Object segmentation from wide baseline video
Refereed conference paper presented and published in conference proceedings

香港中文大學研究人員
替代計量分析
.

其它資訊
摘要In this paper, we propose an automatic approach to segment object from stereo videos, for which the viewpoints are widely apart. We first present a novel saliency analysis to emphasize the foreground object. The saliency map is estimated by combining the depth information recovered by feature matching and the boundary information revealed by color segmentation. The object mask is extracted initially based on the saliency map and then refined by graph-cut segmentation, where color and motion information are efficiently incorporated in both data and smoothness terms. Moreover, a background image is gradually reconstructed during video segmentation, based on which an additional constraint is imposed on the data term to further improve the video segmentation. The proposed method is tested on stereo videos with widely separated viewpoints and severe background clutters. Good experimental results demonstrate the feasibility of the proposed method. © 2013 IEEE.
著者Cui C., Zhang Q., Ngan K.N.
會議名稱2013 IEEE International Symposium on Circuits and Systems, ISCAS 2013
會議開始日19.05.2013
會議完結日23.05.2013
會議地點Beijing
會議國家/地區中國
詳細描述organized by IEEE,
出版年份2013
月份9
日期9
頁次717 - 720
國際標準書號9781467357609
國際標準期刊號0271-4310
語言英式英語

上次更新時間 2021-27-02 於 23:51