Adaptive Fibonacci Search Method of Video Key Frame Extraction

International Journal of Computer Trends and Technology (IJCTT)          
© 2019 by IJCTT Journal
Volume-67 Issue-10
Year of Publication : 2019
Authors : Baomin Shao, Hongyun Jia
DOI :  10.14445/22312803/IJCTT-V67I10P103


MLA Style:Baomin Shao, Hongyun Jia  "Adaptive Fibonacci Search Method of Video Key Frame Extraction," International Journal of Computer Trends and Technology 67.10 (2019):16-19.

APA Style Baomin Shao, Hongyun Jia. Adaptive Fibonacci Search Method of Video Key Frame ExtractionInternational Journal of Computer Trends and Technology, 67(10),16-19.

With the development of video techniques, one of the issues of building a proficient video processing system is to present a whole video with key frames to eliminate redundant information. This paper presented a novel video key frame extraction method using adaptive Fibonacci search algorithm. A pre-sampling was employed for selecting the suitable parameters for the sequence search process. After color and texture features were computed and combined, each frame was represented by a 92-dimensional feature vector, with the help of similarity measurement of frame combined feature vector, a divide-and-conquer searching method was executed. Experiments showed that this approach considerably reduced the processing time of each video while maintaining a similar precision and recall rates, at the same time, it could extract key frames from videos more effectively.

[1] D.B. Ponceleon, S. Srinivasan, A. Amir, D. Petkovic, D. Diklic, Key to effective video retrieval: effective cataloging and browsing, in: Proceedings of the ACM International Conference on Multimedia, 1998, pp. 99–107.
[2] B.T. Truong, S. Venkatesh, Video abstraction: a systematic review and classification, ACM Transactions on Multimedia Computing, Communications, and Applications 3 (1) (2007) 1–37.
[3] A.G. Money, H.W. Agius, Video summarization: a conceptual framework and survey of the state of the art, Journal of Visual Communication and Image Representation 19 (2) (2008) 121–143.
[4] S. Uchihashi and J. Foote, Summarizing video using a shot importance measure and a frame-packing algorithm, in IEEE ICASSP, 1999, vol. 6, pp. 3041-3044.
[5] Z. Rasheed and M. Shah, Detection and representation of scenes in videos, IEEE Trans. Multimedia, vol. 7, no. 6, pp. 1097-1105,Dec. 2005
[6] Y. Zhuang, Y. Rui, T. S. Huang and S. Mehrotra, Adaptive key frame extraction using unsupervised clustering, In Proceedings of IEEE International Conference on Image Processing (ICIP), 1998.
[7] Vasileios Chasanis, Aristidis Likas and Nikolaos Galatsanos,Video rushes summarization using spectral clustering and sequence alignment, Proceedings of the 2nd ACM TRECVid Video Summarization Workshop, 2008.
[8] G. Paschos, “Perceptually uniformcolor spaces for color texture analysis: an empirical evaluation,” IEEE Transactions on Image Processing, vol. 10, no. 6, pp. 932– 937, 2001.
[9] J. Almeida, N.J. Leite, R.S. Torres, VISON: video summarization for online applications, Pattern Recognition Letters 33 (4) (2012) 397–409.
[10] G. Paschos, Perceptually uniform color spaces for color texture analysis: an empirical evaluation, IEEE Transactions on Image Processing 10 (6) (2001) 932–937.
[11] B.S. Manjunath, J.R. Ohm, V.V. Vasudevan, A. Yamada, MPEG-7 color and texture descriptors, IEEE Transactions on Circuits and Systems for Video Technology 6 (11) (2000).

Key frame extraction, Video analysis, Fibonacci search, Image feature vector