Neural Competitive Structures for Segmentation Based on Motion Features

Visual attention is the ability to rapidly detect the interesting parts of a given scene on which higher level computer vision tasks can focus. This paper reports a computational model of dynamic visual attention which combines static and dynamic features to detect salient locations in natural image sequences. Therefore, the model computes a map of interest - saliency map - related to static features and a saliency map derived from dynamic scene features and then combines them into a final saliency map, which topographically encodes stimulus saliency. The information provided by the model of attention is then used by a tracking method to attentively track the interesting features in the scene. The experimental results, reported in this work refer to real color image sequences. They clearly validate the reported model of dynamic visual attention and show its usefulness in guiding the tracking task.

[1]  Andrew B. Watson,et al.  A look at motion in the frequency domain , 1983 .

[2]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[3]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[5]  D. Heeger.  Normalization of cell responses in cat striate cortex , 1992, Visual Neuroscience.

[6]  Atsuto Maki,et al.  Attentional Scene Segmentation: Integrating Depth and Motion , 2000, Comput. Vis. Image Underst..

[7]  A. Yuille,et al.  A model for the estimate of local image velocity by cells in the visual cortex , 1990, Proceedings of the Royal Society of London. B. Biological Sciences.

[8]  Heinz Hügli,et al.  Computing visual attention from scene depth , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[9]  Edward H. Adelson,et al.  The extraction of Spatio-temporal Energy in Human and Machine Vision , 1997 .

[10]  Eero P. Simoncelli,et al.  A model of neuronal responses in visual area MT , 1998, Vision Research.

[11]  Thierry Pun,et al.  Attentive mechanisms for dynamic and static scene analysis , 1995 .

[12]  Subutai Ahmad,et al.  Visit: an efficient computational model of human visual attention , 1992 .

[13]  Dariu M. Gavrila,et al.  6 – From door to door — principles and applications of computer vision for driver assistant systems , 2001 .

[14]  Eero P. Simoncelli.  Coarse-to-fine estimation of visual motion , 1993 .

[15]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[16]  S. Engel,et al.  Colour tuning in human visual cortex measured with functional magnetic resonance imaging , 1997, Nature.

[17]  Heinz Hügli,et al.  A Real Time Implementation of the Saliency-Based Model of Visual Attention on a SIMD Architecture , 2002, DAGM-Symposium.

[18]  D J Heeger,et al.  Model for the extraction of image flow. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[19]  Gregory Bock,et al.  Higher-order processing in the visual system , 1994 .