期刊文献+

基于混合高斯模型的运动阴影抑制算法 被引量:20

Moving cast shadow suppression from a Gaussian mixture shadow model
下载PDF
导出
摘要 复杂场景的背景建模、运动目标检测、运动目标所投射阴影的检测与抑制在智能监控、机器人视觉、视频会议等领域有着广泛的应用。在运动前景检测阶段,给出了一种改进的混合高斯算法进行场景的背景建模,根据各点像素值出现的混乱程度采取不同的高斯函数参数更新机制,缓解了混合高斯算法计算量大的问题。在运动目标的阴影检测与抑制中,提出了一种基于混合高斯的阴影抑制算法,该算法先利用阴影在HSV颜色空间的特点,判断被检测为运动前景的像素是否为疑似阴影,然后用混合高斯阴影模型对所有疑似阴影值进行聚类,进一步完成阴影抑制。仿真结果表明:该算法可更有效地抑制阴影对运动目标检测的影响,并具有较强的实时性。 The background modeling of complex environment, moving object detection, and moving cast shadow suppression could be applied to a lot of fields such as intelligent surveillance, robot vision and videoeonference ect. In moving foreground detection, an improved mixture Gaussian-based background modeling method was presented, which updated the parameters of Gaussians according to the frequency of pixel value changes, to reduce the cost of computation. In shadow suppression, a mixture Gaussian-based clustering algorithm was provided to detect and suppress shadow. This method firstly identifies whether a pixel value is probable shadow by shadow model in HSV color space, the pixel values detected as probable shadow are then put into mixture Gaussian shadow model to learn and cluster. The experimental results indicates that the oroDosed aooroach in this paper can process in real-time and remove shadow more effectively.
出处 《计算机应用》 CSCD 北大核心 2006年第5期1021-1023,1026,共4页 journal of Computer Applications
基金 国家自然科学基金资助项目(60372085) 陕西省科学技术研究发展计划资助项目(2003K06G15)
关键词 背景建模 混合高斯 阴影抑制 HSV颜色空间 background modeling Gaussian mixture shadow suppression HSV color space
  • 相关文献

参考文献9

  • 1YONEYAMA A, YEH CH, KUO CCJ. Moving cast shadow elimination for robust vehicle extraction based on 2D joint vehicle/shadow models[A]. Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS'03) [C]. Miami, FL, USA.IEEE Computer Society, 2003.229 -236.
  • 2SALVADOR E, CAVALLARO A, EBRAHIMI T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2) : 238 - 259.
  • 3BAISHENG C, YUNQI L. Indoor and outdoor people detection and shadow suppression by exploiting HSV color information[A]. Proceedings of the Fourth International Conference on Computer and Information Technology[C]. Wuhan, China. IEEE Computer Society,2004. 137 - 142.
  • 4MARTEL-BRISSON N, ZACCARIN A. Moving cast shadow detection from a gaussian mixture shadow model[A]. CVPR 2005[C].IEEE Computer Society Conference, 2005.
  • 5PRATI A, MIKIC I, TRIVEDI MM, et al. Detecting moving shadows: algorithms and evaluation[J]. IEEE transactions on pattern analysis and machine intelligence, 2003, 25(7) : 918 - 923.
  • 6POWER PW, SCHOONEES JA. Understanding background mixture models for foreground segmentation[A]. Proceedings of Image and Vision Computing New Zealand [C]. Auckland, New Zealand,2002. 267 - 271.
  • 7CHEUNG SCS, KAMATH C. Robust techniques for background subtraction in urban traffic video[A]. Proceedings of Electronic Imaging: Visual Communications and Image Processing 2004 (Part One) [C]. San Jose, California. Bellingham, WA: SPIE, 2004.,(5308) : 881 - 892.
  • 8NADIMI S, BHANU B. Physical models for moving shadow and object detection in video[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26(8) : 1079 -1087.
  • 9WANG H, SUTER D. A re-evaluation of mixture-of-gaussian background modeling[A]. IEEE International Conference on Acoustics,Speech, and Signal Processing (ICASSP) [C]. Pennsylvania, USA,2005. 1017 - 1020.

同被引文献217

引证文献20

二级引证文献103

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部