Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
W. Au and B. Roberts. “Adaptive Configuration and Control in an ATR System,” IUW, pp. 667–676, 1996.
J. Aloimonos. “Purposive and Qualitative Active Vision”, IUW, pp 816–828, Sept. 1990.
K. Andress and A. Kak. “Evidence Accumulation and Flow of Control in a Hierarchical Spatial Reasoning System,” AI Magazine, 9(2):75–94, 1988.
M. Arbib. The Metaphorical Brain: An Introduction to Cybernetics as Artificial Intelligence and Brain Theory. Wiley Interscience, New York, 1972
D. Ballard. “Generalizing the Hough Transform to Detect Arbitrary Shapes,” PR, 13(2): 11–122, 1981.
R. Beveridge. LiME Users Guide. Technical report 97-22, Colorado State University Computer Science Department, 1997.
B. Burns, A. Hanson and E. Riseman. “Extracting Straight Lines,” PAMI 8(4):425–455, 1986.
S. Chien, H. Mortensen, C. Ying and S. Hsiao. “Integrated Planning for Automated Image Processing,” Integrated Planning Applications, AAAI Spring Symposium Series, March 1995, pp 26–35.
V. Clement and M. Thonnat. “A Knowledge-Based Approach to Integration of Image Processing Procedures,” CGVIP, 57(2):166–184, 1993.
D. Comaniciu and P. Meer. “Robust Analysis of Feature Space: Color Image Segmentation,” CVPR, pp. 750–755, 1997.
B. Draper, R. Collins, J. Brolio, A. Hanson and E. Riseman. “The Schema System,” IJCV, 2(2):209–250, 1989.
B. Draper and A. Hanson. “An Example of Learning in Knowledge Directed Vision,” Theory and Applications of Image Analysis, World Scientific, Singapore, 1992. pp. 237–252.
B. Draper. “Modelling Object Recognition as a Markov Decision Process,” ICPR, D95–99, 1996.
B. Draper and K. Baek. “Bagging in Computer Vision,” CVPR, pp. 144–149, 1998.
V. Hwang, L. Davis and T. Matsuyama. “Hypothesis Integration in Image Understanding Systems,” CGVIP, 36(2):321–371, 1986.
K. Ikeuchi and M. Hebert. “Task Oriented Vision,” IUW, pp. 497–507, 1990.
X. Jiang and H. Bunke. “Vision planner for an intelligent multisensory vision system,” Automatic Object Recognition IV, pp. 226–237, 1994.
M. Kass, A. Witken and D. Terzopoulis. “Snakes: Active Contour Models,” IJCV 1(4):321–331, 1988.
A. Lansky, et al. “The COLLAGE/KHOROS Link: Planning for Image Processing Tasks,” Integrated Planning Applications, AAAI Spring Symposium Series, 1995,pp 67–76.
M. Maloof, P. Langley, S. Sage, T. Binford. “Learning to Detect Rooftops in Aerial Images,” IUW, 835–846, 1997.
W. Mann and T. Binford. “SUCCESSOR: Interpretation Overview and Constraint System,” IUW, 1505–1518, 1996.
D. McKeown, W. Harvey and J. McDermott. “Rule-Based Interpretation of Aerial Imagery,” PAMI, 7(5);570–585, 1985.
J. Mundy. “The Image Understanding Environment Program,” IEEE Expert, 10(6):64–73, 1995.
M. Nagao and T. Matsuyama. A Structural Analysis of Complex Aerial Photographs. N.Y.: Plenum Press, 1980.
D. Nguyen. An Iterative Technique for Target Detection and Segmentation in IR Imaging Systems, Technical Report, Center for Night Vision and Electro-Optics, 1990.
J. Peng and B. Bhanu. “Closed-Loop Object Recognition using Reinforcement Learning,” PAMI 20(2):139–154, 1998.
J. Rasure and S. Kubica. “The KHOROS Application Development Environment,” In Experimental Environments for Computer Vision, World Scientific, New Jersey, 1994.
S. Ravela, B. Draper, J. Lim and R. Weiss. “Tracking Object Motion Across Aspect Changes for Augmented Reality,” IUW, pp. 1345–1352, 1996.
R. Rimey and C. Brown. “Control of Selective Perception using Bayes Nets and Decision Theory,“ IJCV, 12(2): 173–207.
R. Sutton. “Learning to Predict by the Methods of Temporal Differences,” ML, 3(9):9–44, 1988.
G. Tesauro. “Temporal Difference Learning and TD-Gammon,” CACM, 38(3):58–68, 1995.
S. Ullman. “Visual Routines,” Cognition, 18:97–156, 1984.
S. Umbaugh. Computer Vision and Image Processing: A Practical Approach using CVIPtools, Prentice Hall, New Jersey, 1998.
C. Watkins. Learning from Delayed rewards, Ph.D. thesis, Cambridge University, 1989.
W. Zhang and T. Dietterich. “A Reinforcement Learning Approach to Job-Shop Scheduling,” IJCAI, 1995.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Draper, B.A., Bins, J., Baek, K. (1999). ADORE: Adaptive Object Recognition. In: Computer Vision Systems. ICVS 1999. Lecture Notes in Computer Science, vol 1542. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49256-9_31
Download citation
DOI: https://doi.org/10.1007/3-540-49256-9_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65459-9
Online ISBN: 978-3-540-49256-6
eBook Packages: Springer Book Archive