基于2D时空熵门限的运动目标检测
The Moving Object Detection Based on 2D Spatio-temporal Entropic Thresholding
-
摘要: 该文给出一种基于二维(2D)时空熵门限进行运动目标检测的方法。研究了几种通用运动目标检测方法的特点,运用2D熵门限分割方法检测运动目标的结构区域,在2D熵门限的基础上,提出了一种快速熵门限求解算法。实验结果表明,这种方法可以很好地检测出运动目标,同时可大大提高运算速度。
-
关键词:
- 运动目标检测; 二维熵门限; 形态学方法
Abstract: A method of moving object detection based on two dimensional (2D) spatio-temporal entropic thresholding is proposed in this paper. The characteristics of several common approaches for moving object detection are analyzed, and 2D entropic thresholding method is used to detect the structural region of the moving object. The 2D thresholding method is first deduced. A fast algorithm for entropic thresholding is put forward. The experimental results show that this method can be used to detect the moving object, and reduce the computational time efficiently. -
Forsyth D A, Ioffe S, Haddon J. Bayesian structure from motion.The Proc. of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, Sept 1999, vol. 1: 660 - 665.[2]Wang D. Unsupervised video segmentation based on watersheds and temporal tracking[J].IEEE Trans. on Circuits and Systems for Video Technology.1998, 8(5):539-[3]Bilal Ahmad M, Tae-Sun Choi. Edge detection-based block motion estimation. Electronics Letters, 2001, 37(1): 136 - 144.[4]Fan Jianping, Zhu Xingquan, Wu Lide. Automatic model-based semantic object extraction algorithm[J].IEEE Trans. on Circuits and Systems for Video Technology.2001, 11(10):1073-[5]Fan J, Elmagarmid A K. Statistical approaches to tracking-based moving object extraction.The Proc. of 1999 International Conference on Information Intelligence and Systems, Bethesda,MD, USA, 31 Oct. - 3 Nov. 1999:375 - 381.[6]Abutaleb A S. Automatic thresholding of gray level pictures using two-dimensional entropy[J].Computer Vision Graphics Image Process.1989, 47(1):22-[7]Brink A D. Thresholding of digital images using two dimensional entropies[J].Pattern Recognition.1992, 25 (8):803-[8]Wang Qing, Wang Qiurang, Feng D D, et al.. A fast 2D entropic thresholding method by wavelet decomposition. The Proceedings of 2002 International Conference on Image Processing, Rochester,New York, June 2002, vol.3:265 - 268. -
计量
- 文章访问数: 2413
- HTML全文浏览量: 114
- PDF下载量: 765
- 被引次数: 0
下载:
