Simultaneous segmentation and classification of human actions in video streams using deeply optimized Hough transform

PATTERN RECOGNITION

卷:47

Article

Chan-Hon-Tong, Adrien¹  Achard, Catherine^2,3  Lucat, Laurent¹ 

[1] CEA, Ctr Etudes Saclay, LIST, Lab Vis & Ingn Contenus, F-91400 Orsay, France

[2] CNRS, ISIR, UMR 7222, F-75005 Paris, France

[3] Univ Paris 06, Sorbonne Univ, ISIR, UMR 7222, F-75005 Paris, France

关键词: Human actions;    Segmentation;    Classification;    Video streams;    Hough;   

DOI  :  10.1016/j.patcog.2014.05.010

来源: Elsevier

【 摘 要 】

Most researches on human activity recognition do not take into account the temporal localization of actions. In this paper, a new method is designed to model both actions and their temporal domains. This method is based on a new Hough method which outperforms previous published ones on honeybee dataset thanks to a deeper optimization of the Hough variables. Experiments are performed to select skeleton features adapted to this method and relevant to capture human actions. With these features, our pipeline improves state-of-the-art performances on TUM dataset and outperforms baselines on several public datasets. (C) 2014 Elsevier Ltd. All rights reserved.

【 授权许可】

Free