Graph Construction for Salient Object Detection in Videos

被引:9
作者
Fu, Keren [1 ,2 ]
Gu, Irene Y. H. [2 ]
Yun, Yixiao [2 ]
Gong, Chen [1 ]
Yang, Jie [1 ]
机构
[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai 200030, Peoples R China
[2] Chalmers Univ Technol, Dept Signals & Syst, S-41296 Gothenburg, Sweden
来源
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) | 2014年
关键词
Salient region detection; Graph construction; Video processing; Optical flows;
D O I
10.1109/ICPR.2014.411
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently many graph-based salient region/object detection methods have been developed. They are rather effective for still images. However, little attention has been paid to salient region detection in videos. This paper addresses salient region detection in videos. A unified approach towards graph construction for salient object detection in videos is proposed. The proposed method combines static appearance and motion cues to construct graph, enabling a direct extension of original graph-based salient region detection to video processing. To maintain coherence in both intra-and inter-frames, a spatial-temporal smoothing operation is proposed on a structured graph derived from consecutive frames. The effectiveness of the proposed method is tested and validated using seven videos from two video datasets.
引用
收藏
页码:2371 / 2376
页数:6
相关论文
共 19 条
[1]   SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].
Achanta, Radhakrishna ;
Shaji, Appu ;
Smith, Kevin ;
Lucchi, Aurelien ;
Fua, Pascal ;
Suesstrunk, Sabine .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281
[2]  
[Anonymous], 2010, P BRIT MACH VIS C
[3]  
[Anonymous], 2010, CVPR
[4]  
[Anonymous], CVPR
[5]  
[Anonymous], 2013, CVPR
[6]  
[Anonymous], WORKSH COMP ATT APPL
[7]  
[Anonymous], 2013, CVPR
[8]  
[Anonymous], 2012, ECCV
[9]  
[Anonymous], 2012, ECCV
[10]  
[Anonymous], 2013, CVPR