An Experiment in Distributed Visual Attention

Attention mechanisms of biological vision have been applied to machine vision for several applications, like visual search and object detection. Most of the proposed models are centred on a unique way of attention, mainly stimulus-driven or bottom-up attention. We propose a visual attention system that integrates several attentional behaviours. To get a real-time implementation, we have designed a distributed software architecture that exhibits an efficient and flexible structure. We describe some implementation details and real experiments performed in a mobile robot endowed with a stereo vision head.

[1]  C. Koch,et al.  A saliency-based search mechanism for overt and covert shifts of visual attention , 2000, Vision Research.

[2]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Rajesh P. N. Rao,et al.  Eye movements in iconic visual search , 2002, Vision Research.

[4]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  A. Treisman,et al.  Emergent features, attention, and object perception. , 1984, Journal of experimental psychology. Human perception and performance.

[6]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[7]  Matthijs C. Dorst Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[8]  Laurent Itti,et al.  An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[9]  M. Goodale,et al.  The visual brain in action , 1995 .

[10]  D. Spalding The Principles of Psychology , 1873, Nature.