文章基本信息

标题：A Novel Visual Saliency Detection Method Using Motion Segmentation
本地全文：下载
作者：Man Hua ; Yanling Li
期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2016
卷号：11
期号：5
页码：417-424
DOI：10.14257/ijmue.2016.11.5.39
出版社：SERSC
摘要：In this paper, we propose a novel visual saliency detection method using motion segmentation. We group the corner point trajectories using a two stage clustering algorithm. The most stable trajectories are pre-clustered using mean shift in the first stage. Then, we propose an unsupervised clustering method to cluster the trajectories and detect the number of motions automatic. At last, the motion saliency map is generated with the segmented spare feature points. Experimental results show that our proposed method is capable of achieving both good accurate and the stable performance.
关键词：Visual saliency; Motion segmentation; Trajectory clustering