Generic Neighborhood Operators
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual learning and recognition of 3-D objects from appearance
International Journal of Computer Vision
Spatiotemporal energy-based method for velocity estimation
Signal Processing
Feature Detection with Automatic Scale Selection
International Journal of Computer Vision
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Visual Recognition Using Local Appearance
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Pfinder: real-time tracking of the human body
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
An Appearance-Based Representation of Action
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Parameterized Modeling and Recognition of Activities
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Computer Vision and Image Understanding
Local descriptors for spatio-temporal recognition
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Efficient descriptor tree growing for fast action recognition
Pattern Recognition Letters
| Hi-index | 0.00 |
This paper presents a new technique for the perception and recognition of activities using statistical descriptions of their spatio-temporal properties. A set of motion energy receptive fields is designed in order to sample the power spectrum of a moving texture. Their structure relates to the spatio-temporal energy models of Adelson and Bergen where measures of local visual motion information are extracted by comparing the outputs of a triad of Gabor energy filters. Then the probability density function required for Bayes rule is estimated for each class of activity by computing multi-dimensional histograms from the outputs from the set of receptive fields. The perception of activities is achieved according to Bayes rule. The result at each instant of time is the map of the conditional probabilities that each pixel belongs to each one of the activities of the training set. Since activities are perceived over a short integration time, a temporal analysis of outputs is done using Hidden Markov Models. The approach is validated with experiments in the perception and recognition of activities of people walking in visual surveillance scenari. The presented work is in progress and preliminary results are encouraging, since recognition is robust to variations in illumination conditions, to partial occlusions and to changes in texture. It is shown that it constitute a powerful early vision tool for human behaviors analysis for smart-environnements.