Qualitative Spatio-temporal Reasoning Based Group Activity Recognition
Yiting Liu · Journal of Information and Computational Science · 2014
Human group activity recognition is still a challenging task in computer vision. However, most of the works focus on the feature extraction and the analysis of the motion trajectories for recognizing the multi-person or group activities in surveillance videos. A qualitative spatio-temporal relation based on Hidden Markov Model (HMM) method is proposed to classify human group activities. We first propose Unified QTCB relations to represent the relations of the group. And then Unified QTCB relation based on HMM is proposed for group activity classification. Experiments are successfully conducted on the human group activity video database, and the performance of our approach is evaluated and compared with some other methods. The results show that our approach is more suitable for recognizing group activities.