期刊名称：Journal of Theoretical and Applied Computer Science
印刷版ISSN：2299-2634
电子版ISSN：2300-5653
出版年度：2016
卷号：10
期号：1
页码：11-18
出版社：Polska Akademia Nauk * Oddzial w Gdansku, Komisja Informatyki,Polish Academy of Sciences, Gdansk Branch, Computer Science Commission
摘要：This paper presents an approach for action recognition based on binary silhouette se-quences extracted from consecutive frames of a video. It uses shape descriptors and corre-lation coefficient to represent and match entire sequences, regardless the number of frames. Each set of binary silhouettes corresponds to one action, such as jumping or waving. The paper provides experimental results on the use of the proposed approach and four shape description algorithms, namely the Two-Dimensional Fourier Descriptor, Generic Fourier Descriptor, Point Distance Histogram and UNL-Fourier Descriptor. The results are ana-lysed in terms of the highest classification accuracy and the smallest shape descriptor size.
