Simultaneous Joint and Object Trajectory Templates for Human Activity Recognition from 3-D Data

TL;DR

This paper introduces a novel approach for human activity recognition from 3-D joint and object trajectories, using dynamic time warping and wavelet features to handle variations and interactions, achieving superior results on challenging datasets.

Contribution

It presents a new method for generating joint and object activity templates and warping samples to these templates, effectively modeling human-object interactions in 3-D data.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively models human-object interactions in activity recognition

Handles variations in speed and style of actions

Abstract

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.