Attention and Visual Search: Active Robotic Vision Systems that Search

Visual attention is a multi-faceted phenomenon, playing different roles in different situations and for different processing mechanisms. Regardless, attention is a mechanism that optimizes the search processes inherent in vision. This perspective leads to a sound theoretical foundation for studies of attention in both machine and in the brain. The development of this foundation and the many ways in which attentive processes manifest themselves will be overviewed. One particular example of a practical robotic vision system that employs some of these attentive processes will be described. A difficult problem for robotic vision systems is visual search for a given target in an arbitrary 3D space. A solution to this problem will be described that optimizes the probability of finding the target given a fixed cost limit in terms of total number of robotic actions the robot requires to find its visual target. A robotic realization will be shown.

[1]  T. Garvey.  Perceptual strategies for purposive vision , 1975 .

[2]  Richard A. Volz,et al.  Object recognition using multiple views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[3]  C. Ian Connolly,et al.  The determination of next best views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[4]  Peter Kovesi,et al.  Automatic Sensor Placement from Vision Task Requirements , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Ronald A. Rensink,et al.  A New Proof of the NP Completeness of Visual Match , 1989 .

[6]  John K. Tsotsos.  The Complexity of Perceptual Search Tasks , 1989, IJCAI.

[7]  John K. Tsotsos.  Analyzing vision at the complexity level , 1990, Behavioral and Brain Sciences.

[8]  John K. Tsotsos,et al.  Active object recognition , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Steven A. Shafer,et al.  Selective Perception for Robot Driving , 1993, AAAI.

[10]  Ruzena Bajcsy,et al.  Occlusions as a Guide for Planning the Next View , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Lambert E. Wixson,et al.  Viewpoint selection for visual search , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[13]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1997, Comput. Vis. Image Underst..

[14]  Yiming Ye,et al.  Sensor Planning for 3D Object Search , 1999 .

[15]  John K. Tsotsos,et al.  Fast pattern recognition using gradient-descent search in an image pyramid , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Yiming Ye,et al.  A Complexity‐Level Analysis of the Sensor Planning Task for Object Search , 2001, Comput. Intell..

[17]  Jun Ota,et al.  Controlling a mobile robot that searches for and rearranges objects with unknown locations and shapes , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[18]  Hugh F. Durrant-Whyte,et al.  Coordinated decentralized search for a lost target in a Bayesian world , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[19]  John K. Tsotsos.  On the relative complexity of active vs. passive visual search , 2004, International Journal of Computer Vision.

[20]  Lambert E. Wixson,et al.  Using intermediate objects to improve the efficiency of visual search , 1994, International Journal of Computer Vision.

[21]  S. Kyllingsbaek,et al.  Modeling visual attention. , 2006, Behavior research methods.

[22]  S. Kyllingsbæk.  Modeling visual attention , 2006 .

[23]  John K. Tsotsos,et al.  Attention links sensing to recognition , 2008, Image Vis. Comput..