计算机应用 ›› 2013, Vol. 33 ›› Issue (02): 539-542.DOI: 10.3724/SP.J.1087.2013.00539

• 多媒体处理技术 • 上一篇    下一篇

基于颜色和纹理特征的伪装色矿工目标检测

鲜晓东,李克文   

  1. 重庆大学 自动化学院,重庆 400044
  • 收稿日期:2012-08-13 修回日期:2012-09-28 出版日期:2013-02-01 发布日期:2013-02-25
  • 通讯作者: 鲜晓东
  • 作者简介:鲜晓东(1966-),女,重庆人,副教授,硕士,主要研究方向:无线传感器网络、移动机器人控制、信号处理;
    李克文(1986-),男,湖北钟祥人,硕士研究生,主要研究方向:视频图像处理。
  • 基金资助:
    重庆市教育委员会科学技术研究项目

Detection of camouflaged miner objects based on color and texture features

XIAN Xiaodong,LI Kewen   

  1. College of Automation, Chongqing University, Chongqing 400044, China
  • Received:2012-08-13 Revised:2012-09-28 Online:2013-02-01 Published:2013-02-25
  • Contact: XIAN Xiaodong

摘要: 针对矿井下某些地段低光照低对比度导致矿工目标与环境颜色相似,呈现伪装色特点,一般场景目标检测方法易产生矿工漏检、误检的问题,提出了采用高斯混合模型(GMM)和局部二值模式(LBP)纹理模型线性融合的方法对目标矿工进行检测。首先利用高斯混合模型拟合背景颜色信息,然后通过局部二值模式纹理模型提取图像纹理信息,最后将颜色信息和纹理信息线性融合对矿工进行检测。实验结果表明,在满足实时性的同时,减少了矿工目标出现漏检、误检的问题,该方法可对具有伪装色特征的矿工目标进行实时检测,准确性高。

关键词: 伪装色, 高斯混合模型, 局部二值模式, 颜色信息, 纹理信息

Abstract: Due to the low illumination, low contrast and similar color between target and environment in a coal mine, problems of undetected objects and false detections appear. An improved miner target detection method was proposed, integrating Gaussian Mixture Model (GMM) with Local Binary Pattern (LBP). The color information of background was fitted by means of GMM, and the texture information was extracted by employing LBP, then the miners targets were detected by integrating the color and the texture information. The simulation results indicate that the proposed algorithm decreases the problems of undetected objects and false detections, and can detect miner target in real-time with high precision.

Key words: camouflage, Gaussian Mixture Model (GMM), Local Binary Pattern (LBP), color information, texture information

中图分类号: