Summarization of human activity videos via low-rank approximation
Ioannis Mademlis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Abstract
Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic solutions for key-frame extraction. This work presents a method based on selecting as key-frames video frames able to optimally reconstruct the entire video. The novelty lies in modelling the reconstruction algebraically as a Column Subset Selection Problem (CSSP), resulting in extracting key-frames that correspond to elementary visual building blocks. The problem is formulated under an optimization framework and approximately solved via a genetic algorithm. The proposed video summarization method is being evaluated using a publicly available annotated dataset and an objective evaluation metric. According to the quantitative results, it clearly outperforms the typical clustering approach.
BibTeX
@inproceedings{icassp2017_summarizationofh,
title = {Summarization of human activity videos via low-rank approximation},
author = {Ioannis Mademlis and Anastasios Tefas and Nikos Nikolaidis and Ioannis Pitas},
booktitle = {ICASSP 2017},
year = {2017}
}