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

Vehicle body color detection and identification method

A technology of color detection and recognition method, which is applied in the field of vehicle body color detection and recognition, can solve the problem of not being able to detect and recognize vehicles of various colors, and achieve the effect of small amount of calculation

Active Publication Date: 2013-12-11
QINGDAO HISENSE TRANS TECH
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing vehicle body color detection and recognition method cannot detect and recognize vehicles of various colors, the present invention provides a vehicle body color detection and recognition method, which can recognize floats and improve detection accuracy

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
  • Vehicle body color detection and identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Embodiment one, see figure 1 As shown, a vehicle body color detection and recognition method in this embodiment includes the following steps:

[0033] Training steps:

[0034] Train a main color model, including at least 3 color types in the main color model;

[0035] Color detection and recognition steps:

[0036] S1. Detect and obtain the rectangular area of ​​the vehicle;

[0037] S2. Main color identification, including:

[0038] S21. Input all pixels in the area into the main color model, and determine that each pixel corresponds to a color in the color list in the main color model;

[0039] S22. Calculate the proportion of each color in the color list, and sort according to the proportion from large to small;

[0040] S23. Calculate the variance M of the proportion of the top 4 digits in the ranking. If the variance M is smaller than the threshold T, it is judged to be a float; otherwise, it is judged to be a monochromatic car, and the color with the highest ...

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 vehicle body color detection and identification method. The method comprises the following steps of: training: training out a main color model; color detection and identification: (1) detecting and acquiring a vehicle rectangle region; (2) main color identification: (21), inputting all pixel points from the region into the main color model so as to judge colors (corresponding to each pixel point) in a color list in the main color model; (22), performing statistics on the occupation proportion of each color in the color list and sequencing the colors from big to small according to the occupation proportion; and (23), judging a festooned vehicle or a monochromatic vehicle by utilizing the variance M of the occupation proportion of the former four sequenced colors. The method disclosed by the invention is used for performing color analysis on the whole vehicle body, so that not only the single color vehicle but also the festooned vehicle with multiple colors can be identified, which is favorable for the rapid positioning of the relevant vehicle. The disturbance of various light rays during the selection of a fixed region is avoided by utilizing a high-confidence region. The method is small in calculated quantity and realizes the high-definition real-time detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a vehicle body color detection and recognition method. Background technique [0002] Motor vehicle body color recognition is an important attribute of vehicle detection in intelligent transportation. It plays an important role in the investigation of suspected vehicles and the automatic detection of licensed vehicles. However, the body color recognition is seriously interfered by ambient light. Different body areas will reflect different colors, which will have a great impact on the detection of body color. Patent 20111013540.7, whose invention name is the method for automatic identification of body color in vehicle intelligent monitoring system, discloses that the color positioning of the vehicle body is assisted by the license plate area. A priori calibration is performed for low confidence levels. However, this patent does not consider the interference o...

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 Applications(China)
IPC IPC(8): G06K9/62
Inventor 田永鸿苏驰王耀威刘韶温炜张弢王彬孙婷婷
Owner QINGDAO HISENSE TRANS TECH
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