Sample image set is set up according to existing traffic sign first, and extracted in sample image
The sample of traffic sign, sets up sample feature set, and the disaggregated model of traffic sign is obtained by machine learning；Then from video
Video sequence image is decomposed in stream, scanning window image collection is set up, the feature of traffic sign is obtained from video image, and obtain
Characteristic vector into image；Characteristic vector and disaggregated model are then subjected to similarity mode, judgement draws testing result；Together
When, the traffic sign characteristic vector having confirmed that is inputted after disaggregated model, and this feature vector feedback is given sample special by disaggregated model
Collection is closed, and proceeds to learn Optimum Classification model.
6. traffic sign as claimed in claim 1 or 2 quickly recognizes alignment system, it is characterized in that：The traffic sign map
The course of work of locating module is：The picture frame of the traffic sign identified photographed using diverse location in video flowing,
Reconstruct the measurable threedimensional model of traffic sign in video, and calculate the center of the three-dimensional traffic mark to each frame figure
As the coordinate under the camera coordinate system of place, with reference to the location information of above-mentioned photographing image frame, you can obtain each two field picture
In same traffic sign location information, based on least-squares algorithm, determine that the traffic sign is final using these location informations
Location information.
7. a kind of quick recognition positioning method of traffic sign, it is characterized in that, comprise the following steps：
Step S1：Shoot the video of roadside and captured video is positioned；
Step S2：The step S1 video sequences obtained are resolved into single-frame images, and carry out storehouse, each stack image pair is recorded
The location information answered；Take out the image of stack top, extract the characteristic vector in the two field picture, and with the sample characteristics in disaggregated model
Set is analyzed, and is detected in the two field picture whether there is traffic sign, if nothing, is abandoned the two field picture, takes out one from stack top again
Two field picture replicate analysis；If so, the traffic sign to be carried out to new storehouse together with the two field picture, the stack is used for depositing image, and
Continue to be analyzed from the new image of image stack top taking-up, until all frames containing the traffic sign are detected；It can obtain
Obtain n frames and carry the traffic indication map of the machine location information, while will identify that the traffic sign establishing criteria come is classified, be
Follow-up data statistics provides data；After the identification and classification of a traffic sign is completed, for depositing detection traffic sign
The increase of stack ID 1, reenter next testing process；
Step S3：, can be based on n frames all in the stack for depositing same traffic sign after the identification and classification that complete traffic sign
Image, builds the threedimensional model of the traffic sign, with reference to the location information of this n two field picture, can obtain the positioning of traffic sign
Information；Now, the traffic sign should have n location information, using the least square method of foregoing description, obtain the traffic sign
Best orientation information.
8. the quick recognition positioning method of traffic sign as claimed in claim 7, it is characterized in that：With reference to electronic map and divide
Traffic sign classification, you can export containing traffic sign be distributed electronic map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710213257.9A CN106980855B (en) | 2017-04-01 | 2017-04-01 | Traffic sign rapid identification and positioning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710213257.9A CN106980855B (en) | 2017-04-01 | 2017-04-01 | Traffic sign rapid identification and positioning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106980855A true CN106980855A (en) | 2017-07-25 |
| CN106980855B CN106980855B (en) | 2020-04-17 |
Family
ID=59345077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710213257.9A Active CN106980855B (en) | 2017-04-01 | 2017-04-01 | Traffic sign rapid identification and positioning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106980855B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109029339A (en) * | 2018-05-09 | 2018-12-18 | 苏州天瞳威视电子科技有限公司 | A kind of the traffic sign distance measuring method and device of view-based access control model |
| CN109215487A (en) * | 2018-08-24 | 2019-01-15 | 宽凳（北京）科技有限公司 | A kind of high-precision cartography method based on deep learning |
