CN106599850A - Traffic analysis method and traffic analysis system based on vehicle logo recognition - Google Patents
Traffic analysis method and traffic analysis system based on vehicle logo recognition Download PDFInfo
- Publication number
- CN106599850A CN106599850A CN201611167461.3A CN201611167461A CN106599850A CN 106599850 A CN106599850 A CN 106599850A CN 201611167461 A CN201611167461 A CN 201611167461A CN 106599850 A CN106599850 A CN 106599850A
- Authority
- CN
- China
- Prior art keywords
- logo
- image
- vehicle
- characteristic
- 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- Withdrawn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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V2201/09—Recognition of logos
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (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)
- Image Processing (AREA)
Abstract
The invention provides a traffic analysis method and a traffic analysis system based on vehicle logo recognition, wherein the method and the system relate to the field of video analysis technology. The method comprises the following steps of 1), acquiring an original image through an image camera; 2), performing vehicle logo recognition, namely determining a vehicle logo area by means of a texture characteristic analysis positioning method; 3), performing image transforming processing, namely performing characteristic transforming processing on a vehicle logo image for obtaining a characteristic vector set of the vehicle logo image; and 4), performing matching processing on characteristic points in the characteristic vector set of the vehicle logo image and characteristic points in a preset characteristic vector set for obtaining a matched characteristic point set; and 5), matching the vehicle logos, namely acquiring a corresponding vehicle logo type according to the matched characteristic point set, and realizing an accurate vehicle logo acquiring recognition result.
Description
Technical field
The present invention relates to Video Analysis Technology field, and in particular to one kind is based on vehicle-logo recognition traffic analysis method and is
System.
Background technology
With the development of social economy, vehicle increases, and by computer information, intelligentized management vehicle becomes must
So.License plate recognition technology is widely used in traffic flow monitoring, the charge of highway bayonet socket, red light violation vehicle monitoring and
In cell automatic fare collection system.Vehicle recongnition technique is one of key technology of intelligent transportation field, and vehicle-logo recognition technology is car
The new research direction of technology of identification, the type of the logo of vehicle can be divided into circle, oval and square, current place by shape
Reason technology can only be identified to car plate and large-scale, medium-sized, dilly, but can not recognize specific vehicle.The identification of logo
It is broadly divided into logo coarse positioning, logo fine positioning, three steps of vehicle-logo recognition, opening up using car plate and logo in the prior art
Relation is flutterred, the approximate region of logo is determined；Rough position according to extracting accurately extracts again logo, but logo is being carried out
When positioning, identification, because the chaff interference of some backgrounds and front influences whether the segmentation of logo, and then the knowledge of logo is had influence on
Not.Vehicle-logo recognition is affected for the chaff interference in prior art due to car plate, so as to affect to distinguish the problem of vehicle, at present not yet
Propose effective solution.
This is directed to, needs make improvement.
The content of the invention
The invention provides a kind of be based on vehicle-logo recognition traffic analysis method and system, improve logo recognition accuracy and
Efficiency.
One kind is based on vehicle-logo recognition traffic analysis method, comprises the following steps：
1) original image is obtained, original image is obtained by video camera；
2) vehicle-logo location, using using analysis of texture localization method, determining a car mark region；
3) image conversion process, to the logo image eigentransformation process is carried out, to obtain the spy of the logo image
Levy vectorial set；
4) matching treatment, in the characteristic point in the characteristic vector set of the logo image and default characteristic vector set
Characteristic point carry out matching treatment, to obtain matching characteristic point set；
5) logo is matched, corresponding logo type is obtained according to the matching characteristic point set.
Further, the step 2) in, vehicle-logo location method is specifically, the figure in original image after pretreatment
As enterprising line scans, it is determined that determining the initial row coordinate of candidate region containing the candidate region of logo line segment in a column direction
And height；Then enter rank scanning to candidate region and determine its row coordinate and width, thereby determine that a car mark region.
