CN108734113A - Vehicle automatic marking method, storage medium, electronic equipment, system - Google Patents
Vehicle automatic marking method, storage medium, electronic equipment, system Download PDFInfo
- Publication number
- CN108734113A CN108734113A CN201810391480.7A CN201810391480A CN108734113A CN 108734113 A CN108734113 A CN 108734113A CN 201810391480 A CN201810391480 A CN 201810391480A CN 108734113 A CN108734113 A CN 108734113A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- feature
- rectangular area
- contour
- module
- 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.)
- Withdrawn
Links
Classifications
-
- 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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides vehicle automatic marking method, including region acquisition, the judgement of profile automatic Picking, profile, region adjustment, region division, feature mark.The invention further relates to storage medium, electronic equipment, vehicle automatic marking systems.The present invention is automatically adjusted area size using computer graphics disposal technology, it realizes vehicle characteristics accurate in image and effectively marks, it effectively reduces the workload manually marked and marks requirement, and then realize the self registering automation of parking lot unattended, traffic accident treatment, escaping behavior after traffic accident, vehicles peccancy and informationization.The present invention is highly practical, is promoted convenient for vehicle identification field.
Description
Technical field
The present invention relates to vehicle mark more particularly to vehicle automatic marking method, storage medium, electronic equipment, systems.
Background technology
With the development of intelligent monitoring technology, the development and application of vehicle automatic marking system is more extensive.Vehicle is marked automatically
Injection system is the important branch of intelligent transportation, it needs the correlations such as artificial intelligence, image procossing, computer vision, pattern-recognition
The integrated application of technology.Vehicle recongnition technique domestic at present is increasingly mature, continuous with intelligent transport technology application
Deepen, the more polynary information of vehicles of the highly desirable extraction of industrial quarters, in addition to the number-plate number, it is also necessary to the brand of vehicle, model with
And the information characteristics such as color.These features are in parking lot unattended, traffic accident treatment, escaping behavior after traffic accident, vehicles peccancy
Automatically recording equal fields has an extensive and urgent application demand, but more information characteristics mean a greater amount of operations with than
Right, according to traditional method for comparing analysis one by one, operand is huge and unwanted picture information is excessive, is badly in need of a kind of more efficient
Method assists vehicle identification.
Invention content
For overcome the deficiencies in the prior art, the purpose of the present invention is to provide vehicle automatic marking methods, using calculating
Machine graph processing technique is automatically adjusted area size, realizes vehicle characteristics accurate in image and effectively marks, has
Effect reduces the workload manually marked and is required with mark, and then realizes that parking lot unattended, traffic accident treatment, traffic are started
Thing escape, the self registering automation of vehicles peccancy and informationization.
The present invention provides vehicle automatic marking method, includes the following steps:
Region obtains, and obtains the rough regional extent of vehicle of image domestic demand mark, obtains the first rectangular area;
Profile automatic Picking obtains the vehicle's contour for the need mark included in first rectangular area, obtains the first vehicle
Profile;
Profile judges whether first vehicle's contour exceeds first rectangular area;
Region adjusts, if first vehicle's contour exceeds first rectangular area, expands first rectangle region
Domain;If first vehicle's contour reduces first rectangular area without departing from first rectangular area;
Region division, by face image, vehicle tail image before vehicle respectively to the characteristic attribute of first vehicle's contour
It is special to obtain corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, car light for segmentation
Sign;
Feature marks, and the characteristic attribute of face image or vehicle tail image before same vehicle is associated mark.
Further, the region adjustment obtains institute specifically using the pixel collection for traversing first vehicle's contour
Longitudinal extreme value with transverse direction in pixel collection is stated, minimum area-encasing rectangle range is established with the extreme value, and cover described first
Rectangular area be adjusted after the first rectangular area.
Further, the region adjustment is specifically each using acquisition first vehicle's contour and first rectangular area
Boundary exceeds relationship, if first vehicle's contour exceeds the boundary of first rectangular area, first rectangle region
The boundary in domain Moving Unit pixel to outside first rectangular area;If first vehicle's contour is without departing from first rectangle
The boundary in region, the then boundary of first rectangular area Moving Unit pixel into first rectangular area.
Further, the region division specifically use SVM classifier to the characteristic attribute of first vehicle's contour into
Row segmentation, obtains vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, car light feature.
Further, further include step color mark, count the RGB component of each pixel in first vehicle's contour,
The combination of the highest RGB component of the frequency of occurrences is obtained, and marks the color of vehicle with the corresponding color designation of the combination.
A kind of electronic equipment, including:Processor;
Memory;And program, wherein described program is stored in the memory, and is configured to by processor
It executes, described program includes for executing vehicle automatic marking method.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Driving automatic marking method.
Module, profile extraction module, profile determination module, region adjustment are chosen in vehicle automatic marking system, including region
Module, region division module, feature labeling module;Wherein,
Module is chosen in the region, selects the approximate range of the vehicle of required mark in image for frame and obtains the first rectangle
Region;
The profile extraction module, for extract included in first rectangular area need mark vehicle's contour and
To the first vehicle's contour;
Whether the profile determination module exceeds first rectangular area for first vehicle's contour;
The region adjusts module, for expanding or shrinking first rectangle according to the result of the profile determination module
Region;
The region division module, for face image, vehicle tail image before vehicle respectively to first vehicle's contour
Characteristic attribute segmentation, it is special to obtain corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet
Sign, car light feature;
The feature labeling module, before the same vehicle for being divided according to the region division module face image or
The characteristic attribute of vehicle tail image is associated mark.
Further, further include characteristic module library, the feature labeling module is divided according to the region division module
To same vehicle before the characteristic attribute of face image or vehicle tail image degree of approximation matching is carried out in the characteristic module library,
And the highest feature of the degree of approximation in the characteristic module library is labeled as characteristic attribute.
Further, further include color labeling module, the color labeling module is for counting first vehicle's contour
The RGB component of interior each pixel obtains the combination of the highest RGB component of the frequency of occurrences, and with the corresponding color name of the combination
Claim the color of mark vehicle.
Compared with prior art, the beneficial effects of the present invention are:
The present invention provides vehicle automatic marking method, including region acquisition, the judgement of profile automatic Picking, profile, region tune
Whole, region division, feature mark.The invention further relates to storage medium, electronic equipment, vehicle automatic marking systems.The present invention adopts
Area size is automatically adjusted with computer graphics disposal technology, vehicle characteristics accurate in image is realized and effectively marks
Note effectively reduces the workload that manually marks and is required with mark, so realize parking lot unattended, traffic accident treatment,
The self registering automation of escaping behavior after traffic accident, vehicles peccancy and informationization.The present invention is highly practical, is convenient for vehicle identification field
It promotes.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, below with presently preferred embodiments of the present invention and after coordinating attached drawing to be described in detail such as.
The specific implementation mode of the present invention is shown in detail by following embodiment and its attached drawing.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings:
Fig. 1 is the vehicle automatic marking method flow diagram of the present invention;
Fig. 2 is the vehicle automatic marking system circuit theory schematic diagram of the present invention.
Specific implementation mode
In the following, in conjunction with attached drawing and specific implementation mode, the present invention is described further, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
Vehicle automatic marking method, as shown in Figure 1, including the following steps:
Region obtains, and obtains the rough regional extent of vehicle of image domestic demand mark, obtains the first rectangular area;Specifically
Ground, because information is more in image, it is understood that there may be block or other complaint messages, be improved annotating efficiency, artificial hand can be used
Dynamic frame selects rough regional extent, the vehicle of selected digital image domestic demand mark;It should be appreciated that automatic frame choosing can also be used, pass through ash
Subregion is carried out after degree processing, intersection builds regional extent in region.
Profile automatic Picking obtains the vehicle's contour for the need mark included in the first rectangular area, obtains the first vehicle wheel
It is wide;In one embodiment, for the vehicle's contour included in the first rectangular area there are two kinds of situations, one is the complete position of vehicle's contour
In in the first rectangular area, secondly being located in the first rectangular area for vehicle's contour part;For the first situation, using gray scale
The inflection point pixel of processing extraction grey scale change, it is the first vehicle's contour to be sequentially connected inflection point pixel;For the second situation, portion
The inflection point pixel for dividing the vehicle's contour being located in the first rectangular area first to use gray proces extraction grey scale change, then again to portion
The vehicle's contour divided carries out extension gray proces, wherein extends gray proces and can be used to the extending direction of profile translation one
First rectangular area, then gray proces are carried out to the image in the first rectangular area of translation, it is sequentially connected adjacent two first squares
Vehicle's contour in shape region obtains the first vehicle's contour.
Profile judges, compares whether the first vehicle's contour exceeds the first rectangular area;Because selection or automatic frame are selected as manually
Preliminary to choose, the first rectangular area range is inaccurate, and usually, error will not be very big, substantially in 2-10 pixel point range,
Accurately to mark vehicle, need to be adjusted the first rectangular area.Wherein, judge whether the first vehicle's contour exceeds the first square
Shape region, using region criterion:Whether the transverse and longitudinal coordinate of the pixel on the first vehicle's contour is less than the side of the first rectangular area
Bound function, if being less than, pixel is located inside the first rectangular area;If being equal to, pixel is located at the first rectangular area
On boundary;If more than then pixel is located at outside the first rectangular area.
Region adjusts, if the first vehicle's contour exceeds the first rectangular area, expands the first rectangular area;If the first vehicle
Profile then reduces the first rectangular area without departing from the first rectangular area;Specifically, the pixel of the first vehicle's contour of traversal can be used
Point set obtains longitudinal extreme value with transverse direction in pixel collection, establishes minimum area-encasing rectangle range with extreme value, and cover first
Rectangular area be adjusted after the first rectangular area;Or using obtaining the first vehicle's contour and each boundary in the first rectangular area
Beyond relationship, if the first vehicle's contour exceeds the boundary of the first rectangular area, the boundary of the first rectangular area is to the first rectangle
Moving Unit pixel outside region;If the first vehicle's contour is without departing from the boundary of the first rectangular area, the side of the first rectangular area
Boundary's Moving Unit pixel into the first rectangular area.
Region division respectively divides the characteristic attribute of the first vehicle's contour by face image, vehicle tail image before vehicle,
Obtain corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, car light feature;Specifically
Ground is split using the characteristic attribute of the first vehicle's contour of SVM classifier pair, and it is special to obtain vehicles identifications feature, vehicle license
Sign, vehicle model feature, vehicle air inlet feature, car light feature.
Feature marks, and the characteristic attribute of face image or vehicle tail image before same vehicle is associated mark.According to
The shooting vehicle angles of Image Acquisition are different, and there are front image, tail portion image, side images, usually, side image information
It measures very few, does not charge to mark herein, therefore face image before front image, that is, vehicle, tail portion image, that is, vehicle tail image, wherein vehicle
First vehicle's contour of preceding face image includes that vehicles identifications feature, vehicle license feature, vehicle air inlet feature, car light are special
Sign, the first vehicle's contour of vehicle tail image includes vehicles identifications feature, vehicle license feature, vehicle model feature, car light
Whether feature, particularly, the information for same vehicle in comparison different images are legal, before the vehicle that can extract same vehicle respectively
Characteristic attribute in face image, vehicle tail image carries out summarizing association comparison, and is carried out with the vehicle registration information of vehicle administration office
Matching, whether comprehensive descision is legal vehicle.
In one embodiment, further include step color mark (not shown), count each pixel in the first vehicle's contour
RGB component obtains the combination of the highest RGB component of the frequency of occurrences, and to combine the color that corresponding color designation marks vehicle.
A kind of electronic equipment, including:Processor;Memory;And program, Program are stored in memory, and
And be configured to be executed by processor, program includes for executing vehicle automatic marking method;A kind of computer-readable storage medium
Matter, is stored thereon with computer program, and computer program is executed by processor vehicle automatic marking method.
Vehicle automatic marking system, as shown in Fig. 2, choosing module, profile extraction module, profile including region judges mould
Block, region adjustment module, region division module, feature labeling module;Wherein,
Module is chosen in region, selects the approximate range of the vehicle of required mark in image for frame and obtains the first rectangle region
Domain;
Profile extraction module, for extract included in the first rectangular area need mark vehicle's contour and obtain the first vehicle
Profile;
Profile determination module, for comparing whether the first vehicle's contour exceeds the first rectangular area;
Region adjusts module, for expanding or shrinking the first rectangular area according to the result of profile determination module;
Region division module, for face image, vehicle tail image before vehicle respectively to the feature category of the first vehicle's contour
Property segmentation, it is special to obtain corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, car light
Sign;
Feature labeling module, face image or vehicle tail before the same vehicle for being divided according to region division module
The characteristic attribute of image is associated mark.
In one embodiment, as shown in Fig. 2, further including characteristic module library, feature labeling module is according to region division module
The characteristic attribute of face image or vehicle tail image carries out the degree of approximation in characteristic module library before dividing obtained same vehicle
Match, and the highest feature of the degree of approximation in characteristic module library is labeled as characteristic attribute.
In one embodiment, further include color labeling module (not shown), color labeling module is for counting the first vehicle
The RGB component of each pixel in profile obtains the combination of the highest RGB component of the frequency of occurrences, and to combine corresponding color name
Claim the color of mark vehicle.
The present invention provides vehicle automatic marking method, including region acquisition, the judgement of profile automatic Picking, profile, region tune
Whole, region division, feature mark.The invention further relates to storage medium, electronic equipment, vehicle automatic marking systems.The present invention adopts
Area size is automatically adjusted with computer graphics disposal technology, vehicle characteristics accurate in image is realized and effectively marks
Note effectively reduces the workload that manually marks and is required with mark, so realize parking lot unattended, traffic accident treatment,
The self registering automation of escaping behavior after traffic accident, vehicles peccancy and informationization.The present invention is highly practical, is convenient for vehicle identification field
It promotes.
More than, only presently preferred embodiments of the present invention is not intended to limit the present invention in any form;All one's own professions
The those of ordinary skill of industry can be shown in by specification attached drawing and above and swimmingly implement the present invention;But all to be familiar with sheet special
The technical staff of industry without departing from the scope of the present invention, is made a little using disclosed above technology contents
The equivalent variations of variation, modification and evolution are the equivalent embodiment of the present invention;Meanwhile all substantial technologicals according to the present invention
To the variation, modification and evolution etc. of any equivalent variations made by above example, technical scheme of the present invention is still fallen within
Within protection domain.
Claims (10)
1. vehicle automatic marking method, which is characterized in that include the following steps:
Region obtains, and obtains the rough regional extent of vehicle of image domestic demand mark, obtains the first rectangular area;
Profile automatic Picking obtains the vehicle's contour for the need mark included in first rectangular area, obtains the first vehicle wheel
It is wide;
Profile judges whether first vehicle's contour exceeds first rectangular area;
Region adjusts, if first vehicle's contour exceeds first rectangular area, expands first rectangular area;If
First vehicle's contour then reduces first rectangular area without departing from first rectangular area;
Region division respectively divides the characteristic attribute of first vehicle's contour by face image, vehicle tail image before vehicle,
Obtain corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, car light feature;
Feature marks, and the characteristic attribute of face image or vehicle tail image before same vehicle is associated mark.
2. vehicle automatic marking method as described in claim 1, it is characterised in that:The region adjustment is specifically using traversal institute
The pixel collection for stating the first vehicle's contour is obtained longitudinal extreme value with transverse direction in the pixel collection, is built with the extreme value
Vertical minimum area-encasing rectangle range, and cover the first rectangular area after first rectangular area is adjusted.
3. vehicle automatic marking method as described in claim 1, it is characterised in that:The region adjustment is specifically using acquisition institute
That states the first vehicle's contour and each boundary in the first rectangular area exceeds relationship, if first vehicle's contour is beyond described the
The boundary of one rectangular area, the then boundary of first rectangular area Moving Unit pixel to outside first rectangular area;If
First vehicle's contour is without departing from the boundary of first rectangular area, then the boundary of first rectangular area is to described
Moving Unit pixel in one rectangular area.
4. vehicle automatic marking method as described in claim 1, it is characterised in that:The region division is specifically using SVM points
Class device is split the characteristic attribute of first vehicle's contour, obtains vehicles identifications feature, vehicle license feature, vehicle type
Number feature, vehicle air inlet feature, car light feature.
5. vehicle automatic marking method according to any one of claims 1-4, it is characterised in that:It further include step color mark
Note counts the RGB component of each pixel in first vehicle's contour, obtains the combination of the highest RGB component of the frequency of occurrences, and
The color of vehicle is marked with the corresponding color designation of the combination.
6. a kind of electronic equipment, it is characterised in that including:Processor;
Memory;And program, wherein described program is stored in the memory, and is configured to be held by processor
Row, described program include the method required for perform claim described in 1.
7. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that:The computer program quilt
Processor executes the method as described in claim 1.
8. vehicle automatic marking system, it is characterised in that:Including region choose module, profile extraction module, profile determination module,
Region adjusts module, region division module, feature labeling module;Wherein,
Module is chosen in the region, selects the approximate range of the vehicle of required mark in image for frame and obtains the first rectangle region
Domain;
The profile extraction module, vehicle's contour for extracting the need included in first rectangular area mark simultaneously obtain the
One vehicle's contour;
Whether the profile determination module exceeds first rectangular area for first vehicle's contour;
The region adjusts module, for expanding or shrinking first rectangle region according to the result of the profile determination module
Domain;
The region division module, for face image, vehicle tail image before vehicle respectively to the spy of first vehicle's contour
Attribute segmentation is levied, corresponding vehicles identifications feature, vehicle license feature, vehicle model feature, vehicle air inlet feature, vehicle are obtained
Lamp feature;
The feature labeling module, face image or vehicle before the same vehicle for being divided according to the region division module
The characteristic attribute of tail portion image is associated mark.
9. vehicle automatic marking system as claimed in claim 8, it is characterised in that:Further include characteristic module library, the feature
The feature category of face image or vehicle tail image before the same vehicle that labeling module is divided according to the region division module
Property degree of approximation matching is carried out in the characteristic module library, and the highest feature of the degree of approximation in the characteristic module library is labeled as
Characteristic attribute.
10. vehicle automatic marking system as claimed in claim 8, it is characterised in that:Further include color labeling module, the face
Color labeling module is used to count the RGB component of each pixel in first vehicle's contour, obtains highest RGB points of the frequency of occurrences
The combination of amount, and with the color of the corresponding color designation mark vehicle of the combination.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810391480.7A CN108734113A (en) | 2018-04-27 | 2018-04-27 | Vehicle automatic marking method, storage medium, electronic equipment, system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810391480.7A CN108734113A (en) | 2018-04-27 | 2018-04-27 | Vehicle automatic marking method, storage medium, electronic equipment, system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108734113A true CN108734113A (en) | 2018-11-02 |
Family
ID=63939333
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810391480.7A Withdrawn CN108734113A (en) | 2018-04-27 | 2018-04-27 | Vehicle automatic marking method, storage medium, electronic equipment, system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108734113A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110059101A (en) * | 2019-04-16 | 2019-07-26 | 北京科基中意软件开发有限公司 | A kind of vehicle data lookup system and lookup method based on image recognition |
CN110929737A (en) * | 2019-11-12 | 2020-03-27 | 东软睿驰汽车技术(沈阳)有限公司 | Label generation method and device |
CN113326901A (en) * | 2021-06-30 | 2021-08-31 | 北京百度网讯科技有限公司 | Image annotation method and device |
CN113343857A (en) * | 2021-06-09 | 2021-09-03 | 浙江大华技术股份有限公司 | Labeling method, labeling device, storage medium and electronic device |
-
2018
- 2018-04-27 CN CN201810391480.7A patent/CN108734113A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110059101A (en) * | 2019-04-16 | 2019-07-26 | 北京科基中意软件开发有限公司 | A kind of vehicle data lookup system and lookup method based on image recognition |
CN110929737A (en) * | 2019-11-12 | 2020-03-27 | 东软睿驰汽车技术(沈阳)有限公司 | Label generation method and device |
CN113343857A (en) * | 2021-06-09 | 2021-09-03 | 浙江大华技术股份有限公司 | Labeling method, labeling device, storage medium and electronic device |
CN113326901A (en) * | 2021-06-30 | 2021-08-31 | 北京百度网讯科技有限公司 | Image annotation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108734113A (en) | Vehicle automatic marking method, storage medium, electronic equipment, system | |
CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
CN109740548B (en) | Reimbursement bill image segmentation method and system | |
US20200026930A1 (en) | Lane line detection method and apparatus | |
CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
CN103473739B (en) | A kind of Leukocyte Image Accurate Segmentation method and system based on support vector machine | |
CN103971097B (en) | Vehicle license plate recognition method and system based on multiscale stroke models | |
CN107273896A (en) | A kind of car plate detection recognition methods based on image recognition | |
CN103824081B (en) | Method for detecting rapid robustness traffic signs on outdoor bad illumination condition | |
CN106650553A (en) | License plate recognition method and system | |
CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
CN104732227A (en) | Rapid license-plate positioning method based on definition and luminance evaluation | |
CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
CN105184291B (en) | A kind of polymorphic type detection method of license plate and system | |
CN103020970A (en) | Corn ear image grain segmentation method | |
CN110674812B (en) | Civil license plate positioning and character segmentation method facing complex background | |
Azad et al. | New method for optimization of license plate recognition system with use of edge detection and connected component | |
Shaikh et al. | A novel approach for automatic number plate recognition | |
CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
CN107992810B (en) | Vehicle identification method and device, electronic equipment and storage medium | |
CN104766344A (en) | Vehicle detecting method based on moving edge extractor | |
CN104866838B (en) | A kind of front vehicles automatic testing method of view-based access control model | |
Wei et al. | Detection of lane line based on Robert operator | |
CN106778777B (en) | Vehicle matching method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181102 |