Simultaneous Joint and Object Trajectory Templates for Human Activity Recognition from 3-D Data
This work addresses the problem of robust human activity recognition for applications like surveillance or human-computer interaction, but it appears incremental as it builds on existing template and warping techniques.
The paper tackled human activity recognition from 3-D skeleton data by proposing a method that generates action templates and uses temporal warping with wavelet features to handle speed and style variations, achieving state-of-the-art results on challenging datasets.
The availability of low-cost range sensors and the development of relatively robust algorithms for the extraction of skeleton joint locations have inspired many researchers to develop human activity recognition methods using the 3-D data. In this paper, an effective method for the recognition of human activities from the normalized joint trajectories is proposed. We represent the actions as multidimensional signals and introduce a novel method for generating action templates by averaging the samples in a "dynamic time" sense. Then in order to deal with the variations in the speed and style of performing actions, we warp the samples to the action templates by an efficient algorithm and employ wavelet filters to extract meaningful spatiotemporal features. The proposed method is also capable of modeling the human-object interactions, by performing the template generation and temporal warping procedure via the joint and object trajectories simultaneously. The experimental evaluation on several challenging datasets demonstrates the effectiveness of our method compared to the state-of-the-arts.