[1] Wang Yujian, Wu Zhenyang,. Motion connectivity-based initial video object extraction [J]. Journal of Southeast University (English Edition), 2007, 23 (4): 500-506. [doi:10.3969/j.issn.1003-7985.2007.04.005]
Copy
Motion connectivity-based initial video object extraction(
)
基于运动连通性的初始视频对象提取
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 23
- Issue:
- 2007 4
- Page:
- 500-506
- Research Field:
- Information and Communication Engineering
- Publishing date:
- 2007-12-30
Info
- Title:
- Motion connectivity-based initial video object extraction
- 基于运动连通性的初始视频对象提取
- Author(s):
- Wang Yujian1; 2; Wu Zhenyang1
-
1 School of Information Science and Engineering, Southeast University, Nanjing 210096, China
2CBG/MMPD, Alcatel-Lucent Shanghai Bell Co.Ltd., Shanghai 201206, China
- Keywords:
- video object extraction; motion connectivity; adaptive threshold; cumulated difference image
- PACS:
- TN911.73
- DOI:
- 10.3969/j.issn.1003-7985.2007.04.005
- Abstract:
- In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed.Moving objects in video sequences are highly connected and structured, which makes motion connectivity an advanced feature for segmentation.Accordingly, after sharp noise elimination, the cumulated difference image, which exhibits the coherent motion of the moving object, is adaptively thresholded.Then the maximal connected region is labeled, post-processed and output as the final segmenting mask.Hence the initial video object is effectively extracted. Comparative experimental results show that the proposed algorithm extracts the initial video object automatically, promptly and properly, thereby achieving satisfactory subjective and objective performance.
- 为了从视频序列中获取初始视频对象, 提出了一种改进的基于运动连通性的初始视频对象提取算法.视频中的运动对象高度连通结构化, 这就使得运动连通性是适用于视频对象分割的高级特征.据此首先对反映对象的一致性运动的累计帧差图进行尖锐噪声滤除, 然后应用自适应阈值算法提取对象运动区域, 接着根据运动连通性标记出最大连通区域, 通过后处理得到视频对象的分割模版从而有效提取出初始视频对象.对比实验结果表明, 该算法能自动、快速、准确地提取出初始视频对象, 获得了理想的主客观分割效果.
References:
[1] Meier T, Ngan K N.Automatic segmentation of moving objects for video object plane generation [J].IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5):525-538.
[2] Liang T M, Tang D X, Chen J.Research and implementation of a video object extraction system [J].Computer Engineering, 2003, 29(1): 182-193.
[3] Radke R J, Andra S, Al-Kofahi O, et al.Image change detection algorithms:a systematic survey [J].IEEE Transactions on Image Processing, 2005, 14(3):294-307.
[4] Neri A, Colonnese S, Russo G, et al.Automatic moving object and background separation [J].Signal Processing, 1998, 66(2):219-232.
[5] Mech R, Wollborn M.A noise robust method for segmentation of moving objects in video sequences [C]//Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing.Munich, Germany, 1997:2657-2660.
[6] Zheng H, Pan L.The automatic selection of image threshold on the basis of genetic algorithms [J].Journal of Image and Graphics, 1999, 4(4):327-330.
[7] Aach T, Kaup A, Mester R.Statistical model-based change detection in moving video [J].Signal Processing, 1993, 31(2):165-180.
[8] Kim C, Hwang J.Fast and automatic video object segmentation and tracking for content-based applications [J].IEEE Transactions on Circuits and Systems for Video Technology, 2002, 12(2):122-129.
[9] Liu M Y, Dai Q H, Liu X D, et al.Automatic extraction of initial moving object based on advanced feature and video analysis [C]//Proceedings of Visual Communication and Image Processing.Beijing, China, 2005:160-168.
[10] Wang Y J, Gao J P, Wu Z Y.A novel video object spatial segmenting strategy based on morphological filtering [C]//Proceedings of International Conference on Computational Intelligence and Security.Guangzhou, China, 2006:1677-1682.
Memo
- Memo:
- Biographies: Wang Yujian(1980—), male, doctor, yujian.wang@alcatel-sbell.com.cn;Wu Zhenyang(1949—), male, professor, zhenyang@seu.edu.cn.