Further, the step 3) it is specially：
1) edge positioning is carried out to the original image, to obtain edge image；
2) eigentransformation process is carried out to the edge image, to obtain characteristic vector of the correspondence per edge image described in width
Set；
3) cluster analyses are carried out to the characteristic vector set, with obtain multiple class data and with class data each described
Corresponding characteristic mean；
4) row label setting is entered to characteristic mean each described, to obtain the characteristic mean collection for arranging label, by the spy
Average collection is levied as the characteristic vector set.
Further, the step 4) include：Detect in the characteristic vector set of the logo image and whether there is and institute
State the characteristic point that the characteristic point in default characteristic vector set matches；Exist in the characteristic vector set of the logo image
In the case of the characteristic point matched with the characteristic point in default characteristic vector set, the matching characteristic point set is obtained.
Further, also including step 6) output result, the logo type after matching is shown with word and logo modes.
One kind is based on vehicle-logo recognition traffic analysis system,
1) image collection module, by video camera original image is obtained；
2) vehicle-logo location module, using using analysis of texture localization method, determining a car mark region；
3) conversion process module, to the logo image eigentransformation process is carried out, to obtain the spy of the logo image
Levy vectorial set；
4) matching treatment module, to characteristic point and default set of eigenvectors in the characteristic vector set of the logo image
Characteristic point in conjunction carries out matching treatment, to obtain matching characteristic point set；
5) logo matching module, according to the matching characteristic point set corresponding logo type is obtained.
Further, the conversion process module includes：
1) vehicle-logo location module, for carrying out edge positioning to the logo image, to obtain edge image；
2) feature transform module, for carrying out eigentransformation process to the edge image, to obtain correspondence per described in width
The characteristic vector set of edge image；
3) analysis and processing module, for carrying out cluster analyses to the characteristic vector set, with obtain multiple class data with
And characteristic mean corresponding with class data each described；
4) label setup module, is arranged for entering row label to characteristic mean each described, to obtain the spy for arranging label
Average collection is levied, using the characteristic mean collection as the characteristic vector set.
Further, the step 1) image collection module also include step：
1) image capture module, for gathering original image；
2) location Calculation module, for carrying out vehicle-logo location calculating to the original image, to obtain the original image
In initial logo image；
3) intercepting process module, for carrying out intercepting process to the initial logo image, to obtain the logo image.
Further, output result is, it is determined that the logo after being identified to car mark region per class vehicle-logo recognition model is known
Other result confidence level；Using confidence level highest vehicle-logo recognition result as vehicle-logo recognition result.
Further, also the logo type after matching is shown with word and logo modes including output display module.
It is an advantage of the current invention that：Logo image to be identified is processed after logo image is obtained, obtains car
The characteristic vector set of logo image, then to the characteristic point in default characteristic vector set and the feature of logo image to be identified
Point carries out matching operation, realizes the vehicle-logo recognition in images to be recognized, solves in prior art due to the chaff interference of car plate
Affect vehicle-logo recognition, so as to affect to distinguish vehicle, realize the recognition result for accurately obtaining logo, so as to can to complex background,
Inclination, deformation, dirt, partial occlusion, the logo of light change carry out effective effect for recognizing.
Description of the drawings
Fig. 1 is flow chart of the present invention based on vehicle-logo recognition traffic analysis method；
Fig. 2 is a kind of schematic diagram based on vehicle-logo recognition traffic analysis system of the present invention.
Specific embodiment
To make purpose, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention, rather than the embodiment of whole.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
With reference to accompanying drawing 1 and Fig. 2, the present invention is a kind of to be based on vehicle-logo recognition traffic analysis method, comprises the following steps：
1) original image is obtained, original image is obtained by video camera；
2) vehicle-logo location, using using analysis of texture localization method, determining a car mark region；
3) image conversion process, to the logo image eigentransformation process is carried out, to obtain the spy of the logo image
Levy vectorial set；
4) matching treatment, in the characteristic point in the characteristic vector set of the logo image and default characteristic vector set
Characteristic point carry out matching treatment, to obtain matching characteristic point set；
5) logo is matched, corresponding logo type is obtained according to the matching characteristic point set.
