A Biologically Inspired System for Action Recognition
Top Cited Papers
- 1 January 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
- https://doi.org/10.1109/iccv.2007.4408988
Abstract
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 motion- direction 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 achieving the highest results reported to date.Keywords
This publication has 27 references indexed in Scilit:
- A Hierarchical Model of Shape and Appearance for Human Action ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A Model of Biological Motion Perception from Configural Form CuesJournal of Neuroscience, 2006
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal WordsPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- Event-based analysis of videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A stochastic model for the detection of coherent motionBiological Cybernetics, 2004
- Neural mechanisms for the recognition of biological movementsNature Reviews Neuroscience, 2003
- Adaptive background mixture models for real-time trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Parameterized Modeling and Recognition of ActivitiesComputer Vision and Image Understanding, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Spatial summation in the receptive fields of simple cells in the cat's striate cortex.The Journal of Physiology, 1978