5 March 2014 Human interaction recognition through two-phase sparse coding
Author Affiliations +
In this paper, we propose a novel method to recognize two-person interactions through a two-phase sparse coding approach. In the first phase, we adopt the non-negative sparse coding on the spatio-temporal interest points (STIPs) extracted from videos, and then construct the feature vector for each video by sum-pooling and l2-normalization. At the second stage, we apply the label-consistent KSVD (LC-KSVD) algorithm on the video feature vectors to train a new dictionary. The algorithm has been validated on the TV human interaction dataset, and the experimental results show that the classification performance is considerably improved compared with the standard bag-of-words approach and the single layer non-negative sparse coding.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
B. Zhang, B. Zhang, N. Conci, N. Conci, Francesco G. B. De Natale, Francesco G. B. De Natale, "Human interaction recognition through two-phase sparse coding", Proc. SPIE 9026, Video Surveillance and Transportation Imaging Applications 2014, 90260F (5 March 2014); doi: 10.1117/12.2041206; https://doi.org/10.1117/12.2041206

Back to Top