CN109801498A - Licence plate recognition methods a kind of while using a variety of triggering modes - Google Patents
Licence plate recognition methods a kind of while using a variety of triggering modes Download PDFInfo
- Publication number
- CN109801498A CN109801498A CN201711134851.5A CN201711134851A CN109801498A CN 109801498 A CN109801498 A CN 109801498A CN 201711134851 A CN201711134851 A CN 201711134851A CN 109801498 A CN109801498 A CN 109801498A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- plate recognition
- triggering
- license plate
- recognition result
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The present invention relates to field of license plate recognition, especially a kind of simultaneously using the licence plate recognition method of a variety of triggering modes, the multiframe recognition result for first passing through video forms track of vehicle, determines to be same vehicle according to the track of vehicle of formation；Then judge whether vehicle passes through corresponding triggering mode and triggered, result of the vehicle output containing track of vehicle triggered.After adopting the above method, the present invention can export license plate recognition result using a variety of trigger timings simultaneously, and in the case where a kind of mode can not trigger identification, other kind of mode can also trigger identification.Thus when vehicle encounters fraction incident in the process of moving causes license plate that can not identify, identification output can be triggered in normal vehicle driving process by having more triggering modes；It avoids and such as encounters accidental problem under single triggering identification method bring trigger timing and lead to the problem of can not identifying always or recognition result can not be exported.
Description
Technical field
The present invention relates to field of license plate recognition, especially a kind of simultaneously using the Car license recognition side of a variety of triggering modes
Method.
Background technique
With the progress of image processing techniques, identify license plate in vehicle management and traffic using image processing techniques
It is played an increasingly important role in management.Car license recognition step based on image processing techniques mainly has License Plate, vehicle
Board correction, License Plate Character Segmentation, Recognition of License Plate Characters.License Plate Character Segmentation be to character each in the license plate image corrected into
Row segmentation, to obtain the independent image of each character, to be used in subsequent character recognition, to determine specific license plate
Number.
The existing ground sensation of license plate result trigger timing stablizes identification, virtual coil etc..1. ground sensation, logical in vehicle
Row installs ground induction coil on ground, and when above vehicle driving to coil, coil output signal is done to identification device, identification device
Then identification exports.This mode can with accurate vehicle position, only to a determining position when just identify, avoid vehicle
Not the problem of marching into the arena on road and identifying.2. stablizing identification, identification device identified always, when having identified stable license plate
When recognition result, recognition result is exported.This mode avoids the problem of single image Car license recognition inaccuracy, only when more
Just recognition result is exported when image or single image are apparent.3. virtual coil selects in the image-region of identification device
A small region is selected, identification device identifies always, and only just output identification is tied when the license plate recognized intersects with this region
Fruit.This mode avoids vehicle not the problem of identifying result on approach course.The prior art can only be selected using upper
A kind of identification triggering mode is stated, such as stable identification has been used just not to be available virtual coil.Above-mentioned two can not be used simultaneously
Kind or a variety of triggering modes.
Summary of the invention
The technical problem to be solved in the invention is trigger timing interior row when only using a kind of Car license recognition triggering mode
People, which is blocked, or major light unfavorable factor is caused leaks vehicle problem.
In order to solve the above technical problems, a kind of licence plate recognition method using a variety of triggering modes simultaneously of the invention,
The multiframe recognition result for first passing through video forms track of vehicle, determines to be same vehicle according to the track of vehicle of formation；So
Judge whether vehicle passes through corresponding triggering mode and triggered afterwards, result of the vehicle output containing track of vehicle triggered.
Further, following steps are specifically included,
Step S1: single-frame images obtains, and a hardwood image is obtained from video；
Step S2: single-frame images Car license recognition judges whether single-frame images can identify license plate number；If it is then
Enter step S3；If it is not possible, then return step S1；
Step S3: license plate recognition result record；
Step S4: license plate recognition result judgement judges whether are the license plate recognition result of single-frame images and recognition result before
It is similar；If similar, in groups by similar license plate recognition result；If dissimilar, return step S1；
Step S5: track of vehicle judgement judges license plate recognition result in groups and the upper whether same track of a vehicle；If
It is that then license plate recognition result trajectory lists will be added in groups；If it is not, then the track of vehicle that creation is new；
Step S6: judge vehicle with which kind of triggering mode triggers and exports the result containing track of vehicle.
