A model of selective visual attention for a stereo pair of images

Human visual attention system has a remarkable ability to interpret complex scenes with the ease and simplicity by selecting or focusing on a small region of visual field without scanning the whole images. In this paper, a novel selective visual attention model by using 3D image display system for a stereo pair of images is proposed. It is based on the feature integration theory and locates ROI(region of interest) or FOA(focus of attention). The disparity map obtained from a stereo pair of images is exploited as one of spatial visual features to form a set of topographic feature maps in our approach. Though the true human cognitive mechanism on the analysis and integration process might be different from our assumption the proposed attention system matches well with the results found by human observers.

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

[2]  I. Ohzawa,et al.  Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. , 1990, Science.

[3]  Thierry Pun,et al.  Integration of bottom-up and top-down cues for visual attention using non-linear relaxation , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  K Nakayama,et al.  Binocular visual surface perception. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[5]  I. Ohzawa,et al.  Encoding of binocular disparity by complex cells in the cat's visual cortex. , 1996, Journal of neurophysiology.

[6]  N. Qian.  Binocular Disparity and the Perception of Depth , 1997, Neuron.

[7]  Carlo Tomasi,et al.  A Pixel Dissimilarity Measure That Is Insensitive to Image Sampling , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Anthony J. Maeder,et al.  Automatic identification of perceptually important regions in an image , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[9]  N. P. Bichot,et al.  Spatial selection via feature-driven inhibition of distractor locations , 1998, Perception & psychophysics.

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

[11]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[12]  W. Backhaus.  Neuronal coding of perceptual systems : proceedings of the International School of Biophysics, Casamicciola, Napoli, Italy, 12-17 October 1998 , 2001 .

[13]  Austen Clark.  Some logical features of feature integration , 2002 .

[14]  Yillbyung Lee,et al.  A Feature-Driven Attention Module for an Active Vision System , 2002, DAGM-Symposium.

[15]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[16]  Takayuki Hamamoto,et al.  A smart image sensor with attention modules , 2005, Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05).

[17]  Laurent Itti,et al.  Models of Bottom-up Attention and Saliency , 2005 .

[18]  S. Petersen,et al.  Stereoscopic Depth Discrimination in the Visual Cortex : Neurons Ideally Suited as Disparity Detectors IZUMI OHZAWA , 2022 .