ADORE: Adaptive Object Recognition

Many modern computer vision systems are built by chaining together standard vision procedures, often in graphical programming environments such as Khoros, CVIPtools or IUE. Typically, these procedures are selected and sequenced by an ad-hoc combination of programmer's intuition and trial-and-error. This paper presents a theoretically sound method for constructing object recognition strategies by casting object recognition as a Markov Decision Problem (MDP). The result is a system called ADORE (Adaptive Object Recognition) that automatically learns object recognition control policies from training data. Experimental results are presented in which ADORE is trained to recognize five types of houses in aerial images, and where its performance can be (and is) compared to optimal.

[1]  Joseph L. Mundy.  The Image Understanding Environment Program , 1995, IEEE Expert.

[2]  Avinash C. Kak,et al.  Evidence Accumulation and Flow of Control in a Hierarchical Spatial Reasoning System , 1988, AI Mag..

[3]  S. Ullman.  Visual routines , 1984, Cognition.

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

[5]  Amy L. Lansky,et al.  The COLLAGE/KHOROS Link: Planning for Image Processing Tasks , 1995 .

[6]  Horst Bunke,et al.  Vision planner for an intelligent multisensory vision system , 1994, Defense, Security, and Sensing.

[7]  Wing Au,et al.  ATR Design via Adaptive Configuration and Control. , 1996 .

[8]  Scott E. Umbaugh,et al.  Computer Vision and Image Processing: A Practical Approach Using CVIPTools , 1997 .

[9]  John Rasure,et al.  The Khoros Application Development Environment , 1994 .

[10]  Bruce A. Draper,et al.  An Example of Learning in Knowledge-Directed Vision , 1992 .

[11]  Wing Au,et al.  Adaptive configuration and control in an ATR system , 1995, Defense, Security, and Sensing.

[12]  Keith Michael Andress,et al.  Evidence accumulation & flow of control , 1988 .

[13]  Allen R. Hanson,et al.  The image understanding environment program , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Gerald Tesauro,et al.  Temporal Difference Learning and TD-Gammon , 1995, J. Int. Comput. Games Assoc..

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

[16]  Makoto Nagao,et al.  A Structural Analysis of Complex Aerial Photographs , 1980, Advanced Applications in Pattern Recognition.

[17]  Bir Bhanu,et al.  Closed-loop object recognition using reinforcement learning , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Katsushi Ikeuchi,et al.  Task Oriented Vision , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Scott E. Umbaugh,et al.  Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom , 1997 .

[20]  Allen R. Hanson,et al.  Extracting Straight Lines , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Pat Langley,et al.  Learning to Detect Rooftops in Aerial Images , 1997 .

[22]  Ben J. A. Kröse,et al.  Learning from delayed rewards , 1995, Robotics Auton. Syst..

[23]  Wei Zhang,et al.  A Reinforcement Learning Approach to job-shop Scheduling , 1995, IJCAI.

[24]  Bruce A. Draper,et al.  Bagging in computer vision , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[25]  Dorin Comaniciu,et al.  Robust analysis of feature spaces: color image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Sai Ravela.  Tracking Object Motion Across Aspect Changes for Augmented Reality , 1996 .

[27]  Larry S. Davis,et al.  Hypothesis integration in image understanding systems , 1985, Comput. Vis. Graph. Image Process..

[28]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[29]  Michael A. Arbib,et al.  The metaphorical brain : an introduction to cybernetics as artificial intelligence and brain theory , 1972 .

[30]  Steve Chien,et al.  Integrated Planning for Automated Image Processing , 1995 .

[31]  Bruce A. Draper.  Modeling object recognition as a Markov decision process , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[32]  Monique Thonnat,et al.  A knowledge-based approach to integration of image processing procedures , 1993 .