Further, judge that vehicle is triggered with which kind of triggering mode successively to judge whether by steady in the step S6
Fixed identification triggering, virtual coil triggering or the triggering of ground induction coil signal.
It is further, further comprising the steps of,
Whether step S7: judgment step S6 output result has recorded, and if it is lifts banister rod；If it is not, then
New car arrival is done to record and argue for the sake of arguing.
Further, three frames finally identified are only recorded in the step S3 as a result, judging single-frame images in step S4
License plate recognition result whether front cross frame recognition result similar therewith；If similar, using three frame results as usable results.
After adopting the above method, the present invention can export license plate recognition result using a variety of trigger timings simultaneously, one
In the case that kind mode can not trigger identification, other kind of mode can also trigger identification.Thus when vehicle is met in the process of moving
When causing license plate that can not identify to fraction incident, having more triggering modes can trigger in normal vehicle driving process
Identification output；It avoids and such as encounters accidental problem under single triggering identification method bring trigger timing and cause not knowing always
The problem of not or recognition result can not being exported.
Detailed description of the invention
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is that the present invention is a kind of simultaneously using the flow chart of the licence plate recognition method of a variety of triggering modes.
Specific embodiment
As shown in Figure 1, of the invention is a kind of simultaneously using the licence plate recognition method of a variety of triggering modes, step S1: single frames
Image obtains, and a hardwood image is obtained from video.
Step S2: single-frame images Car license recognition judges whether single-frame images can identify license plate number；If it is then
Enter step S3；If without recognition result, return step S1.
Step S3: license plate recognition result record only records the three frame results finally identified.
Step S4: license plate recognition result judgement judges that the license plate recognition result of single-frame images and upper two frames recognition result are
It is no similar；If similar, this three frame is as usable results if similar；If dissimilar, return step S1.
Step S5: track of vehicle judgement judges license plate recognition result in groups and the upper whether same track of a vehicle；If
It is that then license plate recognition result trajectory lists will be added in groups, explanation is same vehicle；If it is not, then the track of vehicle that creation is new,
As new car, a track of vehicle and overall situation track unique identification trackid are completely newly constructedglobal=trackidglobal+ 1,
Track of vehicle unique identification trackid=trackid is setglobal。
Step S6: judge that vehicle successively judges whether so which kind of triggering mode triggers and exports the result containing track of vehicle
By stablizing identification triggering, virtual coil triggering or the triggering of ground induction coil signal.It is specific as follows:
Judge whether this vehicle passes through stable identification and triggeredIf triggering
It crosses, jumps to next step.If do not triggered, judge whether to reach stable state, be exported if reaching and in result
Containing track of vehicle trackid, and record this track unique identification passed through stablize identification exported,
trackidstability=trackid.
Judge whether this vehicle passes through virtual coil and triggeredIf triggering
It crosses, jumps to next step.If do not triggered, judge whether by virtual coil, if being exported and if in result
Containing track of vehicle trackid, and records this track unique identification and has passed through virtual coil and exported,
trackidvirtualcoil=trackid.
Ground induction coil signal is judged whether there is, if there is then exporting and containing track of vehicle trackid in result.
Can be used simultaneously different triggering modes repeatedly to export recognition result in this way, and using Vehicle tracing come to
Recognition result have unique identification, recognition result processing can be apparent from using unique identification multiple results indicate it is same
Vehicle.Occasional problem (block, major light) of the vehicle due to single triggering mode when is avoided, and recognition result can not be exported,
Vehicle is caused to reveal identification problem.Simultaneously use a variety of triggering modes, such occasional problem may only influence it is one or more, as long as
Having a kind of triggering mode not receive influence just can correctly export recognition result.And a variety of triggering modes are when all exporting result,
Correct processing can be done according to vehicle unique identification, avoid regarding multiple result into more different vehicles as.
The present invention be due to there is vehicle unique identification trackid in recognition result, even if so vehicle repeatedly identification or
Trackid is the same when difference identification.It can not be influenced by multiple recognition results of same vehicle using this feature.With
Banister rod is risen at once as applicating example after having recognition result:
Whether step S7: judgment step S6 output result has recorded, and judges whether that this result is recorded and argues for the sake of arguingIf it is, lifting banister rod and terminating；It is recorded if it is not, then doing new car and arriving,
Record trackidEnter#%=trackid simultaneously argues for the sake of arguing.
Although specific embodiments of the present invention have been described above, those skilled in the art should be appreciated that this
It is merely illustrative of, various changes or modifications can be made to present embodiment, without departing from the principle and essence of invention, originally
The protection scope of invention is only limited by the claims that follow.
Claims (5)
1. a kind of simultaneously using the licence plate recognition method of a variety of triggering modes, it is characterised in that: first pass through the multiframe identification of video
As a result track of vehicle is formed, determines to be same vehicle according to the track of vehicle of formation；Then judge whether vehicle passes through phase
The triggering mode answered triggered, result of the vehicle output containing track of vehicle triggered.
2. described in accordance with the claim 1 a kind of simultaneously using the licence plate recognition method of a variety of triggering modes, which is characterized in that tool
Body includes the following steps,
Step S1: single-frame images obtains, and a hardwood image is obtained from video；
Step S2: single-frame images Car license recognition judges whether single-frame images can identify license plate number；If it is then into
Step S3；If it is not possible, then return step S1；
Step S3: license plate recognition result record；
Step S4: license plate recognition result judgement judges whether the license plate recognition result of single-frame images is similar to recognition result before；
If similar, in groups by similar license plate recognition result；If dissimilar, return step S1；
Step S5: track of vehicle judgement judges license plate recognition result in groups and the upper whether same track of a vehicle；If it is,
License plate recognition result trajectory lists will be added in groups；If it is not, then the track of vehicle that creation is new；
Step S6: judge vehicle with which kind of triggering mode triggers and exports the result containing track of vehicle.
3. a kind of simultaneously using the licence plate recognition method of a variety of triggering modes according to claim 2, it is characterised in that: institute
It states and judges that vehicle is triggered with which kind of triggering mode successively to judge whether by stablizing identification triggering, virtual coil touching in step S6
Hair or the triggering of ground induction coil signal.
4. a kind of simultaneously using the licence plate recognition method of a variety of triggering modes according to claim 2, which is characterized in that also
Include the following steps,
Whether step S7: judgment step S6 output result has recorded, and if it is lifts banister rod；If it is not, then doing new
Vehicle, which arrives, to be recorded and argues for the sake of arguing.
5. a kind of simultaneously using the licence plate recognition method of a variety of triggering modes according to claim 2, it is characterised in that: institute
It states and only records three frames finally identified in step S3 as a result, the license plate recognition result and before two for judging single-frame images in step S4
Whether frame recognition result is similar；If similar, using three frame results as usable results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711134851.5A CN109801498A (en) | 2017-11-16 | 2017-11-16 | Licence plate recognition methods a kind of while using a variety of triggering modes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711134851.5A CN109801498A (en) | 2017-11-16 | 2017-11-16 | Licence plate recognition methods a kind of while using a variety of triggering modes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109801498A true CN109801498A (en) | 2019-05-24 |
Family
ID=66555303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711134851.5A Pending CN109801498A (en) | 2017-11-16 | 2017-11-16 | Licence plate recognition methods a kind of while using a variety of triggering modes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109801498A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101373517A (en) * | 2007-08-22 | 2009-02-25 | 北京万集科技有限责任公司 | Method and system for recognizing license plate |
| CN101807346A (en) * | 2009-02-16 | 2010-08-18 | 汉王科技股份有限公司 | Automatic license plate identification system at urban checkpoint |
| CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
| CN103914682A (en) * | 2013-01-09 | 2014-07-09 | 深圳市中联创新自控系统有限公司 | Vehicle license plate recognition method and system |
| CN103927871A (en) * | 2014-04-21 | 2014-07-16 | 哈尔滨工业大学 | Vehicle detecting device based on multi-kind sensor information |
| KR101422217B1 (en) * | 2014-06-16 | 2014-08-13 | (주)샤인정보통신 | Method for providing number cognition service of vehicle |
| CN104392239A (en) * | 2014-09-25 | 2015-03-04 | 深圳市捷顺科技实业股份有限公司 | License plate identification method and system |
| CN104573637A (en) * | 2014-12-18 | 2015-04-29 | 厦门翼歌软件科技有限公司 | Multi-camera-based vehicle license plate recognition method |
