Making action recognition robust to occlusions and viewpoint changes

  • Authors:
  • Daniel Weinland;Mustafa Özuysal;Pascal Fua

  • Affiliations:
  • Deutsche Telekom Laboratories, TU Berlin, Germany;Computer Vision Laboratory, EPFL, Switzerland;Computer Vision Laboratory, EPFL, Switzerland

  • Venue:
  • ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.