Further, the step 2) in, vehicle-logo location method is specifically, the figure in original image after pretreatment
As enterprising line scans, it is determined that determining the initial row coordinate of candidate region containing the candidate region of logo line segment in a column direction
And height；Then enter rank scanning to candidate region and determine its row coordinate and width, thereby determine that a car mark region.
Further, the step 3) it is specially：
1) edge positioning is carried out to the original image, to obtain edge image；
2) eigentransformation process is carried out to the edge image, to obtain characteristic vector of the correspondence per edge image described in width
Set；
3) cluster analyses are carried out to the characteristic vector set, with obtain multiple class data and with class data each described
Corresponding characteristic mean；
4) row label setting is entered to characteristic mean each described, to obtain the characteristic mean collection for arranging label, by the spy
Average collection is levied as the characteristic vector set.
Further, the step 4) include：Detect in the characteristic vector set of the logo image and whether there is and institute
State the characteristic point that the characteristic point in default characteristic vector set matches；Exist in the characteristic vector set of the logo image
In the case of the characteristic point matched with the characteristic point in default characteristic vector set, the matching characteristic point set is obtained.
Further, also including step 6) output result, the logo type after matching is shown with word and logo modes.
One kind is based on vehicle-logo recognition traffic analysis system,
1) image collection module, by video camera original image is obtained；
2) vehicle-logo location module, using using analysis of texture localization method, determining a car mark region；
3) conversion process module, to the logo image eigentransformation process is carried out, to obtain the spy of the logo image
Levy vectorial set；
4) matching treatment module, to characteristic point and default set of eigenvectors in the characteristic vector set of the logo image
Characteristic point in conjunction carries out matching treatment, to obtain matching characteristic point set；
5) logo matching module, according to the matching characteristic point set corresponding logo type is obtained.
Further, the conversion process module includes：
1) vehicle-logo location module, for carrying out edge positioning to the logo image, to obtain edge image；
2) feature transform module, for carrying out eigentransformation process to the edge image, to obtain correspondence per described in width
The characteristic vector set of edge image；
3) analysis and processing module, for carrying out cluster analyses to the characteristic vector set, with obtain multiple class data with
And characteristic mean corresponding with class data each described；
4) label setup module, is arranged for entering row label to characteristic mean each described, to obtain the spy for arranging label
Average collection is levied, using the characteristic mean collection as the characteristic vector set.
Further, the step 1) image collection module also include step：
1) image capture module, for gathering original image；
2) location Calculation module, for carrying out vehicle-logo location calculating to the original image, to obtain the original image
In initial logo image；
3) intercepting process module, for carrying out intercepting process to the initial logo image, to obtain the logo image.
Further, output result is, it is determined that the logo after being identified to car mark region per class vehicle-logo recognition model is known
Other result confidence level；Using confidence level highest vehicle-logo recognition result as vehicle-logo recognition result.
Further, also the logo type after matching is shown with word and logo modes including output display module.
