Using intermediate objects to improve the efficiency of visual search

When using a mobile camera to search for a target object, it is often important to maximize the efficiency of the search. We consider a method for increasing efficiency by searching only those subregions that are especially likely to contain the object. These subregions are identified via spatial relationships. Searches that use this method repeatedly find an “intermediate” object that commonly participates in a spatial relationship with the target object, and then look for the target in the restricted region specified by this relationship. Intuitively, such searches, calledindirect searches, seem likely to provide efficiency increases when the intermediate objects can be recognized at low resolutions and hence can be found with little extra overhead, and when they significantly restrict the area that must be searched for the target. But what is the magnitude of this increase, and upon what other factors does efficiency depend? Although the idea of exploiting spatial relationships has been used in vision systems before, few have quantitatively examined these questions.We present a mathematical model of search efficiency that identifies the factors affecting efficiency and can be used to predict their effects. The model predicts that, in typical situations, indirect search provides up to an 8-fold increase in efficiency. Besides being useful as an analysis tool, the model is also suitable for use in an online system for selecting intermediate objects.

[1]  Rudolf Ahlswede,et al.  Search Problems , 1987 .

[2]  Andrea Califano,et al.  Data and model driven foveation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

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

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

[5]  J M Tenenbaum,et al.  MSYS: A System for Reasoning About Scenes. , 1975 .

[6]  R. Bajcsy.  Active perception , 1988 .

[7]  Dana H. Ballard,et al.  Computer Vision , 1982 .

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

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

[10]  Douglas A. Reece,et al.  Using Active Vision to Simplify Perception for Robot Driving , 1991 .

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

[12]  W. Eric L. Grimson,et al.  Gaussian error models for object recognition , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  L. Wixson.  Exploiting World Structure to Efficiently Search for Objects , 1992 .

[14]  Dana H. Ballard,et al.  Principles of animate vision , 1992, CVGIP Image Underst..

[15]  Robert C. Bolles,et al.  Verification Vision for Programmable Assembly , 1977, IJCAI.

[16]  Roger Y. Tsai,et al.  Overview of the MVP sensor planning system for robotic vision tasks , 1992 .

[17]  Yiannis Aloimonos,et al.  Purposive and qualitative active vision , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

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

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

[20]  Peter J. Burt,et al.  Smart sensing within a pyramid vision machine , 1988, Proc. IEEE.

[21]  J. McDermott,et al.  Rule-Based Interpretation of Aerial Imagery , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[23]  Konstantinos A. Tarabanis,et al.  The MVP sensor planning system for robotic vision tasks , 1995, IEEE Trans. Robotics Autom..

[24]  Christopher M. Brown,et al.  Control of selective perception using bayes nets and decision theory , 1994, International Journal of Computer Vision.

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

[26]  Michael J. Swain.  Low-resolution cues for guiding saccadic eye movements , 1992, Other Conferences.

[27]  R. Larsen,et al.  An introduction to mathematical statistics and its applications (2nd edition) , by R. J. Larsen and M. L. Marx. Pp 630. £17·95. 1987. ISBN 13-487166-9 (Prentice-Hall) , 1987, The Mathematical Gazette.

[28]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.