| KR20160067631A (en) * | 2014-12-04 | 2016-06-14 | 황용호 | Method for recognizing vehicle plate |
| US20170124418A1 (en) * | 2013-12-04 | 2017-05-04 | Irida Labs S.A. | System and a method for the detection of multiple number-plates of moving cars in a series of 2-d images |
| CN106778648A (en) * | 2016-12-26 | 2017-05-31 | 江苏盛世华安智能科技股份有限公司 | Vehicle tracing and Vehicle License Plate Recognition System and recognition methods |
-
2017
- 2017-11-16 CN CN201711134851.5A patent/CN109801498A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101373517A (en) * | 2007-08-22 | 2009-02-25 | 北京万集科技有限责任公司 | Method and system for recognizing license plate |
| CN101807346A (en) * | 2009-02-16 | 2010-08-18 | 汉王科技股份有限公司 | Automatic license plate identification system at urban checkpoint |
| CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
| CN103914682A (en) * | 2013-01-09 | 2014-07-09 | 深圳市中联创新自控系统有限公司 | Vehicle license plate recognition method and system |
| US20170124418A1 (en) * | 2013-12-04 | 2017-05-04 | Irida Labs S.A. | System and a method for the detection of multiple number-plates of moving cars in a series of 2-d images |
| CN103927871A (en) * | 2014-04-21 | 2014-07-16 | 哈尔滨工业大学 | Vehicle detecting device based on multi-kind sensor information |
| KR101422217B1 (en) * | 2014-06-16 | 2014-08-13 | (주)샤인정보통신 | Method for providing number cognition service of vehicle |
| CN104392239A (en) * | 2014-09-25 | 2015-03-04 | 深圳市捷顺科技实业股份有限公司 | License plate identification method and system |
| KR20160067631A (en) * | 2014-12-04 | 2016-06-14 | 황용호 | Method for recognizing vehicle plate |
| CN104573637A (en) * | 2014-12-18 | 2015-04-29 | 厦门翼歌软件科技有限公司 | Multi-camera-based vehicle license plate recognition method |
| CN106778648A (en) * | 2016-12-26 | 2017-05-31 | 江苏盛世华安智能科技股份有限公司 | Vehicle tracing and Vehicle License Plate Recognition System and recognition methods |
Non-Patent Citations (6)
| Title |
|---|
| 于海亮: ""基于软触发的车牌识别"", 《可编程控制器与工厂自动化》 * |
| 唐震等: ""高清治安卡口智能信息识别系统及应用"", 《电视技术》 * |
| 宋文举: ""高清治安卡口智能信息识别系统及应用"", 《科技致富向导》 * |
| 朱月红: ""城区治安卡口系统设计关键要素简析"", 《警察技术》 * |
| 焦宏斌: ""基于图像处理的车牌识别系统的研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈泳: ""智能视频监控平台开发及其在停车场车牌识别系统中的应用与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019105342A1 (en) | Method and apparatus for detecting fake license plates of vehicles, readable storage medium, and electronic device | |
| CN110163176B (en) | Lane line change position identification method, device, equipment and medium | |
| JP2019075116A (en) | Method for acquiring bounding box corresponding to object on image by using cnn (convolutional neural network) including tracking network | |
| CN106960195A (en) | A kind of people counting method and device based on deep learning | |
| CN103366154B (en) | Reconfigurable clear path detection system | |
| CN110443225A (en) | A kind of actual situation Lane detection method and device thereof based on statistics of pixel eigenvalue | |
| CN106408554A (en) | Remnant detection apparatus, method and system | |
| CN102201059A (en) | Pedestrian detection method and device | |
| CN112733581B (en) | Vehicle attribute identification method and system | |
| KR102641117B1 (en) | Method and apparatus of augmenting image | |
| CN111191611A (en) | Deep learning-based traffic sign label identification method | |
| CN110544268B (en) | Multi-target tracking method based on structured light and SiamMask network | |
| CN108073926A (en) | A kind of licence plate recognition method and device | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN108198431A (en) | Vehicle parking detection device | |
| CN108335492A (en) | Vehicle parking detection method and computer readable storage medium | |
| CN107451156A (en) | A kind of image recognition methods and identification device again | |
| KR102564856B1 (en) | Method and apparatus of detecting road line | |
| CN104735296B (en) | Pedestrian's detecting system and method | |
| CN112232368A (en) | Target recognition model training method, target recognition method and related device thereof | |
| CN111914845A (en) | Character layering method and device in license plate and electronic equipment | |
| CN108171229A (en) | A kind of recognition methods of hollow adhesion identifying code and system | |
| CN111340045A (en) | License plate number recognition method and device and storage medium | |
| CN109643363A (en) | The mthods, systems and devices of feature extraction and object detection | |
| CN109800684A (en) | The determination method and device of object in a kind of video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |