Making Action Recognition Robust to Occlusions and Viewpoint Changes

Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single location independent histogram. This limits their performance in presence of occlusions and when running on multiple viewpoints. We propose a novel approach to providing robustness to both occlusions and viewpoint changes that yields significant improvements over existing techniques. At its heart is a local partitioning and hierarchical classification of the 3D Histogram of Oriented Gradients (HOG) descriptor to represent sequences of images that have been concatenated into a data volume. We achieve robustness to occlusions and viewpoint changes by combining training data from all viewpoints to train classifiers that estimate action labels independently over sets of HOG blocks. A top level classifier combines these local labels into a global action class decision.


Présenté à:
European Conference on Computer Vision, Heraklion, Greece, September, 2010
Année
2010
Laboratoires:




 Notice créée le 2010-06-23, modifiée le 2019-12-05

n/a:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)