Exploiting World Structure to Efficiently Search for Objects

This paper studies the task of using a mobile camera platform to search a region of space for a target object. Our goal is to maximize the efficiency of such searches. The problem is analyzed using a simple mathematical description of the factors that affect search efficiency. This analysis suggests that one way to improve efficiency is to take advantage of the spatial relationships in which the target object commonly participates. Searches that do so, which we call indirect searches, are modeled as two-stage processes that first find an intermediate object that commonly participates in a spatial relationship for the target object, and then look for the target in the restricted region specified by this relationship. A mathematical model of search efficiency is then used to analyze the efficiency of indirect search over a wide range of situations that vary the spatial structure of the domain as well as recognition performance. The model predicts that, for searches that involve rotating a camera about a fixed location, indirect searches improve efficiency by factors of 2 to 8. An implemented robot search system substantiates these predictions. Finally, we highlight some areas in need of further research if these efficiencies are to be achieved.

[1]  I. Biederman,et al.  Searching for objects in real-world scences. , 1973, Journal of experimental psychology.

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

[3]  Daniel M Russell.  Constraint Networks: Modeling and Inferring Object Locations by Constraints, , 1978 .

[4]  Patrick Rabbitt,et al.  SORTING, CATEGORIZATION, AND VISUAL SEARCH , 1978 .

[5]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[6]  Rodney A. Brooks,et al.  Visual map making for a mobile robot , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[7]  Oscar Firschein,et al.  Readings in computer vision: issues, problems, principles, and paradigms , 1987 .

[8]  Rodney A. Brooks,et al.  Asynchronous Distributed Control System For A Mobile Robot , 1987, Other Conferences.

[9]  John K. Tsotsos,et al.  Knowledge organization and its role in representation and interpretation for time-varying data: the ALVEN system , 1987 .

[10]  A. Treisman.  Features and Objects: The Fourteenth Bartlett Memorial Lecture , 1988, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[11]  Jonathan H. Connell,et al.  A colony architecture for an artificial creature , 1989 .

[12]  D. W. Thompson,et al.  Representations in High-Level Vision: Reassessing the Inverse Optics Paradigm , 1989 .

[13]  Lambert E. Wixson,et al.  Real-Time Detection Of Multi-Colored Objects , 1990, Other Conferences.

[14]  Edward M. Riseman,et al.  A Fast Line Finder for Vision-Guided Robot Navigation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  L. Stark,et al.  Dissertation Abstract , 1994, Journal of Cognitive Education and Psychology.

[16]  Lambert E. Wixson,et al.  Scaling Reinforcement Learning Techniques via Modularity , 1991, ML.

[17]  Christopher M. Brown,et al.  Task-specific utility in a general Bayes net vision system , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[19]  Christopher M. Brown,et al.  Where to Look Next Using a Bayes Net: Incorporating Geometric Relations , 1992, ECCV.

[20]  Christopher M. Brown,et al.  Task-oriented vision with multiple Bayes nets , 1993 .

[21]  Dean A. Pomerleau,et al.  Neural Network Perception for Mobile Robot Guidance , 1993 .