A Reactive Vision System: Active-Dynamic Saliency

We develop an architecture for reactive visual analysis of dynamic scenes. We specify a minimal set of system features based upon biological observations. We implement feature on a processing network based around an active stereo vision mechanism. Active rectification and mosaicing allows static stereo algorithms to operate on the active platform. Foveal zero disparity operations permit attended object extraction and ensures coordinated stereo fixation upon visual surfaces. Activedynamic inhibition of return, and task dependent biasing result in a flexible, preemptive and retrospective system that responds to unique visual stimuli and is capable of top-down modulation of attention towards regions and cues relevant to tasks.

[1]  Masayuki Inaba,et al.  Real time 3D depth flow generation and its application to track walking human beings , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Alexander Zelinsky,et al.  MAP ZDF segmentation and tracking using active stereo vision: Hand tracking case study , 2007, Comput. Vis. Image Underst..

[3]  B. Frost,et al.  Common reference frame for neural coding of translational and rotational optic flow , 1998, Nature.

[4]  Peter I. Corke,et al.  Quantitative Evaluation of Matching Methods and Validity Measures for Stereo Vision , 2001, Int. J. Robotics Res..

[5]  Alexander Zelinsky,et al.  A Novel Mechanism for Stereo Active Vision , 2000 .

[6]  Alexander Zelinsky,et al.  Active Vision - Rectification and Depth Mapping , 2004 .

[7]  A. B. Bonds,et al.  Two-dimensional receptive-field organization in striate cortical neurons of the cat , 1994, Visual Neuroscience.

[8]  H. Nothdurft Texture discrimination by cells in the cat lateral geniculate nucleus , 2004, Experimental Brain Research.

[9]  Gordon Cheng,et al.  Distributed visual attention on a humanoid robot , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[10]  C. Genovese,et al.  Spatial Updating in Human Parietal Cortex , 2003, Neuron.

[11]  C. Gilbert,et al.  Interactions between attention, context and learning in primary visual cortex , 2000, Vision Research.

[12]  D. Dacey,et al.  This paper was presented at a colloquium entitled ‘ ‘ Vision : From Photon to Perception , ’ ’ organized by , 1998 .

[13]  John H. R. Maunsell,et al.  Attentional modulation of visual motion processing in cortical areas MT and MST , 1996, Nature.

[14]  M. Carrasco,et al.  Spatial covert attention increases contrast sensitivity across the CSF: support for signal enhancement , 2000, Vision Research.

[15]  Christof Koch,et al.  Feature combination strategies for saliency-based visual attention systems , 2001, J. Electronic Imaging.

[16]  S. Nieuwenhuis,et al.  Neural mechanisms of attention and control: losing our inhibitions? , 2005, Nature Neuroscience.

[17]  Gerhard Krieger,et al.  Investigation of a sensorimotor system for saccadic scene analysis: an integrated approach , 1998 .