Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2012, Vol. 13 Issue (10): 736-749    DOI: 10.1631/jzus.C1200071
    
Non-interactive automatic video segmentation of moving targets
Yu Zhou, An-wen Shen, Jin-bang Xu
Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Non-interactive automatic video segmentation of moving targets
Yu Zhou, An-wen Shen, Jin-bang Xu
Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
 全文: PDF 
摘要： Extracting moving targets from video accurately is of great significance in the field of intelligent transport. To some extent, it is related to video segmentation or matting. In this paper, we propose a non-interactive automatic segmentation method for extracting moving targets. First, the motion knowledge in video is detected with orthogonal Gaussian-Hermite moments and the Otsu algorithm, and the knowledge is treated as foreground seeds. Second, the background seeds are generated with distance transformation based on foreground seeds. Third, the foreground and background seeds are treated as extra constraints, and then a mask is generated using graph cuts methods or closed-form solutions. Comparison showed that the closed-form solution based on soft segmentation has a better performance and that the extra constraint has a larger impact on the result than other parameters. Experiments demonstrated that the proposed method can effectively extract moving targets from video in real time.
关键词： Video segmentation;  Auto-generated seeds;  Cost function;  Alpha matte    
Abstract: Extracting moving targets from video accurately is of great significance in the field of intelligent transport. To some extent, it is related to video segmentation or matting. In this paper, we propose a non-interactive automatic segmentation method for extracting moving targets. First, the motion knowledge in video is detected with orthogonal Gaussian-Hermite moments and the Otsu algorithm, and the knowledge is treated as foreground seeds. Second, the background seeds are generated with distance transformation based on foreground seeds. Third, the foreground and background seeds are treated as extra constraints, and then a mask is generated using graph cuts methods or closed-form solutions. Comparison showed that the closed-form solution based on soft segmentation has a better performance and that the extra constraint has a larger impact on the result than other parameters. Experiments demonstrated that the proposed method can effectively extract moving targets from video in real time.
Key words: Video segmentation    Auto-generated seeds    Cost function    Alpha matte
收稿日期: 2012-03-15 出版日期: 2012-10-01
CLC:  TP751.1  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Yu Zhou
An-wen Shen
Jin-bang Xu

引用本文:

Yu Zhou, An-wen Shen, Jin-bang Xu. Non-interactive automatic video segmentation of moving targets. Front. Inform. Technol. Electron. Eng., 2012, 13(10): 736-749.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.C1200071    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2012/V13/I10/736

[1] Xiu-rui Geng, Lu-yan Ji, Kang Sun. 高光谱图像主成分非负矩阵分解方法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(5): 403-412.
[2] Li-gang Ma, Jin-song Deng, Huai Yang, Yang Hong, Ke Wang. 基于国产高分辨率遥感影像和面向对象多变量模型的城市土地利用分类[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(3): 238-248.