Real-Time Attention for Robotic Vision

This paper discusses the development and real-time implementation of an algorithm to determine interest points in a scene. The algorithm models interest points as the points of intersection of lines of symmetry between edges in an image and is based on psychophysical experiments of human gaze fixation. A novel, real-time method of computing these interest points is achieved by adopting a symmetry measure which determines the loci of centers of co-circular edges.The algorithm has been implemented on a parallel network of Texas Instruments TMS320C40 (C40) processors. In addition, the implementation permits the algorithm to operate on non-uniformly mapped logÂ?polar images. This configuration facilitates near real-time performance on images covering a very large field of view.Results show that the algorithm has practical uses in a number of areas, including face recognition, object tracking and the positioning of an active vision sensor in real-time.

[1]  D. Proffitt,et al.  The roles of contour and luminance distribution in determining perceived centers within shapes , 1983, Perception & psychophysics.

[2]  Mark S. Nixon,et al.  Approaches to extending the Hough transform , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[3]  Eric L. Schwartz,et al.  Design considerations for a space-variant visual sensor with complex-logarithmic geometry , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[4]  Yehezkel Yeshurun,et al.  Detection of interest points using symmetry , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[5]  S. Kaplan.  The Physiology of Thought , 1950 .

[6]  Werner von Seelen,et al.  CARTRACK: computer vision-based car following , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[7]  Andrew Zisserman,et al.  Using a mixed wave/ diffusion process to elicit the symmetry set , 1989, Image Vis. Comput..

[8]  Leslie G. Ungerleider,et al.  Object vision and spatial vision: two cortical pathways , 1983, Trends in Neurosciences.

[9]  L. Kaufman,et al.  “Center-of-gravity” Tendencies for fixations and flow patterns , 1969 .

[10]  J E Cutting,et al.  Perceiving the centroid of curvilinearly bounded rolling shapes , 1980, Perception & psychophysics.

[11]  Martin D. Levine,et al.  Annular symmetry operators: a method for locating and describing objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[12]  Anne Treisman,et al.  Emergent features, attention, and object perception. , 1984 .

[13]  P. Locher,et al.  SYMMETRY CATCHES THE EYE , 1987 .

[14]  J. Bruell,et al.  Notes toward a motor theory of visual egocentric localization. , 1955, Psychological review.

[15]  I. Rock.  The Logic of Perception , 1983 .

[16]  G. Sela,et al.  Fast computation of multiscalar symmetry in foveated images , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[17]  Barbara Gillam.  New evidence for “closure” in perception , 1975 .

[18]  S. Coren,et al.  Effect of Non-Target Stimuli upon Length of Voluntary Saccades , 1972, Perceptual and motor skills.

[19]  Kjell Brunnström,et al.  Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch , 1992, ECCV.

[20]  R. Pritchard.  Visual Illusions Viewed as Stabilized Retinal Images , 1958 .

[21]  Peter Kwong-Shun Tam,et al.  Modification of hough transform for circles and ellipses detection using a 2-dimensional array , 1992, Pattern Recognit..

[22]  S. Coren.  An efferent component in the visual perception of direction and extent. , 1986, Psychological review.

[23]  B. Julesz,et al.  Human factors and behavioral science: Textons, the fundamental elements in preattentive vision and perception of textures , 1983, The Bell System Technical Journal.

[24]  James J. Clark,et al.  Modal Control Of An Attentive Vision System , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[25]  Hanspeter A. Mallot,et al.  Saccadic object recognition with an active vision system , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[26]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[27]  Martin D. Levine,et al.  Visual information processing in primate cone pathways. I. A model , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[28]  A Treisman,et al.  Feature analysis in early vision: evidence from search asymmetries. , 1988, Psychological review.