CN107808519A - A kind of multiple features vehicle match method - Google Patents
A kind of multiple features vehicle match method Download PDFInfo
- Publication number
- CN107808519A CN107808519A CN201610726671.5A CN201610726671A CN107808519A CN 107808519 A CN107808519 A CN 107808519A CN 201610726671 A CN201610726671 A CN 201610726671A CN 107808519 A CN107808519 A CN 107808519A
- Authority
- CN
- China
- Prior art keywords
- identification
- vehicle
- multiple features
- vehicle match
- match method
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Image Analysis (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention discloses a kind of multiple features vehicle match method, comprise the following steps：Obtain the image information of vehicle；Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；Weight distribution is carried out to characteristic information in feature database and standards of grading are formulated according to weight；Vehicle image information is obtained again and extracts the multiple characteristic informations of identification；The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；Vehicle match success or not is judged according to appraisal result；Divide mechanism equally using multiple features, various dimensions, solve the problems, such as matching error, substantially increase the accuracy of timing, charging.
Description
Technical field
The present invention relates to vehicle recongnition technique field, more particularly to a kind of multiple features vehicle match method.
Background technology
With the development of modernization, increasing automobile is currently being used.At present in vehicle toll management system, meeting
There is the situation of wrong charging, i.e. appearance vehicle without entrance vehicle is correctly matched, occur the reason for such situation mainly by
Caused by outlet or entrance Car license recognition mistake.
The content of the invention
In view of the above-mentioned deficiency that presently, there are, the present invention provides a kind of multiple features vehicle match method, efficiently solves
The problem of matching error, substantially increase the accuracy of timing, charging.
To reach above-mentioned purpose, embodiments of the invention adopt the following technical scheme that：
A kind of multiple features vehicle match method, the multiple features vehicle match method comprise the following steps：
Obtain the image information of vehicle；
Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；
Weight distribution is carried out to characteristic information in feature database and standards of grading are formulated according to weight；
Vehicle image information is obtained again and extracts the multiple characteristic informations of identification；
The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；
Vehicle match success or not is judged according to appraisal result.
According to one aspect of the present invention, the identification feature information includes：The identification of the number-plate number, the identification of logo,
The identification of vehicle and the identification of body color.
According to one aspect of the present invention, the identification of the number-plate number includes：Pass through the pattern-recognition skill of neutral net
The template matching technique of art, depth Network Recognition technology and incomplete character is identified respectively, and comprehensive matching draws most probable
Recognition result.
According to one aspect of the present invention, the identification of the logo includes：Car is identified using the identification technology of sparse theory
Brand, the vehicles identifications of the vehicle production time limit etc.
According to one aspect of the present invention, the vehicle includes：Truck, buggy, motor bus, car and medium-sized visitor
Car.
According to one aspect of the present invention, the identification of the body color includes eight major classes separated roughly：It is black, white
Color, red, navy blue, silver gray, silvery white, orange, purple.
According to one aspect of the present invention, the multiple features vehicle match method includes obtaining the headstock part figure of vehicle
Picture, acquisition process are to be absorbed by camera.
It is described that weight distribution is carried out to characteristic information in feature database and is formulated according to weight according to one aspect of the present invention
Standards of grading include：Weight is distributed according to the difficulty or ease of characteristic information identification, so as to formulate standards of grading according to weight.
It is described to include according to the difficulty or ease of identification to distribute weight according to one aspect of the present invention：Easily identify, account for
Weight is high；It is difficult to, the weight accounted for is low.
According to one aspect of the present invention, the multiple features vehicle match method includes：Point threshold is preset, to sentence
Whether is disconnected vehicle match.
The advantages of present invention is implemented：Multiple features vehicle match method of the present invention, comprises the following steps：Obtain vehicle
Image information；Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；To feature in feature database
Information carries out weight distribution and formulates standards of grading according to weight；Vehicle image information is obtained again and extracts the multiple features of identification
Information；The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；Judged according to appraisal result
Vehicle match success or not；Divide mechanism equally using multiple features, various dimensions, solve the problems, such as matching error, greatly improve
Timing, the accuracy of charging.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it will use below required in embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of multiple features vehicle match method schematic diagram of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
As shown in figure 1, a kind of multiple features vehicle match method, the multiple features vehicle match method comprises the following steps：
Step S1：Obtain the image information of vehicle；
The embodiment that the step S1 obtains the image information of vehicle can be：Obtain the headstock part figure of vehicle
Picture, acquisition process are to be absorbed by camera.For example, being equipped with camera at the entrance and exit in parking lot, camera is clapped
Take the photograph the vehicle head part image into parking lot or the vehicle for leaving parking lot.
Step S2：Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；
The step S2, which is identified according to the image information of acquisition and extracted multiple characteristic informations and establish feature database, to be included：Car plate
The identification of number, the identification of logo, the identification of vehicle and the identification of body color.
The number-plate number is most important feature, so system is the preferential identification number-plate number, 7 characters are as main
With foundation.The number-plate number is identified respectively using three sets of different types of recognizers, and three sets of algorithms are respectively：Neutral net
Mode identification technology, depth Network Recognition technology, the template matching technique of incomplete character, the result of three sets of algorithm identifications integrate again
Fusion, finally gives a most probable recognition result.
The method specifically merged, by taking Chinese character as an example, what it is if the identification of two results is " Shanghai ", and identification is
" Shandong ", then final result just selects in " Shanghai ".
In actual applications, if three results are variant, using the result of depth recognition, because after tested, depth
The result of identification is best.
The identification of logo uses the identification technology of sparse theory, identifies brand, the vehicle production time limit, the sub-brand name of vehicle
Deng the logo of certain car is can recognize that in the present embodiment is：BMW, a system, 2013 sections etc..
Vehicle is always divided into：5 kinds of vehicles such as truck, buggy, motor bus, car, middle bus.
The identification of body color can only separate eight major classes roughly:That is black, white, red, navy blue, silver gray, silvery white
Color, orange, purple.
In actual applications, image acquisition and feature recognition are carried out for entering the vehicle in parking lot, and by the spy of identification
In reference breath deposit feature database.
Step S3：Weight distribution is carried out to characteristic information in feature database and standards of grading are formulated according to weight；
The step S3 carries out weight distribution to characteristic information in feature database and formulates the specific of standards of grading according to weight
Embodiment can be：Weight is distributed according to the difficulty or ease of identification, such as, it is not easy to the general character obscured, weight are higher；Hold
Confusing weight, it is lower；Further feature also distributes weight according to the difficulty or ease of identification.
In actual applications, it may include following embodiment：
1st, ordinary numbers and character are denoted as 2 points, such as：2nd, 3,4,6,7,9,0, A, C, etc.；
2nd, the first character of characters on license plate is Chinese character, and discrimination compares almost, is uniformly denoted as 1 point；
3rd, hold confusing character and be denoted as 1 point：Such as " B " and " 8 ", " 0 " and " D ", " 5 " and " S ", " 1 " and " L "；
4th, the recognition accuracy of logo is higher, so logo is all denoted as 2 points.
5th, vehicle only has several, and by contrast, feature is weaker, is only denoted as 1 point.
6th, body color is only denoted as 1 point.
Step S4：Vehicle image information is obtained again and extracts the multiple characteristic informations of identification；
The step S4 obtains vehicle image information and extracted again identifies that the embodiment of multiple characteristic informations can
For：The vehicle left for exit, shot by camera and obtain its vehicle head part image, pass through the figure to acquisition
Identification and acquisition as carrying out multiple features according to step S2.
Step S5：The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；
The tool that the step S5 feature baseds storehouse is scored the multiple characteristic informations extracted again according to standards of grading
Body embodiment can be：Characteristic information in characteristic information and feature database that step S4 is obtained carries out matching and compared, and according to
Standards of grading obtain scoring when comparing matching.
In actual applications, it may include following embodiment：
Feature recognition when such as certain car entrance is as follows：Anhui B7K14D, Cherry A3, blueness, minibus；
Feature recognition when outlet is as follows：Anhui BFKL4D, Cherry A3, silver gray, minibus；
Point system more than is scored, such as following table：
Step S6：Vehicle match success or not is judged according to appraisal result.
The step S6 judges that the embodiment of vehicle match success or not can be according to appraisal result：Preset
Point threshold, whether to judge vehicle match.
In actual applications, the fractional value that can be set according to user, it is determined whether meet the condition opened a sluice gate automatically, Huo Zheman
The condition charged enough.Such as：It can be opened a sluice gate automatically more than or equal to 12 points, less than 12 points, then whether pop-up window, artificial dry with opening
Lock.
The advantages of present invention is implemented：Multiple features vehicle match method of the present invention, comprises the following steps：Obtain vehicle
Image information；Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；To feature in feature database
Information carries out weight distribution and formulates standards of grading according to weight；Vehicle image information is obtained again and extracts the multiple features of identification
Information；The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；Judged according to appraisal result
Vehicle match success or not；Divide mechanism equally using multiple features, various dimensions, solve the problems, such as matching error, greatly improve
Timing, the accuracy of charging.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those skilled in the art is in technical scope disclosed by the invention, the change or replacement that can readily occur in, all should
It is included within the scope of the present invention.Therefore, protection scope of the present invention should using the scope of the claims as
It is accurate.
Claims (10)
- A kind of 1. multiple features vehicle match method, it is characterised in that the multiple features vehicle match method comprises the following steps：Obtain the image information of vehicle；Identified according to the image information of acquisition and extract multiple characteristic informations and establish feature database；Weight distribution is carried out to characteristic information in feature database and standards of grading are formulated according to weight；Vehicle image information is obtained again and extracts the multiple characteristic informations of identification；The multiple characteristic informations extracted again are scored according to standards of grading in feature based storehouse；Vehicle match success or not is judged according to appraisal result.
- 2. multiple features vehicle match method according to claim 1, it is characterised in that the identification feature information includes： The identification of the number-plate number, the identification of logo, the identification of vehicle and the identification of body color.
- 3. multiple features vehicle match method according to claim 2, it is characterised in that the identification bag of the number-plate number Include：Entered respectively by the template matching technique of the mode identification technology of neutral net, depth Network Recognition technology and incomplete character Row identification, and comprehensive matching draws most probable recognition result.
- 4. multiple features vehicle match method according to claim 2, it is characterised in that the identification of the logo includes：Adopt The vehicles identifications of the brand of vehicle, the vehicle production time limit etc are identified with the identification technology of sparse theory.
- 5. multiple features vehicle match method according to claim 2, it is characterised in that the vehicle includes：It is truck, small Lorry, motor bus, car and middle bus.
- 6. multiple features vehicle match method according to claim 2, it is characterised in that the identification of the body color includes Eight major classes separated roughly：Black, white, red, navy blue, silver gray, silvery white, orange, purple.
- 7. multiple features vehicle match method according to claim 1, it is characterised in that the multiple features vehicle match method Headstock part image including obtaining vehicle, acquisition process are to be absorbed by camera.
- 8. the multiple features vehicle match method according to one of claim 1 to 7, it is characterised in that described in feature database Characteristic information carries out weight distribution and included according to weight formulation standards of grading：According to the difficulty or ease of characteristic information identification come the power of distributing Weight, so as to formulate standards of grading according to weight.
- 9. multiple features vehicle match method according to claim 8, it is characterised in that the difficulty or ease according to identification are divided Include with weight：Easily identify, the weight accounted for is high；It is difficult to, the weight accounted for is low.
- 10. multiple features vehicle match method according to claim 8, it is characterised in that the multiple features vehicle match side Method includes：Point threshold is preset, whether to judge vehicle match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610726671.5A CN107808519A (en) | 2016-08-25 | 2016-08-25 | A kind of multiple features vehicle match method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610726671.5A CN107808519A (en) | 2016-08-25 | 2016-08-25 | A kind of multiple features vehicle match method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107808519A true CN107808519A (en) | 2018-03-16 |
Family
ID=61575767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610726671.5A Pending CN107808519A (en) | 2016-08-25 | 2016-08-25 | A kind of multiple features vehicle match method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107808519A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035447A (en) * | 2018-07-05 | 2018-12-18 | 北京悦畅科技有限公司 | A kind of Logistics Park vehicle parking charging method and system |
| CN109636433A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Feeding card identification method, device, equipment and storage medium based on big data analysis |
| CN110570533A (en) * | 2019-09-04 | 2019-12-13 | 南京亿儒科技有限公司 | Confusable vehicle escape system and method based on big data analysis |
| CN111079466A (en) * | 2018-10-18 | 2020-04-28 | 杭州海康威视数字技术股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
| CN113362612A (en) * | 2021-06-02 | 2021-09-07 | 国电内蒙古东胜热电有限公司 | Vehicle identification method and system |
-
2016
- 2016-08-25 CN CN201610726671.5A patent/CN107808519A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035447A (en) * | 2018-07-05 | 2018-12-18 | 北京悦畅科技有限公司 | A kind of Logistics Park vehicle parking charging method and system |
| CN109636433A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Feeding card identification method, device, equipment and storage medium based on big data analysis |
| CN111079466A (en) * | 2018-10-18 | 2020-04-28 | 杭州海康威视数字技术股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
| CN110570533A (en) * | 2019-09-04 | 2019-12-13 | 南京亿儒科技有限公司 | Confusable vehicle escape system and method based on big data analysis |
| CN113362612A (en) * | 2021-06-02 | 2021-09-07 | 国电内蒙古东胜热电有限公司 | Vehicle identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808519A (en) | A kind of multiple features vehicle match method | |
| CN110378236B (en) | Vehicle identity recognition model construction and recognition method and system based on deep learning | |
| CN106446949B (en) | A kind of vehicle model recognition methods and device | |
| CN101097605B (en) | Vehicle personal identification system of ETC electric no-parking charge | |
| CN108090429B (en) | Vehicle type recognition method for graded front face bayonet | |
| CN106127747A (en) | Car surface damage classifying method and device based on degree of depth study | |
| CN107729818A (en) | A kind of multiple features fusion vehicle recognition methods again based on deep learning | |
| CN103198315B (en) | Based on the Character Segmentation of License Plate of character outline and template matches | |
| CN103150904A (en) | Bayonet vehicle image identification method based on image features | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| Deb et al. | HSI color based vehicle license plate detection | |
| CN106971557A (en) | A kind of vehicle identification method and system | |
| CN106355140B (en) | The method and device of vehicle detection | |
| CN106128113A (en) | The recognition methods of fake license plate vehicle and device | |
| CN103390167A (en) | Multi-characteristic layered traffic sign identification method | |
| CN106886987A (en) | A kind of train license plate binary image interfusion method | |
| CN107506368A (en) | The determination method and device of one species case suspected vehicles | |
| Liu et al. | Real-time recognition of road traffic sign in motion image based on genetic algorithm | |
| CN106205120B (en) | A kind of method and device for extracting road cross traffic limitation | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN108021879A (en) | A kind of vehicular traffic kind identification method based on video image | |
| CN102930242B (en) | Bus type identifying method | |
| CN103699880A (en) | Internet of things-based traffic violation vehicle license plate detection and identification method | |
| CN107180230A (en) | General licence plate recognition method | |
| CN104102909A (en) | Vehicle characteristic positioning and matching method based on multiple-visual information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190117 Address after: No. 1088 Fugang Road, Fengxian District, Shanghai, 200240 Applicant after: Shanghai Entertainment Electronic Commerce Co., Ltd. Address before: Room D3049, 3rd floor, 41 block, 398 Heqing Road, Minhang District, Shanghai, 200240 Applicant before: Shanghai Rui Police Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180316 |
|
| WD01 | Invention patent application deemed withdrawn after publication |