Finding spatio-temporal salient paths for video objects discovery

详细信息    查看全文

• 作者：Ye Luo^a ; ^{luoy0009@e.ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; Junsong Yuan^b ; ^{jsyuan@ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; Jianwei Lu^a ; ^{jwlu33@tongji.edu.cn" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Spatio-temporal path ; Salient object detection ; Temporal coherence ; Video saliency estimation ; Saliency density ; Dynamic programming ; Salient path discovery ; Computer vision
• 刊名：Journal of Visual Communication and Image Representation
• 出版年：2016
• 出版时间：July 2016
• 年：2016
• 卷：38
• 期：Complete
• 页码：45-54
• 全文大小：3861 K

文摘

Many videos capture and follow salient objects in a scene. Detecting such salient objects is thus of great interests to video analytics and search. However, the discovery of salient objects in an unsupervised way is a challenging problem as there is no prior knowledge of the salient objects provided. Different from existing salient object detection methods, we propose to detect and track salient object by finding a spatio-temporal path which has the largest accumulated saliency density in the video. Inspired by the observation that salient video objects usually appear in consecutive frames, we leverage the motion coherence of videos into the path discovery and make the salient object detection more robust. Without any prior knowledge of the salient objects, our method can detect salient objects of various shapes and sizes, and is able to handle noisy saliency maps and moving cameras. Experimental results on two public datasets validate the effectiveness of the proposed method in both qualitative and quantitative terms. Comparisons with the state-of-the-art methods further demonstrate the superiority of our method on salient object detection in videos.