지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2011.7
- 수록면
- 151 - 154 (4page)
이용수
초록· 키워드
오류제보하기
In this paper, we propose the motion distribution and key-frame descriptor based on shot change for near-duplication video contents detection. The motion distribution descriptor of motion distribution histogram in shot is constructed using motion vectors of the macro-block that are gained by video decoding process. We use the motion distribution descriptor for pre-filtering to increase the matching speed. To improve the discriminability, we use the frame descriptor of key-frame which is selected from segmented shot through filtering to determine whether the video is duplicated or not. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast. We confirm that the proposed algorithm can be useful for practical application.
목차
Abstract
1. Introduction
2. Proposed Algorithm
3. Experiments
4. Conclusion
Acknowledgement
5. References
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2013-004-000826841