Video Supervoxels Using Partially Absorbing Random Walks
Publication in refereed journal


引用次數
替代計量分析
.

其它資訊
摘要Supervoxels have been widely used as a preprocessing step to exploit object boundaries to improve the performance of video processing tasks. However, most of the traditional supervoxel algorithms do not perform well in regions with complex textures or weak boundaries. These methods may generate supervoxels with overlapping boundaries. In this paper, we present the novel video supervoxel generation algorithm using partially absorbing random walks to get more accurate supervoxels in these regions. Our spatial-temporal framework is introduced by making full use of the appearance and motion cues, which effectively exploits the temporal consistency in video sequence. Moreover, we build a novel Laplacian optimization structure using two adjacent frames to make our approach more efficient. Experimental results demonstrated that our method achieved better performance than the state-of-the-art supervoxel algorithms.
著者Liang YL, Shen JB, Dong XP, Sun HQ, Li XL
期刊名稱IEEE Transactions on Circuits and Systems for Video Technology
出版年份2016
月份5
日期1
卷號26
期次5
出版社IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
頁次928 - 938
國際標準期刊號1051-8215
電子國際標準期刊號1558-2205
語言英式英語
關鍵詞Laplacian graph; optimization; partially absorbing random walk (PARW); supervoxel; video segmentation
Web of Science 學科類別Engineering; Engineering, Electrical & Electronic

上次更新時間 2021-01-03 於 02:00