Abstract | ||
---|---|---|
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 appro- priate points on the feature vector curve, which represent in an op- timal 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 inter- polation 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. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICME.2002.1035777 | Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference |
Keywords | Field | DocType |
content-based retrieval,database indexing,feature extraction,genetic algorithms,interpolation,minimisation,video databases,approximation error minimization,characteristic frames/shots,estimated points,feature extraction,feature vector curve,genetic algorithm,interpolation,key-frames/shots,optimal efficient algorithm,temporal variations,video summarization,video visual content | Automatic summarization,Feature vector,Brute-force search,Pattern recognition,Computer science,Interpolation,Feature extraction,Minimisation (psychology),Artificial intelligence,Genetic algorithm,Approximation error | Conference |
Volume | Citations | PageRank |
1 | 8 | 0.71 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nikolaos Doulamis | 1 | 691 | 80.72 |
Anastasios D. Doulamis | 2 | 883 | 93.64 |
Klimis S. Ntalianis | 3 | 66 | 15.74 |