A Biologically Inspired System for Action Recognition

We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feedforward architectures [25, 16, 20] and extends a neurobiological model of motion processing in the visual cortex [10]. The system consists of a hierarchy of spatio-temporal feature detectors of increasing complexity: an input sequence is first analyzed by an array of motiondirection sensitive units which, through a hierarchy of processing stages, lead to position-invariant spatio-temporal feature detectors. We experiment with different types of motion-direction sensitive units as well as different system architectures. As in [16], we find that sparse features in intermediate stages outperform dense ones and that using a simple feature selection approach leads to an efficient system that performs better with far fewer features. We test the approach on different publicly available action datasets, in all cases ...

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Poggio
• Keywords: Computer Vision, Feature Selection Approach, Hierarchical Feedforward Architectures, ICCV 2007, Position-invariant Spatio-temporal Feature, Sensitive Units, Spatio-temporal Feature Detectors