It is an advantage of the current invention that：Logo image to be identified is processed after logo image is obtained, obtains car
The characteristic vector set of logo image, then to the characteristic point in default characteristic vector set and the feature of logo image to be identified
Point carries out matching operation, realizes the vehicle-logo recognition in images to be recognized, solves in prior art due to the chaff interference of car plate
Affect vehicle-logo recognition, so as to affect to distinguish vehicle, realize the recognition result for accurately obtaining logo, so as to can to complex background,
Inclination, deformation, dirt, partial occlusion, the logo of light change carry out effective effect for recognizing.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposit between operating
In any this actual relation or order.And, term " including ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that a series of process, method, article or equipment including key elements not only will including those
Element, but also including other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
Above example only to illustrate technical scheme, rather than a limitation；Although with reference to the foregoing embodiments
The present invention has been described in detail, it will be understood by those within the art that：It still can be to aforementioned each enforcement
Technical scheme described in example is modified, or carries out equivalent to which part technical characteristic；And these modification or
Replace, do not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (10)
1. it is a kind of to be based on vehicle-logo recognition traffic analysis method, it is characterised in that to comprise the following steps：
1) original image is obtained, original image is obtained by video camera；
2) vehicle-logo location, using using analysis of texture localization method, determining a car mark region；
3) image conversion process, to the logo image eigentransformation process is carried out, with obtain the feature of the logo image to
Duration set；
4) matching treatment, to the spy in the characteristic point in the characteristic vector set of the logo image and default characteristic vector set
Levy and a little carry out matching treatment, to obtain matching characteristic point set；
5) logo is matched, corresponding logo type is obtained according to the matching characteristic point set.
2. it is according to claim 1 a kind of based on vehicle-logo recognition traffic analysis method, it is characterised in that the step 2)
In, vehicle-logo location method specifically, the enterprising line scans of image in original image after pretreatment, it is determined that in column direction
On the candidate region containing logo line segment, determine the initial row coordinate and height of candidate region；Then ranks are entered to candidate region
Scanning determines its row coordinate and width, thereby determines that a car mark region.
3. it is according to claim 1 a kind of based on vehicle-logo recognition traffic analysis method, it is characterised in that the step 3) tool
Body is：
1) edge positioning is carried out to the original image, to obtain edge image；
2) eigentransformation process is carried out to the edge image, to obtain set of eigenvectors of the correspondence per edge image described in width
Close；
3) cluster analyses are carried out to the characteristic vector set, to obtain multiple class data and corresponding with class data each described
Characteristic mean；
4) row label setting is entered to characteristic mean each described, it is to obtain the characteristic mean collection for arranging label, the feature is equal
Value collection is used as the characteristic vector set.
4. it is according to claim 1 a kind of based on vehicle-logo recognition traffic analysis method, it is characterised in that the step 4) bag
Include：Detect and whether there is in the characteristic vector set of the logo image and the characteristic point phase in the default characteristic vector set
The characteristic point of matching；Exist in the characteristic vector set of the logo image and the characteristic point phase in default characteristic vector set
In the case of the characteristic point of matching, the matching characteristic point set is obtained.
5. it is according to claim 1 a kind of based on vehicle-logo recognition traffic analysis method, it is characterised in that also including step 6)
Output result, the logo type after matching is shown with word and logo modes.
It is 6. a kind of to be based on vehicle-logo recognition traffic analysis system, it is characterised in that
1) image collection module, by video camera original image is obtained；
2) vehicle-logo location module, using using analysis of texture localization method, determining a car mark region；
3) conversion process module, to the logo image eigentransformation process is carried out, with obtain the feature of the logo image to
Duration set；
4) matching treatment module, in the characteristic point in the characteristic vector set of the logo image and default characteristic vector set
Characteristic point carry out matching treatment, to obtain matching characteristic point set；
5) logo matching module, according to the matching characteristic point set corresponding logo type is obtained.
7. a kind of system based on vehicle-logo recognition traffic analysis according to claim 6, it is characterised in that at the conversion
Reason module includes：
1) vehicle-logo location module, for carrying out edge positioning to the logo image, to obtain edge image；
2) feature transform module, for carrying out eigentransformation process to the edge image, to obtain correspondence per edge described in width
The characteristic vector set of image；
3) analysis and processing module, for carrying out cluster analyses to the characteristic vector set, with obtain multiple class data and with
The corresponding characteristic mean of each described class data；
4) label setup module, is arranged for entering row label to characteristic mean each described, equal with the feature for obtaining setting label
Value collection, using the characteristic mean collection as the characteristic vector set.
