Space-Time Facet Model for Human Activity Classification

作者：Samanta Soumitra^*; Chanda Bhabatosh

来源：IEEE Transactions on Multimedia, 2014, 16(6): 1525-1535.

DOI：10.1109/TMM.2014.2326734

• Bag-of-words
• facet model
• human activity
• space time interest point

This paper presents a novel space-time feature-based human activity analysis system. We detect Space Time Interest Points (STIP) and generate their description based on the facet model. The proposed approach detects interest points in video data using the three-dimensional facet model efficiently. Then we describe each interest point by three-dimensional Haar wavelet transform and time derivatives of different order obtained from said facet model. Here we represent each video clip following the bag-of-words approach by learning feature specific dictionary. Finally, classification is done using non-linear SVM with chi(2)-kernel. We evaluate the performance of our system on standard datasets like Weizmann, KTH, UCF sports, ICD, UCF YouTube, and UCF50 and get better, or at least comparable results compared to other state-of-the-art systems.

• 出版日期2014-10