混合高斯模型的自适应前景提取

被引:23
作者
李百惠
杨庚
机构
[1] 南京邮电大学计算机学院
基金
中国博士后科学基金; 高等学校博士学科点专项科研基金;
关键词
混合高斯模型; 前景提取; 背景建模; 动态控制;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
复杂场景下的运动前景提取是计算机视觉研究领域的研究重点。为解决复杂场景中的前景目标提取问题,提出一种应用于复杂变化场景中的基于混合高斯模型的自适应前景提取方法。该方法可以对视频帧中每个像素的高斯分布数进行动态控制,并且通过在线期望最大化(EM)算法对高斯分布的各参数进行学习,此外每个像素的权值更新速率可根据策略进行调整。实验结果表明,该方法对复杂变化场景具有较好的适应性,可有效、快速地提取前景目标,提取结果具有较好的查准率和查全率。
引用
收藏
页码:1620 / 1627
页数:8
相关论文
共 12 条
[1]  
Background modeling method based on improved multi-Gaussian distribution. Kan J,Li K,Tang,J et al. Proceedings of IEEE International Conference on Computer Application and System Modeling . 2010
[2]  
Spatio-temporal nonparametric background modeling and subtraction. Vemulapalli R,Aravind R. Proceedings of IEEE12th International Conference on Computer Vision Workshops . 2009
[3]  
An improved Gaussian mixture background model with real-time adjustment of learning rate. Li Ying-hong,Tian Hong-fang,Zhang Yan. Information Networking and Automation (ICINA),2010 International Conference . 2010
[4]  
Dynamic Control of Adaptive Mixture-of-Gaussians Background Model. Shimada A,Arita D. Proceedings of the IEEE In-ternational Conference on Video and Signal Based Surveillance . 2006
[5]  
Non-parametric background and shadow modeling for object detection. Tanaka T,Shimada A,Arita D,et al. Proceedings of 8th Asian Conference on Computer Vision . 2007
[6]  
Adaptive background mixture models for real-time tracking. Stauffer C, Grimson W. Proceedings of IEEE Computer Soclety Conference on Computer Vision and Pattern Recognition . 1999
[7]  
A Novel Split and Merge EM Algorithm for Gaussian Mixture Model. Li Y,Li L. processings of the 5th International Conference on Natural Computation . 2009
[8]  
Fast background modeling object detection using PCA and temporal difference. Liu P,Lee B. Proceedings of IEEE International Conference on Advance in Engineering,Science and Management . 2012
[9]  
An Improved Adaptive Background Mixture Model for Real time Tracking with Shadow Detection. P KaewTraKulPong,R Bowden. Video Based Surveillance Systems . 2002
[10]  
Wallflower : Principles and practice of background maintenance. Toyama K, Krumm J, Brumitt B, et al. The Proceeding of the Seventh IEEE International Conference on Computer Vision . 1999