8. a kind of system based on vehicle-logo recognition traffic analysis according to claim 6, it is characterised in that the step 1)
Image collection module also includes step：
1) image capture module, for gathering original image；
2) location Calculation module, for carrying out vehicle-logo location calculating to the original image, to obtain the original image in
Initial logo image；
3) intercepting process module, for carrying out intercepting process to the initial logo image, to obtain the logo image.
9. a kind of system based on vehicle-logo recognition traffic analysis according to claim 6, it is characterised in that output result
For it is determined that the vehicle-logo recognition result confidence level after being identified to car mark region per class vehicle-logo recognition model；By confidence level highest
Vehicle-logo recognition result as vehicle-logo recognition result.
10. a kind of system based on vehicle-logo recognition traffic analysis according to claim 6, it is characterised in that also including defeated
Go out display module, the logo type after matching is shown with word and logo modes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611167461.3A CN106599850A (en) | 2016-12-16 | 2016-12-16 | Traffic analysis method and traffic analysis system based on vehicle logo recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611167461.3A CN106599850A (en) | 2016-12-16 | 2016-12-16 | Traffic analysis method and traffic analysis system based on vehicle logo recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106599850A true CN106599850A (en) | 2017-04-26 |
Family
ID=58599699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611167461.3A Withdrawn CN106599850A (en) | 2016-12-16 | 2016-12-16 | Traffic analysis method and traffic analysis system based on vehicle logo recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106599850A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111862073A (en) * | 2020-07-29 | 2020-10-30 | 广东电网有限责任公司 | Temperature acquisition method and device for power equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
| CN101383003A (en) * | 2008-10-31 | 2009-03-11 | 江西赣粤高速公路股份有限公司 | Real-time precise recognition method for vehicle number board |
| US20090161962A1 (en) * | 2007-12-20 | 2009-06-25 | Gallagher Andrew C | Grouping images by location |
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN103065143A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
-
2016
- 2016-12-16 CN CN201611167461.3A patent/CN106599850A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090161962A1 (en) * | 2007-12-20 | 2009-06-25 | Gallagher Andrew C | Grouping images by location |
| CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
| CN101383003A (en) * | 2008-10-31 | 2009-03-11 | 江西赣粤高速公路股份有限公司 | Real-time precise recognition method for vehicle number board |
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN103065143A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111862073A (en) * | 2020-07-29 | 2020-10-30 | 广东电网有限责任公司 | Temperature acquisition method and device for power equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
| CN105160309B (en) | Three lanes detection method based on morphological image segmentation and region growing | |
| CN102708356B (en) | Automatic license plate positioning and recognition method based on complex background | |
| CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
| CN109726717B (en) | Vehicle comprehensive information detection system | |
| CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
| CN101339601B (en) | License plate Chinese character recognition method based on SIFT algorithm | |
| CN102915433B (en) | Character combination-based license plate positioning and identifying method | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN105740886B (en) | A kind of automobile logo identification method based on machine learning | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN102364496A (en) | Method and system for identifying automobile license plates automatically based on image analysis | |
| CN109670449B (en) | Vehicle illegal judgment method based on vertical snapshot mode | |
| CN102542244A (en) | Face detection method and system and computer program product | |
| Sugiharto et al. | Traffic sign detection based on HOG and PHOG using binary SVM and k-NN | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN106529461A (en) | Vehicle model identifying algorithm based on integral characteristic channel and SVM training device | |
| CN103544489A (en) | Device and method for locating automobile logo | |
| CN103106409A (en) | Composite character extraction method aiming at head shoulder detection | |
| CN109325487B (en) | Full-category license plate recognition method based on target detection | |
| CN111915583A (en) | Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene | |
| CN104182728A (en) | Vehicle logo automatic location and recognition method based on pattern recognition | |
| CN104102909A (en) | Vehicle characteristic positioning and matching method based on multiple-visual information | |
| CN112101108B (en) | Left-right pass-through sign recognition method based on graph pole position characteristics | |
| Mammeri et al. | North-American speed limit sign detection and recognition for smart cars |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170426 |