Attentive object detection using an information theoretic saliency measure

  • Authors:

  • Gerald Fritz;Christin Seifert;Lucas Paletta;Horst Bischof

  • Affiliations:

  • Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Graz, Austria;Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Graz, Austria;Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Graz, Austria;Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria

  • Venue:
  • WAPCV'04 Proceedings of the Second international conference on Attention and Performance in Computational Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

A major goal of selective attention is to focus processing on relevant information to enable rapid and robust task performance. For the example of attentive visual object recognition, we investigate here the impact of top-down information on multi-stage processing, instead of integrating generic visual feature extraction into object specific interpretation. We discriminate between generic and specific task based filters that select task relevant information of different scope and specificity within a processing chain. Attention is applied by tuned early features to selectively respond to generic task related visual features, i.e., to information that is in general locally relevant for any kind of object search. The mapping from appearances to discriminative regions is then modeled using decision trees to accelerate processing. The focus of attention on discriminative patterns enables efficient recognition of specific objects, by means of a sparse object representation that enables selective, task relevant, and rapid object specific responses. In the experiments the performance in object recognition from single appearance patterns dramatically increased considering only discriminative patterns, and evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition, even in the presence of severe occlusion and noise effects. In addition, we present performance evaluation on our public available reference object database (TSG-20).