원문정보
보안공학연구지원센터(IJMUE)
International Journal of Multimedia and Ubiquitous Engineering
Vol.11 No.5
2016.05
pp.417-424
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
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.
목차
Abstract
1. Introduction
2. Motion Segmentation Based on Trajectory Clustering
2.1. Trajectory Feature Extraction
2.2. The Preprocessing Based on Mean Shift
2.3. Unsupervised Clustering Algorithm of Motion Vector
3. Generation of Saliency Map
4. Experimental Results
5. Conclusion
References
1. Introduction
2. Motion Segmentation Based on Trajectory Clustering
2.1. Trajectory Feature Extraction
2.2. The Preprocessing Based on Mean Shift
2.3. Unsupervised Clustering Algorithm of Motion Vector
3. Generation of Saliency Map
4. Experimental Results
5. Conclusion
References
저자정보
참고문헌
자료제공 : 네이버학술정보