Performance of Lookahead Control Policies in the Face of Abstractions and Approximations

This paper explores the formulation of image interpretation as a Markov Decision Process (MDP) problem, highlighting the important assumptions in the MDP formulation. Furthermore state abstraction, value function and action approximations as well as lookahead search are presented as necessary solution methodologies. We view the task of image interpretation as a dynamic control problem where the optimal vision operator is selected responsively based on the problem solvingstate at hand. The control policy, therefore, maps problem-solving states to operators in an attempt to minimize the total problem-solving time while reliably interpretingthe image. Real world domains, like that of image interpretation, usually have incredibly large state spaces which require methods of abstraction in order to be manageable by today's information processingsystems. In addition an optimal value function (V*) used to evaluate state quality is also generally unavailable nrequiring appro ximations to be used in conjunction with state abstraction. Therefore, the performance of the system is directly related to the types of abstractions and approximations present.

[1]  Richard E. Korf,et al.  Real-Time Heuristic Search , 1990, Artif. Intell..

[2]  Russell Greiner,et al.  Efficient Interpretation Policies , 2001, IJCAI.

[3]  Devika Subramanian,et al.  Provably Bounded Optimal Agents , 1993, IJCAI.

[4]  Lorenzo Bruzzone,et al.  Image and Signal Processing for Remote Sensing IX: 9-12 September 2003, Barcelona, Spain , 2004 .

[5]  D. A. Sprott,et al.  Foundations of Statistical Inference. , 1972 .

[6]  François A. Gougeon.  Individual Tree Identification from High Resolution MEIS Images , 1999 .

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  Morten Larsen,et al.  Using ray-traced templates to find individual trees in aerial photographs , 1997 .

[9]  Monty Newborn,et al.  Kasparov versus Deep Blue - computer chess comes of age , 1996 .

[10]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[11]  Richard S. Sutton,et al.  Reinforcement Learning , 1992, Handbook of Machine Learning.

[12]  Stuart J. Russell,et al.  Do the right thing - studies in limited rationality , 1991 .

[13]  Jonathan Schaeffer,et al.  A World Championship Caliber Checkers Program , 1992, Artif. Intell..

[14]  Bruce A. Draper,et al.  ADORE: Adaptive Object Recognition , 1999, ICVS.

[15]  Monty Newborn,et al.  Kasparov versus Deep Blue , 1997, Springer New York.

[16]  Richard J. Pollock,et al.  Model-based approach to automatically locating tree crowns in high spatial resolution images , 1994, Remote Sensing.