Browse > Article

Shot Boundary Detection of Video Sequence Using Hierarchical Hidden Markov Models  

Park, Jong-Hyun (목포대학교 공과대학 전자공학과 영상 및 비디오 처리 연구실)
Cho, Wan-Hyun (전남대학교 자연과학대학 통계학과)
Park, Soon-Young (목포대학교 공과대학 전자공학과 영상 및 비디오 처리 연구실)
Abstract
In this paper, we present a histogram and moment-based vidoe scencd change detection technique using hierarchical Hidden Markov Models(HMMs). The proposed method extracts histograms from a low-frequency subband and moments of edge components from high-frequency subbands of wavelet transformed images. Then each HMM is trained by using histogram difference and directional moment difference, respectively, extracted from manually labeled video. The video segmentation process consists of two steps. A histogram-based HMM is first used to segment the input video sequence into three categories: shot, cut, gradual scene changes. In the second stage, a moment-based HMM is used to further segment the gradual changes into a fade and a dissolve. The experimental results show that the proposed technique is more effective in partitioning video frames than the previous threshold-based methods.
Keywords
Citations & Related Records
연도 인용수 순위
  • Reference
1 Y. Tonomura, K. Oisuji, A. Atsu, and Y.Ohba, 'Stored Video Handling Techniques,' MTT Rev. 5, pp. 60-82, 1993
2 L. R. Rabiner, B. H. Juang, 'An Introductionto Hidden Markov Models,' IEEE ASSP Mag.,vol. 3, no. 1, pp. 4-16, 1986   DOI   ScienceOn
3 Ingrid Daubechies, Ten Lectures on Wavelets,CBMS-NSF Regional Conference Series inApplied Mathematics, 1992
4 A. Hampapur, R. Jain, and T. Weymouth,'Digital Video Indexing in Multimedia Systems,' In Proc. of the Workshop on Indexingand Reuse in Muttimedia Sy stems. AAAI, Aug.1994
5 곽영경, 최윤석, 고성제, 'MPEG 비디오의 특성추출을 이용한 효과적인 장면전환 검출,' 한국통신학회논문지, Vol. 24, No. 8B, pp. 1567-1576,1999
6 Shahraray, B., 'Scene Change Detection andContent-Based Sampling Compression: AIgori-thins and Technologies,' In Proceedings, SPIE,pp. 2-13, Feb. 1995
7 Changliang Wang, Kap Luk Chan, and Stan Z.Li, 'Spatial-Frequency Analysis for Color ImageIndexing and Retrieval,' ICARCV '98, pp.1461-1465, 1998
8 N. V. Patel, I. K. Sethi, 'Video Shot Detectionand Characterization for Video Databases,'Pattem Recognition, pp. 583-592, 1997
9 Hong Heather Yu, Wayne Wolf, 'A Hierarchicalultiresolution Video Shot Tiansition DetectionScheme,' Computer Vision and Image Under-standing, vol. 75, pp. 196-213, 1999   DOI   ScienceOn
10 L. R. Rabiner, 'A Tutorial on Hidden MarkovModels and Selected Applications in SpeechRecognition,' Proc. IEEE, vol. 77, pp. 257-285, Feb. 1989   DOI   ScienceOn
11 Ferdinand van der Heijden, Image BasedMeasurement Systems, John Wiley & Son
12 Phillips. M., Wolf, W. 'Video SegmentationTechniques for New,' In MuItimedia Storageand Archiving Systems, SPIE, pp. 243-251,1996
13 J. Boreczky, L. Rowe, 'Comparison of VideoShot Boundary Detection Techniques,' InProceedings, SPIE '96, 1996