Video Shot Boundary Detection in Sport Video Using the Scale Invariant Feature Transform

Abstract:

The main purpose of shot boundary detection is to detect visual content changes between consecutives frames of a video. In this paper, a new shot boundary detection algorithm is proposed based on the scale invariant feature transform (SIFT). The first stage consists on a top down search scheme to detect the locations of transitions by comparing the ratio of matched features extracted via SIFT for every RGB channel of video frames. A temporal sampling period is used to avoid the frame by frame processing. The overview step provides the changes of matched features ratio all along the video. Secondly, a function is performed to detect the shot boundaries. The proposed method can be used for detecting gradual transitions as well as hard cuts and without requiring any training of the video content in advance. Experiments have been conducted on sports video and show that this algorithm achieves good results in detecting both abrupt and gradual transitions.

• Periodical: Applied Mechanics and Materials (Volume 850)
• Pages: 152-158
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.850.152
• Online since: August 2016
• Authors: Zaynab El Khattabi*, Youness Tabii, Abdelhamid Benkaddour
• Keywords: Abrupt Change, Gradual Transition, Scale Invariant Feature Transform (SIFT), Shot Boundary Detection (SBD)

References

[1] T. Mei, L. -X. Tang, J. Tang, X. -S. Hua, Near-Lossless Semantic Video Summarization and Its Applications to Video Analysis, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 9(3), (June 2013).

DOI: 10.1145/2487268.2487269

[2] R. Thompson, Grammar of the Shot, Focal Press, (1998).

[3] J. S. Boreczky, L. A. Rowe, Comparison of video shot boundary detection techniques, Journal of Electronic Imaging, 5(2): 122-128, (April 1996).

DOI: 10.1117/12.238675

[4] R. G. Tapu, Segmentation and structuring of video documents for indexing applications, (December 2012).

[5] G. Jaffre, Ph. Joly, S. Haidar, 'The SAMOVA Shot Boundary Detection for TRECVID Evaluation 2004', Proceedings of the TRECVID 2004 Workshop, Gaithersburg, MD, USA, NIST, (2004).

[6] B. Shahraray, 'Scene change detection and content-based sampling of video sequences', Proc. SPIE Digital Video Compression: Algorithms and Technologies, 2419: 2–13, (1995).

DOI: 10.1117/12.206348

[7] C. -L. Huang, B. -Y. Liao, A robust scene-change detection method for video segmentation, IEEE Transactions on Circuits and Systems for Video Technology, 11(12): 1281 – 1288, (December 2001).

DOI: 10.1109/76.974682

[8] D.S. Guru, M. Suhil , Histogram Based Split and Merge Framework for Shot Boundary Detection, Mining Intelligence and Knowledge Exploration, Lecture Notes in Computer Science, 8284: 180-191, (December, 2013).

DOI: 10.1007/978-3-319-03844-5_19

[9] R. S. Jadon, S. Chaudhury, K. K. Biswas, A fuzzy theoretic approach for video segmentation using syntactic features, Pattern Recognition Letters, 22(13): 1359–1369, (November 2001).

DOI: 10.1016/s0167-8655(01)00041-1

[10] P. Aigrain, H. Zhang, D. Petkovic, 'Content-Based Representation and Retrieval of Visual Media: A State-of-the-Art Review', Multimedia Tools and Applications, 3(3): 179-202, (November 1996).

DOI: 10.1007/bf00393937

[11] P. Panchal, S. Merchant and N. Patel, Scene detection and retrieval of video using motion vector and occurrence rate of shot boundaries, 2012 Nirma University International Conference on Engineering (NUiCONE), 1-6 , (December 2012).

DOI: 10.1109/nuicone.2012.6493257

[12] S. Manjunath, D. S. Guru, M. G. Suraj, B. S. Harish, A Non Parametric Shot Boundary Detection: An Eigen Gap based Approach", COMPUTE , 11 Proceedings of the Fourth Annual ACM Bangalore Conference, N° 14: 1-7, India, (March 2011).

DOI: 10.1145/1980422.1980436

[13] D. Lowe, Distinctive image features from scale invariant keypoints, International Journal of Computer Vision, 60 (2): 91-110, (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

[14] M. Birinci, S. Kiranyaz, A perceptual scheme for fully automatic video shot boundary detection, Signal Processing: Image Communication, 29(3): 410–423, (March 2014).

DOI: 10.1016/j.image.2013.12.003