改进的基于统计模型的前景检测方法

被引:3
作者
强振平 [1 ]
刘辉 [2 ]
尚振宏 [2 ]
陈旭 [1 ]
机构
[1] 西南林业大学计算机与信息学院
[2] 昆明理工大学信息与自动化学院
关键词
前景检测; 背景模型; 统计模型; 贝叶斯决策; 阴影剔除;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
针对基于统计模型的前景检测方法进行改进:一方面,背景模型中记录特征向量属于背景的历史最大概率,在当前帧像素点特征向量与背景模型中已有特征向量匹配时,利用历史最大概率提高其更新速度,使其尽快融入背景;另一方面,对利用贝叶斯决策规则检测的前景目标,剔除其轮廓信息后与背景的空间特征进行匹配,减少阴影对前景检测的影响。实验结果表明,与MoG方法和Li的统计模型方法的前景检测相比,该方法在阴影剔除以及大目标物体遮挡背景恢复等方面都有明显改进。
引用
收藏
页码:1682 / 1685+1694 +1694
页数:5
相关论文
共 11 条
[1]  
Learning Patterns of Activity Using Real-Time Tracking. Stauffer C,Grimson WEL. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2000
[2]   基于改进高斯混合模型的前景检测 [J].
冯华文 ;
龚声蓉 ;
刘纯平 .
计算机工程, 2011, 37 (19) :179-182
[3]  
Pfinder: Real-time Tracking of the Human Body. Wren C,Azarbayejani A,Darrell T,et al. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1997
[4]  
Topology free hidden Markov models:application to background modeling. STENGER B,RAMESH V,PARAGIOS N,et al. Proceedings of the8th IEEE International Conference on Computer Vision . 2001
[5]  
Multi-layer background subtraction based on color and texture. YAO J,ODOBEZ J M. IEEE Conference on Computer Vision and Pattern Recognition . 2007
[6]  
Image difference threshold strategies and shadow detection. ROSIN P L,ELLIS T. Proceedings of the6th British Machine Vision Conference . 1994
[7]  
Foreground object detection in changing background based on color co-occurrence statistics. LI L Y,HUANG W M,GU I Y H,et al. Proceedings of the6th IEEE Workshop on Applications of Computer Vision . 2002
[8]  
Evaluation of background subtraction techniques for video surveillance. BRUTZER S,HOFERLIN B,HEIDEMANN G. 2011IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2011
[9]  
ViBe:A universal background subtraction algorithm for video sequences. BARNICH O,van DROOGENBROECK M. IEEE Transactions on Image Processing . 2011
[10]  
W4 : who? when? where?what ? A real time system for detecting and tracking people. Haritaoglu I,Harwood D,Davis L. Proceedings of IEEE International Conference on Face and Gesture Recognition . 1998