| CN109829401A (en) * | 2019-01-21 | 2019-05-31 | 深圳市能信安科技股份有限公司 | Traffic sign recognition method and device based on double capture apparatus |
| CN110501018A (en) * | 2019-08-13 | 2019-11-26 | 广东星舆科技有限公司 | A kind of traffic mark board information collecting method for serving high-precision map producing |
| CN110889378A (en) * | 2019-11-28 | 2020-03-17 | 湖南率为控制科技有限公司 | Multi-view fusion traffic sign detection and identification method and system |
| CN112926575A (en) * | 2021-01-22 | 2021-06-08 | 北京嘀嘀无限科技发展有限公司 | Traffic accident recognition method, device, electronic device and medium |
| CN113255578A (en) * | 2021-06-18 | 2021-08-13 | 湖北亿咖通科技有限公司 | Traffic identification recognition method and device, electronic equipment and storage medium |
| CN115965926A (en) * | 2023-03-16 | 2023-04-14 | 四川京炜数字科技有限公司 | Vehicle-mounted road sign line inspection system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010041584A1 (en) * | 2008-10-10 | 2010-04-15 | Kabushiki Kaisha Toshiba | Imaging system and method |
| KR20130106106A (en) * | 2012-03-19 | 2013-09-27 | 현대모비스 주식회사 | Appratus and method for judgment 3 dimension |
| CN103345630A (en) * | 2013-06-14 | 2013-10-09 | 合肥工业大学 | Traffic sign positioning method based on spherical panoramic video |
| CN103743383A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Automatic extraction method for road information based on point cloud |
| CN103925927A (en) * | 2014-04-18 | 2014-07-16 | 中国科学院软件研究所 | Traffic sign positioning method based on vehicle-mounted video |
| CN103971126A (en) * | 2014-05-12 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for identifying traffic signs |
| CN103971087A (en) * | 2013-07-12 | 2014-08-06 | 湖南纽思曼导航定位科技有限公司 | Method and device for searching and recognizing traffic signs in real time |
| CN104463935A (en) * | 2014-11-11 | 2015-03-25 | 中国电子科技集团公司第二十九研究所 | Lane rebuilding method and system used for traffic accident restoring |
| CN104517317A (en) * | 2015-01-08 | 2015-04-15 | 东华大学 | Three-dimensional reconstruction method of vehicle-borne infrared images |
| US9146125B2 (en) * | 2012-06-05 | 2015-09-29 | Apple Inc. | Navigation application with adaptive display of graphical directional indicators |
| CN105702152A (en) * | 2016-04-28 | 2016-06-22 | 百度在线网络技术（北京）有限公司 | Map generation method and device |
| CN105718860A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Positioning method and system based on safe driving map and binocular recognition of traffic signs |
| CN106204800A (en) * | 2016-07-06 | 2016-12-07 | 福州瑞芯微电子股份有限公司 | Method, device and the drive recorder that automatic traffic landmark identification is reminded |
| CN106326858A (en) * | 2016-08-23 | 2017-01-11 | 北京航空航天大学 | Road traffic sign automatic identification and management system based on deep learning |
| CN106372577A (en) * | 2016-08-23 | 2017-02-01 | 北京航空航天大学 | Deep learning-based traffic sign automatic identifying and marking method |
-
2017
- 2017-04-01 CN CN201710213257.9A patent/CN106980855B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010041584A1 (en) * | 2008-10-10 | 2010-04-15 | Kabushiki Kaisha Toshiba | Imaging system and method |
| KR20130106106A (en) * | 2012-03-19 | 2013-09-27 | 현대모비스 주식회사 | Appratus and method for judgment 3 dimension |
| US9146125B2 (en) * | 2012-06-05 | 2015-09-29 | Apple Inc. | Navigation application with adaptive display of graphical directional indicators |
| CN103345630A (en) * | 2013-06-14 | 2013-10-09 | 合肥工业大学 | Traffic sign positioning method based on spherical panoramic video |
| CN103971087A (en) * | 2013-07-12 | 2014-08-06 | 湖南纽思曼导航定位科技有限公司 | Method and device for searching and recognizing traffic signs in real time |
| CN103743383A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Automatic extraction method for road information based on point cloud |
| CN103925927A (en) * | 2014-04-18 | 2014-07-16 | 中国科学院软件研究所 | Traffic sign positioning method based on vehicle-mounted video |
| CN103971126A (en) * | 2014-05-12 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for identifying traffic signs |
| CN104463935A (en) * | 2014-11-11 | 2015-03-25 | 中国电子科技集团公司第二十九研究所 | Lane rebuilding method and system used for traffic accident restoring |
| CN104517317A (en) * | 2015-01-08 | 2015-04-15 | 东华大学 | Three-dimensional reconstruction method of vehicle-borne infrared images |
| CN105718860A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Positioning method and system based on safe driving map and binocular recognition of traffic signs |
| CN105702152A (en) * | 2016-04-28 | 2016-06-22 | 百度在线网络技术（北京）有限公司 | Map generation method and device |
| CN106204800A (en) * | 2016-07-06 | 2016-12-07 | 福州瑞芯微电子股份有限公司 | Method, device and the drive recorder that automatic traffic landmark identification is reminded |
| CN106326858A (en) * | 2016-08-23 | 2017-01-11 | 北京航空航天大学 | Road traffic sign automatic identification and management system based on deep learning |
| CN106372577A (en) * | 2016-08-23 | 2017-02-01 | 北京航空航天大学 | Deep learning-based traffic sign automatic identifying and marking method |
Non-Patent Citations (4)
| Title |
|---|
| ANH VU ET AL: "Traffic sign detection, state estimation, and identification using onboard sensors", 《16TH INTERNATIONAL IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC 2013)》 * |
| YIPU ZHAO ET AL: "Computing object-based saliency in urban scenes using laser sensing", 《 2012 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION》 * |
| 肖学钢: "序列图像中交通标志定位检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈放: "道路交通标线检测识别与建图方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109029339A (en) * | 2018-05-09 | 2018-12-18 | 苏州天瞳威视电子科技有限公司 | A kind of the traffic sign distance measuring method and device of view-based access control model |
| CN109029339B (en) * | 2018-05-09 | 2023-10-13 | 苏州天瞳威视电子科技有限公司 | Traffic sign distance measurement method and device based on vision |
| CN109215487A (en) * | 2018-08-24 | 2019-01-15 | 宽凳（北京）科技有限公司 | A kind of high-precision cartography method based on deep learning |
| CN109829401A (en) * | 2019-01-21 | 2019-05-31 | 深圳市能信安科技股份有限公司 | Traffic sign recognition method and device based on double capture apparatus |
| CN110501018A (en) * | 2019-08-13 | 2019-11-26 | 广东星舆科技有限公司 | A kind of traffic mark board information collecting method for serving high-precision map producing |
| CN110501018B (en) * | 2019-08-13 | 2021-11-02 | 广东星舆科技有限公司 | Traffic sign information acquisition method for high-precision map production |
| CN110889378A (en) * | 2019-11-28 | 2020-03-17 | 湖南率为控制科技有限公司 | Multi-view fusion traffic sign detection and identification method and system |
| CN112926575A (en) * | 2021-01-22 | 2021-06-08 | 北京嘀嘀无限科技发展有限公司 | Traffic accident recognition method, device, electronic device and medium |
| CN113255578A (en) * | 2021-06-18 | 2021-08-13 | 湖北亿咖通科技有限公司 | Traffic identification recognition method and device, electronic equipment and storage medium |
| CN113255578B (en) * | 2021-06-18 | 2022-04-29 | 亿咖通(湖北)技术有限公司 | Traffic identification recognition method and device, electronic equipment and storage medium |
| CN115965926A (en) * | 2023-03-16 | 2023-04-14 | 四川京炜数字科技有限公司 | Vehicle-mounted road sign line inspection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106980855B (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106980855A (en) | Traffic sign quickly recognizes alignment system and method | |
| CN105260699B (en) | A kind of processing method and processing device of lane line data | |
| Toulminet et al. | Vehicle detection by means of stereo vision-based obstacles features extraction and monocular pattern analysis | |
| CN105160309B (en) | Three lanes detection method based on morphological image segmentation and region growing | |
| De Charette et al. | Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates | |
| WO2018153304A1 (en) | Map road mark and road quality collection apparatus and method based on adas system | |
| CN104239867B (en) | License plate locating method and system | |
| CN110148196A (en) | A kind of image processing method, device and relevant device | |
| CN110619279B (en) | Road traffic sign instance segmentation method based on tracking | |
| Šegvić et al. | A computer vision assisted geoinformation inventory for traffic infrastructure | |
| CN110689724B (en) | Automatic motor vehicle zebra crossing present pedestrian auditing method based on deep learning | |
| CN115717894B (en) | Vehicle high-precision positioning method based on GPS and common navigation map | |
| CN107491720A (en) | A kind of model recognizing method based on modified convolutional neural networks | |
| CN105404857A (en) | Infrared-based night intelligent vehicle front pedestrian detection method | |
| CN103324920A (en) | Method for automatically identifying vehicle type based on vehicle frontal image and template matching | |
| CN111881790A (en) | Automatic extraction method and device for road crosswalk in high-precision map making | |
| CN103593832A (en) | Method for image mosaic based on feature detection operator of second order difference of Gaussian | |
| CN106446785A (en) | Passable road detection method based on binocular vision | |
| CN108288047A (en) | A kind of pedestrian/vehicle checking method | |
| CN104299009A (en) | Plate number character recognition method based on multi-feature fusion | |
| CN110516633A (en) | A kind of method for detecting lane lines and system based on deep learning | |
| CN106919939B (en) | A kind of traffic signboard tracks and identifies method and system | |
| CN114170580A (en) | Highway-oriented abnormal event detection method | |
| JP2023104982A (en) | Accident analysis device | |
| CN113435336A (en) | Running intelligent timing system and method based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |