CN109948618A - A kind of terminal, the system and method for remote Car license recognition - Google Patents
A kind of terminal, the system and method for remote Car license recognition Download PDFInfo
- Publication number
- CN109948618A CN109948618A CN201910164057.8A CN201910164057A CN109948618A CN 109948618 A CN109948618 A CN 109948618A CN 201910164057 A CN201910164057 A CN 201910164057A CN 109948618 A CN109948618 A CN 109948618A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- module
- character
- license
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000000007 visual effect Effects 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims description 22
- 208000003164 Diplopia Diseases 0.000 claims description 16
- 208000029444 double vision Diseases 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000009466 transformation Effects 0.000 description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000283070 Equus zebra Species 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Character Input (AREA)
Abstract
The invention discloses terminal, the system and method for a kind of remote Car license recognition, it is designed using the dual camera of telephoto lens and wide-angle lens, wherein wide-angle camera visual angle is 120 degree, and telephoto lens visual angle, which is 20 degree, can collect relatively remote interior clear license plate image.By pair License Plate detection, identify position and the size of license plate, each license plate in scene can automatically, be accurately and fast captured by the locating rotation of holder module, it has both superelevation and captures accuracy rate and ultralow omission factor, allow to identify the license board information under the extensive scene such as remote, big wide-angle.
Description
Technical field
The present invention relates to a kind of field of license plate recognition, terminal, the system of specifically a kind of remote Car license recognition
And method.
Background technique
With the development of highway in China communication, the quantity of vehicle is increasing rapidly, to trip provider just
Meanwhile problem becomes increasingly conspicuous present on vehicle management, the mode of labor management is no longer satisfied actual needs.Micro- electricity
Son, communication and computer technology greatly improve traffic administration efficiency in the application of field of traffic.As information source from
Dynamic detection, image recognition technology are increasingly valued by people.The rapid development and Digital image technology of computer in recent years
Reach its maturity, bring dramatic shift for traditional traffic administration, advanced computer processing technology, not only can by manpower from
It is freed in cumbersome artificial observation, monitoring, and its accuracy can be greatly improved, vehicle license plate reading system is just
It is to be developed under such background and purpose.The automatic collection of the relevant informations such as license plate and management are for special bus
Management, garden vehicle management, parking lot management, traffic police's inspection etc. are of great significance to.
About license plate recognition technology and positioning system research, there is the development course of more than ten years in China, has been at present
The application of system is still in infancy, and the mature system that large scale investment uses occurs not yet, and Vehicle License Recognition System is made
For the effective tool for improving traffic administration, technical level still needs to perfect.Domestic and foreign scholars have had more work to this, but real
The effect is unsatisfactory on border, and high speed license plate locating method especially strong to license plate adaptivity, that speed is fast, accuracy rate is high need
Further research.In addition, requiring secondary light source high, it is also difficult to effectively solve the technology of the mobile identification of more license plates under complex background
Problem, such as: inclination, license plate surface filth or abrasion, the light interference of license plate image can all influence the accuracy of positioning.Tradition
Car license recognition generally only supports single car, and background is fairly simple.And current many practical applications, such as on heavy traffic road
Mouth temporarily takes to tax arrear, scraps, reports the loss etc. the inspection of vehicles, then monitor area is more complicated, and existing recognition methods can not be direct
Using;And in most cases, while there are more automobiles, background has billboard, trees, building, zebra stripes and various
Background text etc., existing recognition methods can not well adapt to changeable environment.
Since license plate image is mostly in taken outdoors, the influence of illumination condition, weather condition will receive, image occur and obscure,
Contrast is low, and target area is too small, and color distortion etc. influences, and the adjoint complicated background image of meeting, every time target when acquisition
Present position is different, and visual angle can great changes have taken place for acquisition, and due to license plate hang not just, all will lead to license plate and turn round
Song, these can all influence License Plate and identification.
Summary of the invention
Be to solve the prior art there are the above problem, the application provide the terminal of remote Car license recognition a kind of, system and
Method, while realizing detection and candid photograph to multiple license plates, it has both superelevation and captures accuracy rate and ultralow omission factor, so that long distance
It is possibly realized from the Car license recognition under, big wide-angle etc. extensively scene.
To achieve the above object, a kind of technical solution of the application are as follows: terminal of remote Car license recognition, comprising:
Double vision image capture module, for acquiring larger range, longer-distance image information.It is a wide range of, remote to realize
The Car license recognition of distance, double vision image capture module use a telephoto lens, and the dual camera of a wide-angle lens designs,
Middle wide-angle lens visual angle is 120 degree, and telephoto lens visual angle, which is 20 degree, can collect clear license plate image in range farther out.
Command process module receives license plate position and size information that License Plate detection module issues, generates holder position
Adjustment instruction is set, and instruction is issued to holder module.
Holder module receives the instruction that command process module issues, and adjusts the roll axis and pitching shaft position of holder.
Present invention also provides a kind of systems of remote Car license recognition, comprising:
License plate image obtains module, obtains the image of double vision image capture module acquisition, and the acquisition of wide-angle lens module is
First image, the acquisition of telephoto lens module is the second image.
License Plate detection module, for whether detecting in the first image comprising license plate and license plate position and size letter
License plate position and size information are issued to described instruction processing module by breath, and command process module receives License Plate and detects mould
The license plate position and size information that block issues generate holder position adjustment instruction, and instruction are issued to holder module.Holder mould
Block receives the instruction that command process module issues, and adjusts the roll axis and pitching shaft position of holder.
Image pre-processing module will be in the progress of the second image for carrying out clarity recovery processing to the second image information
Value filtering processing, restores image irradiation, fold, contrast etc., and the image after adjusting clarity is third image.By third image
Using median filter process, then by image binaryzation, morphology boundary is found, then carries out affine transformation correction.
License Plate Character Segmentation module, for being mutual independent character by the Character segmentation on license plate;Complete licence plate area
After the positioning in domain, it is also necessary to license plate area are divided into single character, character recognition is then carried out, finally export result.Character
Segmentation generally uses vertical projection method.The principle of vertical projection method is since the projection of character in vertical direction is inevitable in character
Between or character in gap location obtain local minimum near, and this position should meet licence plate character writing format,
Character, size limitation and some other conditions.So using vertical projection method to the character point of the automobile image under complex environment
Preferable effect is cut.
In addition, present invention also provides a kind of methods of remote Car license recognition, comprising:
Double vision image capture module, the image transmitting that wide-angle lens module is acquired to license plate image obtain module;
Whether license plate image obtains module for image transmitting to License Plate detection module, detect and wrap in the first image
Containing license plate and license plate position and size information, license plate position and size information are issued to described instruction processing module;
Command process module receives license plate position and size information that License Plate detection module issues, generates holder position
Adjustment instruction is set, and instruction is issued to holder module.
Holder module receives the instruction that command process module issues, and adjusts the roll axis and pitching shaft position of holder.Double vision
Image capture module, the image transmitting that telephoto lens module is acquired to license plate image obtain module;
The image transmitting that license plate image acquisition module acquires telephoto lens module to image pre-processing module, locate in advance by image
It manages the clarity in module and restores submodule for the second image progress median filter process, restore image irradiation, fold, contrast
Deng the image after adjusting clarity is third image, by image binaryzation, finds morphology boundary, then carries out affine transformation
Correction;
License Plate detection module is scanned the license plate image in third image information, and the scheme of use is first
A wide range of relevant search is carried out to collected video image, finds several regions for meeting license plate feature as candidate
Then area is further analyzed these candidate regions, judges, finally select an optimal region as license plate area, and
It is split from image.By above step, licence plate is generally possible to be positioned.
License Plate Character Segmentation module, after the positioning for completing license plate area, it is also necessary to which license plate area is divided into single word
Symbol, then carries out character recognition, finally exports result.Character segmentation generally uses vertical projection method.The principle of vertical projection method
Be since the inevitable gap location in intercharacter or character of the projection of character in vertical direction obtains near local minimum,
And this position should meet the limitation of character writing format, character, size and some other conditions of licence plate.So using vertical
Sciagraphy has preferable effect to the Character segmentation of the automobile image under complex environment.
Recognition of License Plate Characters module, character identifying method it is main at present algorithm there are two types of i.e. based on template matching algorithm and
Based on artificial neural network algorithm.Based on template matching algorithm first by the character binaryzation after segmentation, and by its size
It is scaled the size of template in character database, is then matched with all templates, finally selects best match as a result.
The present invention due to using the technology described above, can obtain following technical effect: pass through double vision Image Acquisition mould
Wide-angle lens module in block acquires the image information in larger range, by image transmitting to License Plate detection module, license plate
License plate position in the picture and size information are transmitted to holder module by detection and localization module, and holder module is by adjusting bowing
Face upward the position of axis Yu roll axis, control telephoto lens submodule acquisition clearly license plate image, by collected license plate image into
The correction of row affine transformation and clarity recovery operation, and identify the data information in the license plate.By aforesaid operations, so that long distance
License plate image discrimination from scanning gets a promotion.In addition, the present invention also proposes a kind of double vision image capture module, double vision image
Acquisition module uses a telephoto lens, and the dual camera design of a wide-angle lens, wherein wide-angle camera visual angle is 120
Degree, telephoto lens visual angle, which is 20 degree, can collect clear license plate image in range farther out.Which can be adapted for difference
The Car license recognition of angle, distance.
Detailed description of the invention
Fig. 1 is a kind of terminal block diagram of remote Car license recognition;
Fig. 2 is License Plate Character Segmentation flow chart;
Fig. 3 is a kind of method program flow chart of remote Car license recognition.
Specific embodiment
The present invention is described in further detail in the following with reference to the drawings and specific embodiments: doing as example to the application
Further description explanation.
Referring to Fig.1, a kind of terminal of remote Car license recognition includes double vision image capture module, command process module, cloud
Platform module, wherein double vision image capture module includes wide-angle lens module, using wide-angle lens for acquiring large range of figure
As information;Telephoto lens module, using varifocal telephoto lens for acquiring longer-distance image information.Holder module
It include: roll roller module and pitch axis submodule, holder module receives the holder position that described instruction processing module issues
Adjustment instruction, adjustment roll axis and pitching shaft position, double vision image capture module are mounted in holder module.The pitch axis of holder
Adjustment with roll axis will drive the movement of telephoto lens module.
Referring to Fig. 2, Fig. 2 is License Plate Character Segmentation flow chart.
After the positioning for completing license plate area, then license plate area is divided into single character, then identified.Character segmentation
Generally use vertical projection method.Since the inevitable gap location in intercharacter or character of the projection of character in vertical direction obtains
Near local minimum, and this position should meet licence plate character writing format, character, size limitation and it is some other
Condition.There is preferable effect to the Character segmentation in the automobile image under complex environment using vertical projection method.It promulgates within 2007
China's license plate specification (common small and medium-sized car) provide license plate overall length 440mm, the practical overall length of 7 characters in licence plate is
409mm or so, wide 140mm, each character 45mm wide, 90mm high, character pitch 10mm, wherein second character and third
The spacing of character is more special, is 15.5mm, last character and first character away from boundary 25mm.According to license plate specification,
Characters on license plate is split referring to Fig. 2, the specific steps are as follows:
S101, the license plate image that will acquire carry out binary conversion treatment;
S102 cuts off the extra blank of license plate image, retains main information;
S103 does upright projection calculating to license plate image, since the projection of character in vertical direction is inevitable in intercharacter
Or the gap location in character obtains near local minimum, and this position should meet character writing format, the word of licence plate
Symbol, size limitation and some other conditions.Have using vertical projection method to the Character segmentation in the automobile image under complex environment
Preferable effect.
S104, the image information after traversing upright projection search the accumulative position less than 10 of upright projection white pixel point,
The position is the gap location of two characters;
S105 is split in the accumulative position less than 10 of white pixel;
S107 judges whether the character width of cutting is 45mm, if it is 45mm, for a standard character;
Image remaining under cutting is substituted for former license plate image by S108;
S109, judges whether the number of characters under cutting is equal to 7, if being equal to 7, divides completion, divides not equal to 7
Failure obtains next license plate image, is split.
It is a kind of method detailed process figure for remote Car license recognition that the application proposes, in this example referring to Fig. 3
In can be compatible with the scene of multi-angle, short distance and remote Car license recognition, the specific implementation steps are as follows:
S801 starts the remote Vehicle License Plate Recognition System of binocular;
S802, after system starting will link order processing module, command process module to double vision image capture module and
Holder module assigns self-checking command, and connection successful connection instruction is sent after self-test;
S803 judges whether to receive successful connection instruction.If successful connection system will connect image collection module, if
It connects unsuccessful by repetition S802 step;
S804, system will connect license plate image and obtain module, prepare to obtain the first image;
S805 judges whether to be successfully connected image collection module, if it fails to connect, program will repeat S804 step;
S806, system obtain the image information in larger range by wide-angle lens submodule;
First image transmitting to License Plate detection module, License Plate detection module are detected the first figure by S807, system
As in whether position and size comprising license plate and license plate;To the license plate position detection in image, scheme is first
A wide range of relevant search is carried out to collected video image, finds several regions for meeting license plate feature as candidate
Then area is further analyzed these candidate regions, judges, finally select an optimal region as license plate area, and
It is split from image.By above step, licence plate is generally possible to be positioned.
S808 judges whether there is license plate in the first image, if program will repeat S806 step without license plate, obtains again
Take the first image;If there is license plate is then by image transmitting to image pre-processing module;
S809, image pre-processing module, pretreatment are an important links during Car license recognition, input picture due to
The difference of image capture environment, such as the superiority and inferiority of illumination bright-dark degree and equipment performance, often there are noises, and contrast is not
The disadvantages of enough, in order to guarantee picture quality, it is necessary to be pre-processed to image.Identification is carried out to QR code to need using acquisition equipment
The image of acquisition, but in the collection process of image due to by various factors (as uneven illumination is even, shooting angle, fold)
It influences, may cause image background has various noises, and there may be geometric distortions or image shade for the image received, thus
Cause recognizing apparatus to be difficult to distinguish, bring sizable difficulty to decoding, due to the optics or electricity of CMOS or CCD camera spy
Property, noise is inevitably collected in image acquisition process, these noises are generally salt-pepper noise or speckle noise,
Before the further operatings such as binaryzation, need to remove noise.Common filtering method is divided into linear filtering and nonlinear filtering.
Linear filtering refers to be converted using gray value of certain transformation relation to pixel each in image, the calculating of linear operator
Mode is different, and the algorithm of linear filtering is also just different, and median filtering is by pixel to be processed and small centered on it
The gray value of pixel in window is arranged according to size, and median is taken to replace needing to handle the gray value of pixel.
Can S810, judgement identify license plate, if license board information can be identified, scan success, the end of the program;If
It cannot identify license plate, then license plate position and size information are sent to command process module;
S811, command process module receive license plate position and size information, adjust the roll axis and pitching axle position of holder
It sets.And location information is transferred to holder module, the telephoto lens on holder will acquire a clearly license plate image, transmission
It is identified to Car license recognition device is known, repeats S809 step.
S813, License Plate Character Segmentation module come out the Character segmentation in licence plate using vertical projection method;
S184, Recognition of License Plate Characters module, using template matching algorithm is based on, first by the character binaryzation after segmentation,
And its size is scaled to the size of template in character database, it is then matched, is finally selected most with all templates
Good matching is as a result, finally form license number.
It is exactly that picture pick-up device is used to obtain license plate image information that remote Vehicle License Plate Recognition System, which designs primary problem, examines side
Whether license plate is had, it is necessary to the movement of license plate be correctly detected.Target is extracted from monitored background, this is one
Basic and crucial step.Common Mobile object detection method has powerful connections, and (framing compares for differential technique, image frame differential method
Front and back variation) and based on three kinds of methods such as Block- matchings (sub-module detects picture breakdown).The scene of this system and camera position
Fixation is set, is static background;When Image Acquisition, target position is also relatively fixed, and distracter is fewer, so using the simplest
Practical background differential technique.
The preferable specific embodiment of the above, only the invention, but the protection scope of the invention is not
It is confined to this, anyone skilled in the art is in the technical scope that the invention discloses, according to the present invention
The technical solution of creation and its inventive concept are subject to equivalent substitution or change, should all cover the invention protection scope it
It is interior.
Claims (9)
1. a kind of terminal of remote Car license recognition characterized by comprising
Double vision image capture module, for acquiring license plate image information;
Command process module, for generating the instruction of adjustment holder position;
Holder module, for adjusting holder position according to the holder position command.
2. a kind of terminal of remote Car license recognition according to claim 1, which is characterized in that the double vision Image Acquisition mould
Block includes:
Wide-angle lens module: using wide-angle lens, the license plate image information for being 120 degree for acquiring the visual field;
Telephoto lens module: varifocal telephoto lens is used, for acquiring the license plate image information within the scope of two meters.
3. a kind of terminal of remote Car license recognition according to claim 1, which is characterized in that described instruction processing module connects
After receiving holder location information, the instruction of adjustment holder position is generated, instruction is issued to holder module.
4. a kind of terminal of remote Car license recognition according to claim 1, which is characterized in that the holder module includes:
Roll roller module and pitch axis submodule, after receiving the holder position adjustment instruction that described instruction processing module issues, roll
Roller module adjusts roll shaft position, and pitch axis submodule adjusts pitching shaft position.
5. a kind of system of remote Car license recognition characterized by comprising
License plate image obtains module, for receiving the license plate image information of double vision image capture module acquisition, wide-angle lens module
The image of acquisition is the first image, and the image of telephoto lens module acquisition is the second image;
Image pre-processing module, for carrying out clarity recovery processing to the second image information, acquisition image is third image;
License Plate detection module, for whether detecting in the first image comprising license plate and license plate position and size information,
License plate position and size information are issued to command process module;
License Plate Character Segmentation module, for being mutual independent character by the Character segmentation on license plate;
Recognition of License Plate Characters module identifies the data of the license plate for being scanned to the license plate image in third image information
Information.
6. a kind of system of remote Car license recognition according to claim 5, which is characterized in that described image preprocessing module
For carrying out median filter process to the license plate picture, restore image irradiation, fold, contrast.
7. a kind of system of remote Car license recognition according to claim 5, which is characterized in that the License Plate Character Segmentation
The automotive license plate that module is used to will acquire is cut by kinds of characters.
8. a kind of method of remote Car license recognition, which is characterized in that the wide-angle lens module of double vision image capture module will be schemed
Module is obtained as being transmitted to license plate image, license plate image obtains module and obtains the first image, the first image transmitting to license plate is determined
Position detection module, License Plate detection module detect license plate position and size information, and position and size information are issued to finger
Processing module is enabled, command process module generates the instruction of adjustment holder position, and instruction is transmitted to holder module, holder module
Telephoto lens module is adjusted to designated position, telephoto lens module captures license plate image information, and license plate image is transmitted to
License plate image obtains module, and license plate image obtains module and obtains the second image, by the second image transmitting to image pre-processing module,
Second image is subjected to median filter process, restores image irradiation, fold, contrast, image adjusted is third image, will
Third image transmitting will be transmitted to Recognition of License Plate Characters after the license plate image information correction after segmentation to License Plate Character Segmentation module
Module identifies the license plate image information after segmentation.
9. a kind of method of remote Car license recognition according to claim 8, which is characterized in that License Plate Character Segmentation module,
First to the license plate binary of input, threshold value is obtained using maximum variance between clusters, first sets the minimum widith of each character, most
Big width and Minimum Area;The vertical divider of character is located at the intermediate region of character and character, intermediate region row accumulated value
It is smaller than the row accumulated value on character, therefore from the bottom of to upper scanning, cutting region is recursively found, recurrence meets the following conditions: (1) every
The cutting width of a character is between the minimum widith and maximum width of setting;It (2), should when cutting region is greater than maximum width
Region may contain multiple characters, continue cutting to the region until meeting condition (1);(3) when cutting region is less than minimum
When width, it was demonstrated that any character is not present in the region, and cutting is invalid, removes the cut point;(4) if the cutting region got
Greater than 7 regions then select maximum 7 output from the cutting region for being greater than Minimum Area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910164057.8A CN109948618A (en) | 2019-03-05 | 2019-03-05 | A kind of terminal, the system and method for remote Car license recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910164057.8A CN109948618A (en) | 2019-03-05 | 2019-03-05 | A kind of terminal, the system and method for remote Car license recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109948618A true CN109948618A (en) | 2019-06-28 |
Family
ID=67008469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910164057.8A Pending CN109948618A (en) | 2019-03-05 | 2019-03-05 | A kind of terminal, the system and method for remote Car license recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109948618A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110533737A (en) * | 2019-08-19 | 2019-12-03 | 大连民族大学 | The method generated based on structure guidance Chinese character style |
CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
CN112950950A (en) * | 2021-01-26 | 2021-06-11 | 上海启迪睿视智能科技有限公司 | Parking auxiliary device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0850696A (en) * | 1994-08-05 | 1996-02-20 | Nippondenso Co Ltd | Number recognition device for running vehicle |
CN101547344A (en) * | 2009-04-24 | 2009-09-30 | 清华大学深圳研究生院 | Video monitoring device and tracking and recording method based on linkage camera |
CN103177582A (en) * | 2013-04-22 | 2013-06-26 | 杜东 | All-in-one machine with video velocity measurement and vehicle license plate recognition |
-
2019
- 2019-03-05 CN CN201910164057.8A patent/CN109948618A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0850696A (en) * | 1994-08-05 | 1996-02-20 | Nippondenso Co Ltd | Number recognition device for running vehicle |
CN101547344A (en) * | 2009-04-24 | 2009-09-30 | 清华大学深圳研究生院 | Video monitoring device and tracking and recording method based on linkage camera |
CN103177582A (en) * | 2013-04-22 | 2013-06-26 | 杜东 | All-in-one machine with video velocity measurement and vehicle license plate recognition |
Non-Patent Citations (1)
Title |
---|
MINGO_敏: "车牌识别算法实现及其代码实现之二:字符分割", 《HTTP://BLOG.CSDN.NET/SHANGLIANLM/ARTICLE/DETAILS/78045170》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110533737A (en) * | 2019-08-19 | 2019-12-03 | 大连民族大学 | The method generated based on structure guidance Chinese character style |
CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
CN112950950A (en) * | 2021-01-26 | 2021-06-11 | 上海启迪睿视智能科技有限公司 | Parking auxiliary device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110705405B (en) | Target labeling method and device | |
CN101510258B (en) | Certificate verification method, system and certificate verification terminal | |
CN109341580B (en) | Method, system and device for tracking rail profile | |
CN109948618A (en) | A kind of terminal, the system and method for remote Car license recognition | |
US20130279758A1 (en) | Method and system for robust tilt adjustment and cropping of license plate images | |
CN102842034B (en) | A kind of laser scanning and the device and the recognition methods that automatically identify engraving character | |
CN109447067B (en) | Bill direction detection and correction method and automatic bill checking system | |
CN105067633A (en) | Vehicle-mounted type automatic pavement damage recognition device based on image processing and application method | |
CN108982512A (en) | A kind of circuit board detecting system and method based on machine vision | |
CN108198417B (en) | A kind of road cruising inspection system based on unmanned plane | |
CN104751097A (en) | Vehicle identification code detection processing method and device | |
CN104361314A (en) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion | |
CN110334625A (en) | A kind of parking stall visual identifying system and its recognition methods towards automatic parking | |
CN103093229B (en) | Car is demarcated method for position and device | |
CN110008771B (en) | Code scanning system and code scanning method | |
CN106803087A (en) | A kind of car number automatic identification method and system | |
CN107358236A (en) | A kind of number-plate number identifying system and method based on camera device | |
CN104715250B (en) | cross laser detection method and device | |
CN110084171B (en) | Detection device and detection method for foreign matters on top of subway train | |
CN113673614B (en) | Metro tunnel foreign matter intrusion detection device and method based on machine vision | |
CN114898353A (en) | License plate identification method based on video sequence image characteristics and information | |
CN111046741A (en) | Method and device for identifying lane line | |
WO2022121021A1 (en) | Identity card number detection method and apparatus, and readable storage medium and terminal | |
CN113591643A (en) | Underground vehicle station entering and exiting detection system and method based on computer vision | |
CN106340031A (en) | Method and device for detecting moving object |
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 |
Application publication date: 20190628 |
|
RJ01 | Rejection of invention patent application after publication |