期刊文献+

基于混合高斯模型的多目标跟踪算法

Multi-Target Tracking Algorithm Based on Gaussian Mixture Model
下载PDF
导出
摘要 以杭州市的实际交通状况作为研究背景,提出了基于混合高斯模型的多目标跟踪算法的研究。通过建立基于灰度的混合高斯背景模型的基础上,利用当前帧和背景帧的差分,并经过形态学处理,提取目标的轮廓、重心等数学特征,建立目标特征向量组,提出使用相似度算子来搜索帧间特征向量匹配的目标。实验结果表明,该算法在强烈光照变化的动态背景下,能达到对目标的准确跟踪。
出处 《计算机系统应用》 2009年第9期26-29,共4页 Computer Systems & Applications
基金 国家自然科学基金(60573123)
  • 相关文献

参考文献9

  • 1Huwer S, Niemann H. Adaptive Change Detection for Real-time Surveillance Applications. Proceedings 3rd IEEE Intemational Workshop on Visual Surveillance. 2000:37 - 46.
  • 2Wem CR, Azarbaycjani A,Darrell T, et al. Pfmder: Real-time Tracking of Human Body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19:780 - 785.
  • 3Stauffer C, Grimson WEL. Adaptive Background Mixture Models for real-time Tracking. IEEE Conf, on CVPR. 1999,2:246 - 252.
  • 4Elgammal A, Harwood D, Davis L. Nonparametric model for background subtraction. Proceedings of the 6th European Conference on Computer Vision. Dublin, Ireland, 2000:751 - 767.
  • 5Gordon G; Darrel T, Harville M, et al. Background Estimation and Removal Based on Range and Color. IEEE Conf, on CVPR. 1999,2:459 -464.
  • 6Segen J, Pingali S. A camera-based system for tracking people in real time. Proceedings International Conference on Pattern recognition, Vienna, Austria, 1996:63 - 67.
  • 7Nummiaro K, Merier EK, Gool LV. An adaptive colorbased particle filter. Image and Vision Computing, 2003,21(1):99- 110.
  • 8Lee Mun-wai, Cohen I, Soon Ki-Jung. Particle filter with analytical inference for hunman body tracking. Proceedings of IEEE.
  • 9Collins RT. Mean-shift blob tracking through scale space. Proceedings of IEEE Computer Society Confer- ence on Computer Vision and Pattern Recongnition, Madison, W I,USA, 2003:234 - 240.

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