Towards Fast View Invariant Human Action Recognition

In this paper, we propose a fast method to recognize human actions which accounts for intra-class variability in the way an action is performed. We propose the use of a low dimensional feature vector which consists of (a) the projections of the width profile of the actor on to an “action basis” and (b) simple spatio-temporal features. The action basis is built using eigenanalysis of walking sequences of different people. Given the limited amount of training data, Dynamic Time Warping (DTW) is used to perform recognition. We propose the use of the average-template with multiple features, first used in speech recognition, to better capture the intra-class variations for each action. We demonstrate the efficacy of this algorithm using our low dimensional feature to robustly recognize human actions. Furthermore, we show that view-invariant recognition can be performed by using a simple data fusion of two orthogonal views. For the actions that are still confusable, a temp...

• Type: Conference
• Year: 2008
• Where: Proceedings of the Ist Workshop on Computer Vision and Pattern Recognition for Human Computer Communicative Behavior held in conjunction with CVPR 2008 Anchorage Alaska.
• Authors: Srikanth Cherla, Kaustubh Kulkarni, Amit Kale and V. Ramasubramanian
• Keywords: Dynamic Time Warping, Human Action Recognition, View Invariance