Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for automatically recognizing vehicle colors in road checkpoint videos and pictures

An automatic identification, in-picture technology, applied in the fields of digital image processing and pattern recognition, vehicle color feature sample extraction and identification, can solve problems such as affecting the accuracy of positioning results, prone to errors in color identification, and accurate vehicle positioning errors, etc. Improve the recognition rate, strong stability, good overall effect

Inactive Publication Date: 2019-02-15
GUANGZHOU SUNSHINE NAITE ELECTRONICS
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the color of the actual vehicle itself will not change due to external lighting, and the color of the vehicle itself is fixed, so color recognition is prone to errors
[0008] 2) Vehicle precise positioning error
[0010] When positioning, wrong color judgment will directly affect the accuracy of positioning results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for automatically recognizing vehicle colors in road checkpoint videos and pictures
  • A method for automatically recognizing vehicle colors in road checkpoint videos and pictures
  • A method for automatically recognizing vehicle colors in road checkpoint videos and pictures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to better understand the present invention, the present invention will be further described below in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0055] Such as figure 1 As shown in the figure, the method of automatically identifying the color of road checkpoints and vehicles in pictures includes the extraction and labeling of training samples, the collection and labeling of test samples, the color space conversion of training samples and test samples, and the calculation of the color distribution center of training samples and test samples , color classification recognition and other steps.

[0056] The training samples are the color samples of the vehicles extracted from the color-marked vehicle pictures; the number of training samples is in principle not less than 500 for each color sample, and the color samples need to cover all car colors, namely black, white, gray, red , pink, yellow,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for automatically recognizing vehicle colors in road intersection video and picture. The method comprises the following steps: extracting a training sample and labeling; collecting a test sample and labeling; carrying out color space conversion on the training sample and the test sample; calculating color distribution centers of the training sample and the test sample; and carrying out color classification and recognition. According to the method, the boundedness of an unstable local region of a color sample is avoided; the color feature of the vehicle can be relatively accurately recognized; and the effects on an ambient light source are reduced. For public security video and image monitoring data, the color of the vehicle has relatively good stability in a road, and is not easily artificially changed on the road, so that important roles in recognizing and determining the vehicle are played, the problem that the color of the vehicle cannot be easily effectively recognized in an unstable light environment in which the vehicle is located for a long period of time is solved; and the method plays a positive role in construction of intelligent transportation and safety cities.

Description

technical field [0001] The invention relates to digital image processing and pattern recognition technology, belongs to the field of machine vision, and is a method for extracting and recognizing vehicle color feature samples in road traffic checkpoint videos and images. Background technique [0002] With the rapid growth of the number of motor vehicles, the number of cases of illegal driving, illegal parking, false license plates, traffic accidents and escapes, and the use of vehicles as tools of crime are increasing. Building "safe cities" and "smart transportation" have become important solutions , the automatic analysis of road traffic vehicle checkpoint videos and pictures (abbreviated as checkpoint pictures) is an important part thereof. [0003] For the automatic analysis of road checkpoint videos and pictures, one of the important contents is to recognize the color of vehicles. Since it is very difficult to change the vehicle color on the road, it is even impossible...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/66
Inventor 丁祖春莫文英莫莲枝
Owner GUANGZHOU SUNSHINE NAITE ELECTRONICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com