基于光照不变特征的椭球法运动阴影检测

doi:10.13190/jbupt.200905.109.gaojx

北京邮电大学学报 ›› 2009, Vol. 32 ›› Issue (5): 109-113.doi: 10.13190/jbupt.200905.109.gaojx

基于光照不变特征的椭球法运动阴影检测

高俊祥;杜海清;刘勇

(北京邮电大学信息与通信工程学院，北京 100876)

收稿日期:2008-12-23 修回日期:2009-05-31 出版日期:2009-10-28 发布日期:2009-10-28
通讯作者: 高俊祥

Moving Shadow Detection by Ellipsoidal Method Using Illumination Invariants

GAO Jun-xiang,DU Hai-qing,LIU Yong

(School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China)

Received:2008-12-23 Revised:2009-05-31 Online:2009-10-28 Published:2009-10-28
Contact: GAO Jun-xiang

摘要/Abstract

摘要：

为检测视频监控系统中运动目标的阴影，提出了一种基于光照不变特征c1c2c3的检测算法. 该算法首先根据前景像素和处于相同位置的背景像素的c1c2c3之比定义坐标系，并将阴影检测视为该坐标系内阴影和运动物体的分类问题；然后，采用阴影像素在该坐标系中的分布特性构建1个椭球，并将处在椭球内部的像素判别为阴影像素；最后，根据阴影区域的几何信息进行后处理. 实验表明，该算法能有效地检测不同场景、不同运动物体的阴影，并能适应光照条件的变化.

关键词: 模式识别, 运动阴影检测, 智能视频监控

Abstract:

To detect moving shadow in intelligent video surveillance system, a method using illumination invariants c1c2c3is presented. Firstly, the coordinate
systems are defined on the basis of c1c2c3ratios of foreground and b
ackground pixels at the same position. Secondly, the moving shadow detection can be treated as a classification problem of shadows and moving objects in abovementioned coordinate systems. An ellipsoid is further constructed according to the scattering feature of shadow pixels. All the pixels inside the ellipsoid are extracted as shadows. Finally, the postprocessing is performed by exploiting the geometrical property of shadows. Experiments show that the proposed algorithm is robust and effective in detecting shadows for a variety of scenes and moving objects; moreover, it is suited for varying illumination conditions.

Key words: pattern recognition, moving shadow detection, intelligent video surveillance

高俊祥;杜海清;刘勇. 基于光照不变特征的椭球法运动阴影检测[J]. 北京邮电大学学报, 2009, 32(5): 109-113.

GAO Jun-xiang,DU Hai-qing,LIU Yong. Moving Shadow Detection by Ellipsoidal Method Using Illumination Invariants[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2009, 32(5): 109-113.

参考文献

[1] Bianchi G. Performance analysis of the IEEE 802.11 distributed coordination function[J]. IEEE Journal on Selected Areas in Communications, 2000, 18(3): 535-547.
[2] Ergen M, Lee D, Sengupta R, et al. Wireless token ring protocol performance comparison with IEEE 802.11//ISCC 2003. Antalya: , 2003: 710-715.
[3] Lee D, Attias R, Puri A, et al. A wireless token ring protocol for Ad Hoc networks//Aerospace Conference 2002. Montana: , 2002: 1219-1228.
[4] 何敏, 赵东风, 刘心松. 移动Ad Hoc网络分布式并行接入控制协议分析. 系统工程与电子技术, 2007, 29(3): 443-448. He Min, Zhao Dongfeng, Liu Xinsong. Analysis of a distributed parallel access control protocol for mobile Ad Hoc networks[J]. Systems Engineering and Electrionics, 2007, 29(3): 443-448.
[5] 张宇眉, 张欣, 杨大成, 等. 基于等待时间和信道状态的轮询多址协议[J]. 北京邮电大学学报, 2008, 31(4): 126-129. Zhang Yumei, Zhang Xin, Yang Dacheng, et al. Polling multiple access protocol based on the waiting time and channel state[J]. Journal of Beijing University of Posts and Telecommunications, 2008, 31(4): 126-129.
[6] 张宇眉, 杨大成, 赵东风, 等. 基于队长参数的动态限定轮询多址协议分析[J]. 北京邮电大学学报, 2007, 30(3): 54-57. Zhang Yumei, Yang Dacheng, Zhao Dongfeng, et al. Analysis of the dynamic limited polling protocol based on parameter of queue length[J]. Journal of Beijing University of Posts and Telecommunications, 2007, 30(3): 54-57.
[7] Sun Xianpu, Zhang Yanling, Li Jiandong. Wireless dynamic token protocol for MANET//ICPPW 2007. Xi'an: , 2007: 5.
[8] Johnson E, Tang Zibin, Balakrishnan M, et al. Robust token management for unreliable networks//IEEE MILCOM 2003. Boston: , 2003: 399-404.
[9] Johnson E, Anaya G, Tang Zibin, et al. Performance of the HF token protocol//IEEE MILCOM 2004. Monterey: , 2004: 1021-1027.
[10] Johnson E, Tang Zibin, Balakrishnan M. Token relay with optimistic joining//IEEE MILCOM 2005. Atlantic: , 2005: 2216-2222.

[1]	王智广, 王雷. 设计模式自动识别的研究进展[J]. 北京邮电大学学报, 2018, 41(4): 119-124.
[2]	王雷, 王智广. 考虑多种特征因素的设计模式自动识别[J]. 北京邮电大学学报, 2017, 40(5): 36-42.
[3]	刘渭滨, 邹智元, 邢薇薇. 模式分类中的特征融合方法[J]. 北京邮电大学学报, 2017, 40(4): 1-8.
[4]	王景尧,宋梅,张勇，张英海. 认知网络中基于小波分析的切换判决[J]. 北京邮电大学学报, 2010, 33(6): 98-102.
[5]	苏放范英磊. 基于Fuzzy模式识别的异构网络端到端丢包评判算法[J]. 北京邮电大学学报, 2007, 29(s1): 52-56.
[6]	黎洪松,许保华. 一种基于运动模式识别的视频对象编码算法[J]. 北京邮电大学学报, 2007, 30(4): 74-77.
[7]	陈光, 张洪刚, 郭军. 基于余弦整形变换的手写汉字训练样本生成方法[J]. 北京邮电大学学报, 2006, 29(s2): 118-121.
[8]	胡云伍宏涛张涵钰钮心忻杨义先. 大容量索引图像水印方案的设计与实现[J]. 北京邮电大学学报, 2005, 28(1): 26-29.
[9]	王波涛, 吴伟陵, 吴善培. 一种改进的神经网络训练算法[J]. 北京邮电大学学报, 2004, 27(4): 87-91.
[10]	邵旭, 丁炜, 石晶林, 张志群. 一种QoS自适应定量分类方法[J]. 北京邮电大学学报, 2001, 24(3): 60-64.
[11]	马晓敏, 杨义先. 基于内积方向的神经网络学习算法及应用^*[J]. 北京邮电大学学报, 1998, 21(4): 43-47.

基于光照不变特征的椭球法运动阴影检测

Moving Shadow Detection by Ellipsoidal Method Using Illumination Invariants

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价