CN102708375A - High-definition integrated license plate snapshot recognition equipment and method - Google Patents
High-definition integrated license plate snapshot recognition equipment and method Download PDFInfo
- Publication number
- CN102708375A CN102708375A CN2012101137746A CN201210113774A CN102708375A CN 102708375 A CN102708375 A CN 102708375A CN 2012101137746 A CN2012101137746 A CN 2012101137746A CN 201210113774 A CN201210113774 A CN 201210113774A CN 102708375 A CN102708375 A CN 102708375A
- Authority
- CN
- China
- Prior art keywords
- module
- high definition
- fpga
- car plate
- video
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 5
- 238000010025 steaming Methods 0.000 claims description 22
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 239000007787 solid Substances 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 244000188472 Ilex paraguariensis Species 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 230000011664 signaling Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Landscapes
- Character Discrimination (AREA)
Abstract
The invention provides high-definition integrated intelligent snapshot recognition equipment and a high-definition integrated intelligent snapshot recognition method, wherein the equipment comprises a video input and acquisition module, a signal processing module and a transmission and storage module, the signal processing module comprises a DSP chip, a high-resolution image acquired by a CCD module is subjected to image preprocessing by an FPGA, the DSP chip processes the image input by the FPGA, license plate positioning, license plate segmentation and character recognition are sequentially carried out, license plate information is automatically extracted, the license plate information is converted into a high-definition video stream, and the high-definition video stream is output through a network by a video encoder through H.264 or MPEG4 coding and used for video recording and real-time display.
Description
Technical field
The present invention relates to a kind of car plate and capture identification equipment and method, be specifically related to a kind of high definition integral and intelligent and capture identification equipment and method.
Background technology
Along with the sharp increase of vehicle guaranteeding organic quantity, urban traffic control is also increasingly high to the requirement of intelligent transportation system, and the SD video that analogue camera is taken can not satisfy growing supervisory system requirement.Adopt the high-definition camera imaging technique; Not only can clear candid photograph car plate; High-quality driver and conductor's characteristic can also be provided, and can the registration of vehicle overall picture and information such as automobile scenarios, thereby satisfied the demand of a plurality of business departments such as criminal investigation, public security, traffic police.In addition, adopt 2,000,000 or the video camera of higher pixel, a video camera can be captured 2-3 bar track, and system's construction efficiency also obviously improves.Therefore, the car plate capture and identification system based on high-definition image comprises public security Gate System, electronic police system etc., has become a focus of current development.
Existing car plate capture and identification system generally includes camera, light filling lamp, industrial computer/embedded identifier, hub/router, fiber optic etc.; Because equipment is more; Each equipment all might go wrong, and causes the total system stability decreases, and camera and analytical equipment are not installed together simultaneously; A large amount of lines also is the factors of instability, and the investigation fault wastes time and energy.Because the adjustment of camera and software often will cooperate to be carried out, the design of separate type can be installed to debugging and put to no little inconvenience in addition, and is if think migration equipment to other monitoring point, also very difficult.The rising of Installation and Debugging cost directly restricts the quantity of monitoring point, can bring negative effect for traffic control.Therefore embedded scheme, integrated design are reduced weight, taked to number of devices is an important development direction of car plate capture and identification system.
Summary of the invention
A kind of high definition integral type car plate is captured identification equipment; It is characterized in that: comprise video input and acquisition module, signal processing module, transmission and memory module, wherein, video input and acquisition module comprise CCD module, a FPGA and the 2nd FPGA; The CCD module is connected with a FPGA; Signal processing module comprises dsp chip, and DSP handles the image of FPGA input, extracts license board information automatically; Said license board information is converted into high definition video steaming, and H.264 video encoder carries out said high definition video steaming or the MPEG4 coding is exported through network; Transmission and memory module comprise 3G module, SSD module, SD module and said video encoder; 3G module, SSD module, SD module are carried out the two-way signaling transmission through dsp bus and said dsp chip respectively; Said high definition video steaming sends PC to through the 3G module, and said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.
Further, the 2nd FPGA is OSD FPGA.
Further, the bus switch that a FPGA, the 2nd FPGA, video encoder pass through separately respectively is connected with the video expansion bus, and said video expansion bus links to each other with said DSP.
The high definition integral type car plate that adopts above-mentioned high definition integral type car plate to capture identification equipment is captured recognition methods; It is characterized in that: a FPGA is through the acquisition parameter of its inner integrated 3A algorithm adjustment CCD module; The CCD module is gathered high-definition picture and is sent a FPGA to and carries out the image pre-service; Dsp chip utilizes its embedded intelligent algorithm, carries out successively that car plate location, car plate are cut apart, character recognition, extracts license board information automatically; Said license board information is converted into high definition video steaming, and H.264 video encoder carries out said high definition video steaming or the MPEG4 coding is exported through network; Said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.
Further; Said car plate localization step does; Obtain one group of master's sight word to each characters on license plate training, these main sight word contain the geological information of yardstick, principal direction, relative position, partial descriptions, the image of then a FPGA being imported; Through with the geological information of the main sight word of wherein local feature coupling, accurately estimate the position of car plate.
Further, the step that said car plate is cut apart is that the conscientious Character segmentation of image that the method that adopts adaptive morphology to learn is blured car plate detected fragment and these fragments of merging automatically based on histogrammic algorithm before separating character.
Further, the step of said character recognition does, adopts based on the contextual Character mother plate matching process of shape, input character and standard character is placed in the sorter matees.
Description of drawings:
Accompanying drawing 1 is the structure composition diagram that high definition integral type car plate of the present invention is captured identification equipment.
Embodiment:
Referring to accompanying drawing 1, this equipment integration DSP and FPGA etc. realize the function of total system, and hardware configuration mainly comprises three parts: video input and acquisition module, signal processing module, transmission and memory module.
The each several part major function is following:
1, video input and acquisition module
The high-definition picture of CCD module collection carries out the image pre-service by FPGA, and the acquisition parameter through the inner integrated 3A algorithm adjustment equipment of FPGA like shutter, gain etc., improves the picture quality of gathering, and makes it gorgeous more clear.
2, signal processing module
This module is the core of native system.This module mainly is made up of powerful DSP chip and embedded intelligent algorithm, and main the completion extracted vehicle and license board information automatically, carries out functions such as vehicle detection and car plate identification.
3, transmission and memory module
The data of handling through DSP are sent on the equipment of PC or other protocol compliant by communication 3G module, network interface or serial ports, and when network failure, deal with data stores on SD card or the SSD solid state hard disc.H.264 video encoder carries out or the MPEG4 coding the input high definition video steaming, is used for video record and shows in real time.
A kind of high definition integral type car plate is captured identification equipment and is comprised video input and acquisition module, signal processing module, transmission and memory module; Wherein, Video input and acquisition module comprise CCD module, a FPGA and the 2nd FPGA, and the CCD module is connected with a FPGA, and signal processing module comprises dsp chip; DSP handles the image of FPGA input; Automatically extract license board information, said license board information is converted into high definition video steaming, H.264 video encoder carries out said high definition video steaming or the MPEG4 coding passes through network output; Transmission and memory module comprise 3G module, SSD module, SD module and said video encoder; 3G module, SSD module, SD module are carried out the two-way signaling transmission through dsp bus and said dsp chip respectively; Said high definition video steaming sends PC to through the 3G module, and said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.The 2nd FPGA is OSD FPGA.The bus switch that the one FPGA, the 2nd FPGA, video encoder pass through separately respectively is connected with the video expansion bus, and said video expansion bus links to each other with said DSP.
The high definition integral type car plate that adopts above-mentioned high definition integral type car plate to capture identification equipment is captured recognition methods; The one FPGA is through the acquisition parameter of its inner integrated 3A algorithm adjustment CCD module; The CCD module is gathered high-definition picture and is sent a FPGA to and carries out the image pre-service; Dsp chip utilizes its embedded intelligent algorithm, carries out successively that car plate location, car plate are cut apart, character recognition, extracts license board information automatically; Said license board information is converted into high definition video steaming, and H.264 video encoder carries out said high definition video steaming or the MPEG4 coding is exported through network; Said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.
Said car plate localization step does; Obtain one group of master's sight word to each characters on license plate training; These main sight word contain the geological information of yardstick, principal direction, relative position, partial descriptions; Then to the image of FPGA input, through with the geological information of the main sight word of wherein local feature coupling, accurately estimate the position of car plate.
The step that said car plate is cut apart is that the conscientious Character segmentation of image that the method that adopts adaptive morphology to learn is blured car plate detected fragment and these fragments of merging automatically based on histogrammic algorithm before separating character.
The step of said character recognition does, adopts based on the contextual Character mother plate matching process of shape, input character and standard character is placed in the sorter matees.
Wherein signal processing module also comprises embedded licence plate recognition method except process chip, and it mainly is divided into following three steps:
The car plate location:
This step adopts main sight word discover method, trains one group to characters on license plate and has abundant how much contextual sight word, is used for automatic car plate and detects.To the deficiency of traditional car plate detection method based on image border figure, from how much contextual angles of local feature, with a kind of main sight word generating algorithm of novelty.Obtain one group of master's sight word to each characters on license plate training, these main sight word contain abundant geological information, like yardstick, principal direction, relative position, local description etc.; Then to test pattern, can through with the geological information of the main sight word of wherein local feature coupling, accurately estimate the position of car plate.The main sight word that this method generates has very strong separating capacity and ability to express, and related with specific semantic concept (characters on license plate).The framework of method mainly is made up of three parts: main sight word generates, sight word coupling and car plate location.Generate for main sight word, we collect the number of characteristics sample and are used for training from the training image that marks; To each characters on license plate, we generate one group of master's sight word through cluster.For sight word coupling and car plate location, we extract characteristic from test pattern, and compare with all main sight word that trains, and carry out the car plate location according to the result of mating.
Car plate is cut apart:
The conscientious Character segmentation of image that the method that this step adopts adaptive morphology to learn is blured car plate detected fragment and these fragments of merging automatically based on histogrammic algorithm before separating character.For cutting apart of overlapping character, the morphology hierarchical algorithms is confirmed reference automatically; For cutting apart of concatenation character, the morphology thinning algorithm with cut apart cost and calculate automatic detection reference line.This method can detection of broken, the overlapping or character that connects, has given prominence to adaptive characteristics.
Character recognition:
This step adopts is based on the contextual Character mother plate matching process of shape.Input character and standard character be placed in the sorter mate.If the image template of known target object is T, size is M * N, and image I size to be investigated is L * W (L＞M, W＞N).The process of coupling is at first carried out normalization to character picture and is handled, and manage a template T then and be added on the image I, and the difference of the I subimage under T and its covering relatively.If difference, thinks then that T and I subimage have coupling preferably, have promptly found destination object less than the value of closing that configures in advance.To entire image individual element scanning to be matched and enforcement aforesaid operations, then can confirm whether there is the determined destination object of template T in the image I.The mathematical description of matching process is:
First and the 3rd the corresponding subclass of presentation video I and the autocorrelation of template T respectively wherein.Second cross correlation that has then provided both.This is big more, and then (i, value j) is more little, subimage and the template matches of expression original image good more for D.D (i, j) be zero explanation both mate fully.The Character mother plate that adopts is in real image, to collect, and is on the basis that the MSER algorithm is cut apart, and finds the character zone Far Left, rightmost, and the top and black picture element position bottom are as the actual frame size foundation of confirming character.Carry out the bi-directional scaling image manipulation then, adopt the method for interpolation calculation, so that the template size that obtains stipulating (24 * 48).
Claims (7)
1. a high definition integral type car plate is captured identification equipment; It is characterized in that: comprise video input and acquisition module, signal processing module, transmission and memory module, wherein, video input and acquisition module comprise CCD module, a FPGA and the 2nd FPGA; The CCD module is connected with a FPGA; Signal processing module comprises dsp chip, and DSP handles the image of FPGA input, extracts license board information automatically; Said license board information is converted into high definition video steaming, and H.264 video encoder carries out said high definition video steaming or the MPEG4 coding is exported through network; Transmission and memory module comprise 3G module, SSD module, SD module and said video encoder; 3G module, SSD module, SD module are carried out the two-way signaling transmission through dsp bus and said dsp chip respectively; Said high definition video steaming sends PC to through the 3G module, and said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.
2. high definition integral type car plate as claimed in claim 1 is captured identification equipment, and it is characterized in that: the 2nd FPGA is OSD FPGA.
3. according to claim 1 or claim 2 high definition integral type car plate is captured identification equipment; It is characterized in that: the bus switch that a FPGA, the 2nd FPGA, video encoder pass through separately respectively is connected with the video expansion bus, and said video expansion bus links to each other with said DSP.
4. the high definition integral type car plate that adopts the arbitrary described high definition integral type car plate of claim 1-3 to capture identification equipment is captured recognition methods; It is characterized in that: a FPGA is through the acquisition parameter of its inner integrated 3A algorithm adjustment CCD module; The CCD module is gathered high-definition picture and is sent a FPGA to and carries out the image pre-service; Dsp chip utilizes its embedded intelligent algorithm, carries out successively that car plate location, car plate are cut apart, character recognition, extracts license board information automatically; Said license board information is converted into high definition video steaming, and H.264 video encoder carries out said high definition video steaming or the MPEG4 coding is exported through network; Said high definition video steaming passes through SSD module, SD module stores respectively on SSD solid state hard disc, SD card.
5. high definition integral type car plate as claimed in claim 4 is captured recognition methods; It is characterized in that: said car plate localization step does; Obtain one group of master's sight word to each characters on license plate training, these main sight word contain the geological information of yardstick, principal direction, relative position, partial descriptions, the image of then a FPGA being imported; Through with the geological information of the main sight word of wherein local feature coupling, accurately estimate the position of car plate.
6. high definition integral type car plate as claimed in claim 5 is captured recognition methods; It is characterized in that: the step that said car plate is cut apart does; The conscientious Character segmentation of image that the method that adopts adaptive morphology to learn is blured car plate detected fragment and these fragments of merging automatically based on histogrammic algorithm before separating character.
7. capture recognition methods like claim 5 or 6 described high definition integral type car plates; It is characterized in that: the step of said character recognition does; Employing is based on the contextual Character mother plate matching process of shape, input character and standard character is placed in the sorter matees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210113774.6A CN102708375B (en) | 2012-04-18 | 2012-04-18 | High-definition integrated license plate snapshot recognition equipment and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210113774.6A CN102708375B (en) | 2012-04-18 | 2012-04-18 | High-definition integrated license plate snapshot recognition equipment and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708375A true CN102708375A (en) | 2012-10-03 |
| CN102708375B CN102708375B (en) | 2017-07-18 |
Family
ID=46901118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210113774.6A Expired - Fee Related CN102708375B (en) | 2012-04-18 | 2012-04-18 | High-definition integrated license plate snapshot recognition equipment and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708375B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734170A (en) * | 2018-05-25 | 2018-11-02 | 电子科技大学 | Registration number character dividing method based on machine learning and template |
| CN112085023A (en) * | 2020-09-14 | 2020-12-15 | 重庆紫光华山智安科技有限公司 | Motor vehicle license plate recognition method, system, medium and terminal based on infrared imaging |
| CN113139946A (en) * | 2021-04-26 | 2021-07-20 | 北方工业大学 | Shirt stain positioning device based on vision |
| CN113259679A (en) * | 2021-06-30 | 2021-08-13 | 四川赛狄信息技术股份公司 | Image processing system for realizing image compression based on domestic DSP chip |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090161750A1 (en) * | 2007-12-19 | 2009-06-25 | Marc Racicot | Multiplexing video using a dsp |
| CN201298246Y (en) * | 2008-12-05 | 2009-08-26 | 长安大学 | A highway bridge toll station automatically quoting device |
| CN101909154A (en) * | 2010-08-11 | 2010-12-08 | 深圳市中盟科技股份有限公司 | Intelligent camera device |
| CN201946113U (en) * | 2010-11-24 | 2011-08-24 | 西安迅行信息科技有限公司 | License plate recognition device with high-definition image snapshot function |
-
2012
- 2012-04-18 CN CN201210113774.6A patent/CN102708375B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090161750A1 (en) * | 2007-12-19 | 2009-06-25 | Marc Racicot | Multiplexing video using a dsp |
| CN201298246Y (en) * | 2008-12-05 | 2009-08-26 | 长安大学 | A highway bridge toll station automatically quoting device |
| CN101909154A (en) * | 2010-08-11 | 2010-12-08 | 深圳市中盟科技股份有限公司 | Intelligent camera device |
| CN201946113U (en) * | 2010-11-24 | 2011-08-24 | 西安迅行信息科技有限公司 | License plate recognition device with high-definition image snapshot function |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734170A (en) * | 2018-05-25 | 2018-11-02 | 电子科技大学 | Registration number character dividing method based on machine learning and template |
| CN108734170B (en) * | 2018-05-25 | 2022-05-03 | 电子科技大学 | License plate character segmentation method based on machine learning and template |
| CN112085023A (en) * | 2020-09-14 | 2020-12-15 | 重庆紫光华山智安科技有限公司 | Motor vehicle license plate recognition method, system, medium and terminal based on infrared imaging |
| CN113139946A (en) * | 2021-04-26 | 2021-07-20 | 北方工业大学 | Shirt stain positioning device based on vision |
| CN113259679A (en) * | 2021-06-30 | 2021-08-13 | 四川赛狄信息技术股份公司 | Image processing system for realizing image compression based on domestic DSP chip |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708375B (en) | 2017-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103500322B (en) | Automatic lane line identification method based on low latitude Aerial Images | |
| CN104766086B (en) | The monitoring and managing method and system of a kind of way mark | |
| CN101873414B (en) | Event video detection system based on hierarchical structure | |
| CN111161543A (en) | Automatic snapshot method and system for bus front violation behavior based on image recognition | |
| CN102915432B (en) | A kind of vehicle-mounted microcomputer image/video data extraction method and device | |
| CN102509090B (en) | A kind of vehicle feature recognition device based on public safety video image in sky net engineering | |
| CN204155449U (en) | A kind of Car license recognition comparison high-definition camera and supervisory system | |
| CN102982311A (en) | Vehicle video characteristic extraction system and vehicle video characteristic extraction method based on video structure description | |
| CN104504377A (en) | Bus passenger crowding degree identification system and method | |
| CN112085952A (en) | Vehicle data monitoring method and device, computer equipment and storage medium | |
| CN108109385A (en) | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method | |
| CN103996041A (en) | Vehicle color identification method and system based on matching | |
| CN103186982A (en) | Intelligent access system for public security | |
| CN113095434A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN103236181A (en) | Traffic signal lamp state monitoring system and method based on machine vision | |
| CN112633120B (en) | Model training method of intelligent roadside sensing system based on semi-supervised learning | |
| CN103646544B (en) | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus | |
| CN102708375A (en) | High-definition integrated license plate snapshot recognition equipment and method | |
| CN104504904A (en) | Mobile acquisition method of transportation facility | |
| CN202003508U (en) | Bus lane illegal vehicle intruding detection equipment | |
| CN205621299U (en) | Supplementary station reporting system and automobile -mounted terminal based on video identification | |
| CN106530727A (en) | Traffic violation information processing system | |
| CN117036798A (en) | Power transmission and distribution line image recognition method and system based on deep learning | |
| CN115588130B (en) | Domain-self-adaption-based cross-domain YOLO detection method | |
| CN109698900B (en) | Data processing method, device and monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170718 Termination date: 20200418 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |