Spatio-Temporal Video Slice Edges Analysis for Shot Transition Detection and Classification

Authors: Aissa Saoudi, Hassane Essafi

Abstract:

In this work we will present a new approach for shot transition auto-detection. Our approach is based on the analysis of Spatio-Temporal Video Slice (STVS) edges extracted from videos. The proposed approach is capable to efficiently detect both abrupt shot transitions 'cuts' and gradual ones such as fade-in, fade-out and dissolve. Compared to other techniques, our method is distinguished by its high level of precision and speed. Those performances are obtained due to minimizing the problem of the boundary shot detection to a simple 2D image partitioning problem.

Keywords: Boundary shot detection, Shot transition detection, Video analysis, Video indexing.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1080255

References:

[1] T. Kikukawa, S.K., Development of an automatic summary editing system for the audio-visual resources. Transactions on Electronics and Information, 1992: p. J75-A(2):204-212,
[2] HongJiang Zhang, A.K., Stephen W. Smoliar Automatic partitioning of full-motion video. 1993. 1(1): p. 10-28
[3] Ishwar K Sethi, N.P., A statistical approach to scene Change Detection. 1995. Vol. 2420.
[4] Ramin Zabih , J.M., Kevin Mai A feature-based algorithm for detecting and classifying production effects. Multimedia Systems, 1999. 7(2): p. 119 - 128.T
[5] A. Akutsu, Y.T., H. Hashimoto, and Y. Ohba, Video indexing using motion vectors. SPIE Visual Communication and Image Processing, 1992. 1818: p. 1522-1530.
[6] Shahraray., B., Scene change detection and content-based sampling of video sequences. SPIE Conference on Digital Video Compression: Algorithms and Technologies, 1995. 2419(2-13).
[7] Sarah, Segmentation and Indexing using Motion Estimation. 2004, University of Bristol.
[8] Chou, S.-C.P.Y.-Z., Effective wipe detection in MPEG compressed video using macro block type information. Multimedia, IEEE Transactions on, 2002. 4(3).
[9] Fernando W.A.C, L.K.K., Abrupt and gradual scene transition detection in MPEG-4 compressed video sequences using texture and macroblock information. Image Processing, 2004. 3: p. 1589-1592.
[10] De Bruyne Sarah, D.N.W., De Wolf Koen, De Schrijver Davy, Verhoeve Piet, Van de Walle Rik, Temporal Video Segmentation on H.264/AVC Compressed Bitstreams. Proceedings of the 13th International Multimedia Modeling Conference, LNCS 4351 Advances in Multimedia Modeling., 2007. 1: p. 1-12.T
[11] Edward H. Adelson, J.R.B., Spatiotemporal energy models for the perception of motion. Journal of optical America, 1985. 2 No 2: p. 284- 299.
[12] C. W. Ngo, T.C.P., R. T. Chin, Camera Breaks Detection by Partitioning of 2D Spatio-temporal Images in MPEG Domain. IEEE Multimedia System 1999. 1.T
[13] Deriche, R., Using Canny's criteria to derive an optimal edge detector recursively implemented. Internat J Comp Vision,1(2), 1987: p. 167-187.
[14] J. Sauvola, M.P.i., Adaptive document image binarization. Pattern Recognition, 2000. 33 (2000): p. 225-236.