广西师范大学学报（自然科学版） ›› 2010, Vol. 28 ›› Issue (3): 165-169.

• • 上一篇    下一篇

一种运动目标阴影轮廓的两步检测算法

王玮, 李红波, 吴渝   

  1. 重庆邮电大学网络智能研究所,重庆400065
  • 收稿日期:2010-06-12 出版日期:2010-09-20 发布日期:2023-02-06
  • 通讯作者: 吴渝(1970—),女,重庆人,重庆邮电大学教授,博士。E-mail:wuyu@cqupt.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(60873079);教育部新世纪人才支持计划;科技部动漫软件开发技术团队支持(国科发高【2009】593号);重庆市科技攻关项目(7818)

Two-step Algorithm for Detecting Shadow Silhouettes of Moving Objects

WANG Wei, LI Hong-bo, WU Yu   

  1. Institute of Web Intelligence,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
  • Received:2010-06-12 Online:2010-09-20 Published:2023-02-06

摘要： 由于运动阴影具有与运动前景相同的特性,在视频处理中分割前景时存在误把阴影检测为前景的问题,可能严重地影响跟踪、识别等后续处理,据此提出一种用于运动目标阴影检测的改进算法。先为每个像素点建立混合高斯模型分割出运动目标,利用阴影区域像素8个相邻区域上像素点的亮度特点判断疑似阴影,然后运用色彩空间向量模型的颜色不变性对所有疑似阴影进行聚类,进一步完成阴影检测。试验结果表明,该方法检测精度高、效果好、速度快,有广泛的应用前景。

关键词: 背景建模, 混合高斯, 阴影检测

Abstract: In the video processing,shadow is often detected mistakenly for foreground in the segmentation with moving foreground because movingshadow shares the same characters with moving foreground.This may seriously affects post-processing such as tracking and identification.An improved algorithm is presented for shadow detection of moving object.Firstly,a Gaussian mixture model is constructed for each pixel to segment the moving object.For a pixel detected to be moving foreground in the shadow area,it is determined whether it is suspected shadowpixel according to the brightness characteristics of the 8 pixels in its neighboring region.Then all the suspected shadow is clustered by virtue of the color invariance in the Color space vector model for further shadow detection.Experimentalresults show that the detection method has a broad application prospects due to its high precision,efficiency,and rapidness.

Key words: background modeling, mixture Gaussian, shadow detection

中图分类号: 

  • TP391.41
[1] HSIEH Jun-wei,HU Wen-feng,CHANG Chia-jung,et al.Shadow elimination for effective movingobject detection by Gaussian shadow modeling[J].Int J Image and Vision Computing,2003,21:505-516.
[2] SALVADOR E,CAVALLARO S,EBRAHIMI T.Cast shadow segmentation using invariant color features[J].Computer Vision and Image Understanding,2004,95:238-259.
[3] CHEN Bai-sheng,LEI Yun-qi.Indoor and outdoor people detection and shadow suppression by exploiting HSV color information[C]//Proceedings of the Fourth International Conference on Computer and Information Technology.Wuhan,China:IEEE Computer Society,2004:137-142.
[4] 叶丽燕,赵建民,朱信忠.基于梯度特征的阴影检测方法[J].计算机技术与发展,2009,19(10):70-72,76.
[5] 杨俊,赵忠明.基于归一化RGB色彩模型的阴影处理方法[J].光电工程,2007,34(12):92-96.
[6] 陈延涛.一种改进的混合高斯模型运动目标检测方法[J].四川大学学报:自然科学版,2009,46(5):1296-1300.
[7] 李忠武,高广珠,余理富,等.图像序列目标检测中阴影的消除[J].计算机应用研究,2004,21(5):205-206.
[8] 黄薇,肖平,冯刚.带有阴影消除的室内运动人体的提取与跟踪[J].计算机工程,2007,33(5):170-172.
[9] LI Yong-bin,FENG Chen-li,XU Wen-li,et al.Gaussian-based codebook model for video background subtraction[C]//Lecture Notes in Computer Science.Berlin:Springer-Verlag,2006:762-765.
[10] KIM K,CHALIDABHONGSE T H,HARWOOD D,et al.Real-time foreground-background segmentation using codebook model[J].Real-Time Imaging,2005,11(3):172-185.
[1] 肖逸群, 宋树祥, 夏海英. 基于多特征的快速行人检测方法及实现[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 61-67.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发