复杂场景中基于对象的运动目标检测方法

被引:8
作者
张笑微
周建雄
机构
[1] 西南科技大学信息工程学院
关键词
混合高斯背景建模; 运动持续性; 运动显著性; 面积变化稳定性;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
基于像素层面的混合高斯背景建模方法不能很好的解决动态背景中的运动目标检测问题。由于背景像素运动的复杂性,该方法很难将动态背景建入模型,会造成大量的误检。本文在混合高斯背景建模的基础上,通过空域和时域对动态背景产生的误检进行抑制。在空域运用MRF模型和混合高斯模型分别计算像素点的先验概率和类条件概率,通过结合像素点的先验概率和类条件概率完成前景图像的分割,在很大程度上去除了小面积的误检;在时域通过目标的运动持续性,运动显著性和面积变化稳定性三个目标特征过滤大面积的误检。通过实验表明,在保证较高检测精度的情况下,该方法能够在很大程度上抑制动态背景产生的误检。
引用
收藏
页码:1 / 7
页数:7
相关论文
共 8 条
  • [1] Statistical modeling of complex backgrounds for foreground object detection. Liyuan Li,Weimin Huang,Irene Yu-Hua Gu,Qi Tian. In: IEEE Transactions on Image Processing, Nov . 2004
  • [2] Motion-based background subtraction using adaptive kernel density estimation. Mittal A,Paragios N. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2004
  • [3] Back-ground modeling and subtraction by codebook construction. KIM K,CHALIDABHONGSE T H,HARWOOD D,et al. ICIP04:2004International Conference on Image Processing . 2004
  • [4] A texture-based method for modeling the background and detecting moving objects. Heikkila,M.,Pietikainen,M. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2006
  • [5] Real-time Background Modeling/Subtraction using Two-Layer Codebook Model. Mohamad Hoseyn Sigari,Mahmood Fathy. Proceedings of International Multiconference of Engineers and Computer Scientists . 2008
  • [6] Foreground Object Detection from Videos Containing Complex Background. Li L Y,Huang W M,Irene Y H,et al. The eleventh ACM international conference on multimedia . 2003
  • [7] A system for video surveillance and monitoring. Collins R,Lipton A,Kanade T,et al. VSAM final report, Technical Report CMU-RI-TR-00-12 . 2000
  • [8] Adaptive background mixture models for real-time tracking. Stauffer C,Grimson WEL. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 1999