An optimal interpolation-based scheme for video summarization

N. Doulamis1, A. Doulamis1, K. Ntalianis1
1Electrical and Computer Engineering Department, National and Technical University of Athens, Athens, Greece

Tóm tắt

In this paper, an optimal and efficient algorithm for video summarization is proposed by exploiting temporal variations of video visual content. In particular, the most characteristic frames/shots (key-frames/shots) are extracted by estimating appropriate points on the feature vector curve, which represent in an optimal way the corresponding trajectory. This is performed by minimizing the approximation error of the feature vector curve and the respective curve formed by the estimated points using an interpolation scheme. A genetic algorithm is used for the minimization task, since the complexity of an exhaustive search is too large to be implemented. Furthermore, a fast technique for increasing the number of extracted key-frames/shots is presented.

Từ khóa

#Data mining #Video sequences #Genetic algorithms #Minimization methods #Cameras #Clustering algorithms #Content based retrieval #Stochastic processes #Sampling methods #Approximation algorithms

Tài liệu tham khảo

10.1109/IVL.1998.694508 goldberg, 1989, Genetic Algorithm in Search Optimization and Machine Learning 10.1109/76.844996 10.1109/30.883444 annan, 1994, Content-based browsing of video sequences, In ACM Multimedia, 77 10.1016/S0031-3203(96)00114-8 yeo, 1995, Rapid scene analysis on compressed videos, IEEE Trans CSVT, 5, 533 avrithis, 1999, Optimization methods for key frames and scenes extraction, Comput Vision and Image Underst, 75, 3, 10.1006/cviu.1999.0761 10.1109/76.809162 10.1109/CVPR.1998.698631 10.1109/5.664279 10.1109/93.311653 10.1016/S0165-1684(00)00019-0 yeo, 1995, Rapid scene analysis on compressed videos, IEEE Trans CSVT, 5, 533