유사도 기반 클러스터링을 사용한 샷 그룹 및 대표 샷 프레임 검출
Shot Group and Representative Shot Frame Detection using Similarity-based Clustering
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper introduces a method for video shot group detection needed for efficient management and summary of video. The proposed method detects shots based on low-level visual properties and performs temporal and spatial clustering based on visual similarity of neighboring shots. Shot groups created from temporal clustering are further clustered into small groups with respect to visual similarity. A set of representative shot frames are selected from each cluster of the smaller groups representing a scene. Shots excluded from temporal clustering are also clustered into groups from which representative shot frames are selected. A number of video clips are collected and applied to the method for accuracy of shot group detection. We achieved 91% of accuracy of the method for shot group detection. The number of representative shot frames is reduced to 1/3 of the total shot frames. The experiment also shows the inverse relationship between accuracy and compression rate.
Abstract
This paper introduces a method for video shot group detection needed for efficient management and summary of video. The proposed method detects shots based on low-level visual properties and performs temporal and spatial clustering based on visual similarity of neighboring shots. Shot groups created from temporal clustering are further clustered into small groups with respect to visual similarity. A set of representative shot frames are selected from each cluster of the smaller groups representing a scene. Shots excluded from temporal clustering are also clustered into groups from which representative shot frames are selected. A number of video clips are collected and applied to the method for accuracy of shot group detection. We achieved 91% of accuracy of the method for shot group detection. The number of representative shot frames is reduced to 1/3 of the total shot frames. The experiment also shows the inverse relationship between accuracy and compression rate.
참고문헌 (19)
- S. Liu, "Mining similarities for clustering web video clips", International Conference on Computer Science and Software Engineering, pp.759~762 (2008)
- S. Cheung, "Fast similarity search and clustering of video sequences on World Wide Web", IEEE Trans on Multimedia, 7(3), pp.524~537 (2004)
- Asghar, M. N., "Video indexing : a survey", International Journal of Computer and Information Tech, 3(1), pp.148~169 (2014)
- S.T. Dhagdi, "Keyframe based video summarization using automatic threshold & edge matching rate", International Journal of Scientific and Research Publications, 2(7)
- J. Baber, "A framework for video segmentation using global and local features", International Journal of Pattern Recognition and AI, 27(5), pp.1~29 (2013)
- X. Zhu, "Hierarchical video summarization and content description joint semantic and visual similarity", ACM, 2003, pp.9(1), 31~53
- Video Clustering, "A. Vailaya", Michigan State University, ~, pp.TR96-64 (1996)
- J. Foo, "Clustering Near-Duplicate Images in Large Collections", Proceedings of the International Workshop on Multimedia Information Retrieval, pp.21~30 (2007)
- M. Flickner, "Query by image and video content : the QBIC system", Computer, 28(9), pp.23~32 (1995)
- S. V. Porter, "Video segmentation and indexing using motion estimation", Ph.D., pp.2004
- Z. Cernekova, "Information theory-based shot cut", fade detection and video summarization, 2006, pp.16(1), 82~91[DOI]
- J. Calic, "Efficient key-frame extraction and video analysis", Proceedings of International Conference on IEEE, pp.28~33 (2002)
- Y. Zhuang, "Adaptive key frame extracting using unsupervised clustering", Proceedings of International Conference on Image Processing, 1, pp.582~585 (2002)
- A. Hanjalic, "Automated high level movie segmentation for advance video retrieval systems", IEEE Trans. on Circuits and Systems for Video Technology, 9(4), pp.580~588 (1999)
- L. H. Chen, "Movie scene segmentation using background information", Pattern Recognition, 41(3), pp.1056~1065 (2008)
- 신동욱, "시각적 특징을 기반한 샷 클러스터링을 통한 비디오 씬 탐지 기법", 지능정보연구, 18(2), pp.47~60 (2012), 한국지능정보시스템학회[DOI]
- M. Yeung, "Segmentation of video by clustering and graph analysis", Computer Vision and Image Understanding, 71(1), pp.94~109 (1998)
- 김승현, "프레임 블록화와 객체의 이동을 이용한 샷 전환 탐지 알고리즘", 한국컴퓨터정보학회논문지, 20(5), pp.21~29 (2015), 한국컴퓨터정보학회
- 신성윤, "대용량 비디오 데이터베이스 구축을 위하여 장면전환 검출과 샷 클러스터링을 이용한 비디오 개요 추출", 한국컴퓨터정보학회논문지, 11(2), pp.111~120 (2006), 한국컴퓨터정보학회