This Article 
 Bibliographic References 
 Add to: 
Feature Space Trajectory Methods for Active Computer Vision
December 2002 (vol. 24 no. 12)
pp. 1634-1643

Abstract—We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from multiple object views in determining the final object class and pose estimate. A probabilistic feature space trajectory (FST) in a global eigenspace is used to represent 3D distorted views of an object and to estimate the class and pose of an input object. Confidence measures for the class and pose estimates, derived using the probabilistic FST object representation, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information. We demonstrate the ability to use FSTs constructed from images rendered from computer-aided design models to recognize real objects in real images and present test results for a set of metal machined parts.

[1] S.A. Hutchinson and A.C. Kak, “Multisensor Strategies Using Dempster-Shafer Belief Accumulation,” Data Fusion in Robotics and Machine Intelligence, M.A. Abidi and R.C. Gonzalez, eds., pp. 165-209, Academic Press, 1992.
[2] F.G. Callari and F.P. Ferrie, “Active Recognition: Using Uncertainty to Reduce Ambiguity,” Proc. 13th Int'l Conf. Pattern Recognition, vol. 1, pp. 925-929, Aug. 1996.
[3] S. Dickinson, H. Christensen, J. Tsotsos, and G. Olofsson, “Active Object Recognition Integrating Attention and Viewpoint Control,” Computer Vision and Image Understanding, vol. 67, no. 3, pp. 239–260, Sept. 1997.
[4] W.E.L. Grimson, Object Recognition by Computer. MIT Press, 1990.
[5] Y. Lamdan and H.J. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," Second Int'l Conf. Computer Vision, pp. 238-249, 1988.
[6] F. Stein and G. Medioni, “Structural Indexing: Efficient 3-D Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 125–145, 1992.
[7] A. Johnson and M. Hebert, "Efficient Multiple Model Recognition in Cluttered 3-D Scenes," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 671-678, 1998.
[8] M.J. Black and A.D. Jepson, “Eigentracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation,” Int'l J. Computer Vision, vol. 26, no. 1, pp. 63-84, Jan. 1998.
[9] R.M. Haralick, H. Joo, C.-N. Lee, X. Zhuang, and M.B. Kim, “Pose Estimation from Corresponding Point Data,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, p. 1426, 1989.
[10] G. Wells, C. Venaille, and C. Torras, “Vision-Based Robot Positioning Using Neural Networks,” Image and Vision Computing, vol. 14, pp. 715-732, 1996.
[11] A.K. Jain, Fundamentals of Digital Image Processing. Prentice Hall, 1989.
[12] D. Casasent and L. Neiberg, “Classifier and Shift-Invariant ATR Neural Networks,” Neural Networks, vol. 8, nos. 7-8, pp. 1117-1130, 1995.
[13] G.G. Lendaris and G.L. Stanley, “Diffraction-Pattern Sampling for Automatic Target Recognition,” IEEE Proc., vol. 58, pp. 198-205, Feb. 1970.
[14] D. Casasent, L. Neiberg, and M.A. Sipe, “FST Distorted Object Representation for Classification and Pose Estimation,” Optical Eng., vol. 37, no. 3, pp. 914-923, Mar. 1998.
[15] C.W. Therrien, Decision Estimation and Classification: An Introduction to Pattern Recognition and Related Topics. John Wiley&Sons, 1989.
[16] H. Murase and S.K. Nayar, “Visual Learning and Recognition of 3-D Objects from Appearance,” Int'l J. Computer Vision, vol. 14, pp. 5-24, 1995.
[17] B. Moghaddam and A. Pentland, “Probabilistic Visual Learning for Object Representation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 696-710, July 1997.
[18] T. Darrell, B. Moghaddam, and A. Pentland, "Active Face Tracking and Pose Estimation in an Interactive Room," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 67-72, 1996.
[19] M. Turk and A. Pentland, “Eigenfaces for Recognition,” J. Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[20] A. Pentland, B. Moghaddam, and Starner, "View-Based and Modular Eigenspaces for Face Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1994, pp. 84-91.
[21] D. Casasent and R. Shenoy, “Feature Space Trajectory for Distorted-Object Classification and Pose Estimation in Synthetic Aperture Radar,” Optical Eng., vol. 36, no. 10, pp. 2719-2728, Oct. 1997.
[22] H. Murase and S.K. Nayar, “Detection of 3D Objects in Cluttered Scenes Using Hierarchical Eigenspace,” Pattern Recognition Letters, vol. 18, no. 4, pp. 375-384, 1997.
[23] H. Murase and S.K. Nayar, “Illumination Planning for Object Recognition Using Parametric Eigenspaces,” IEEE Trans. Pattern and Machine Intelligence, vol. 16, no. 12, pp. 1219-1227, Dec. 1994.
[24] T. Arbel and F.P. Ferrie, “Viewpoint Selection by Navigation through Entropy Maps,” Proc. Seventh Int'l Conf. Computer Vision, 1999.
[25] L. Neilberg, “Feature Space Trajectory Pattern Classifier,” PhD thesis, Dept. of Electrical and Computer Eng., Carnegie Mellon Univ., 1996.
[26] M.A. Sipe and D. Casasent, “Global Feature Space Neural Network for Active Computer Vision,” Neural Computation and Applications, vol. 7, no. 3, pp. 195-215, 1998.
[27] A. Papoulis, Probability, Random Variables, and Stochastic Processes. New York: McGraw-Hill, 1984.
[28] M.A. Sipe and D. Casasent, “Active Object Recognition Using Appearance-Based Representations Derived from Solid Geometric Models,” Proc. Symp. Intelligent Systems and Advanced Manufacturing, vol. 3522, pp. 139-150, Nov. 1998.
[29] M.A. Sipe and D. Casasent, “FST-Based Active Object Recognition for Automated Assembly,” Proc. SPIE Intelligent Robots and Computer Vision XVIII, Algorithms, Techniques, and Active Vision, vol. 3837, pp. 2-13, Nov. 1999.

Index Terms:
Active vision, classification, object recognition, pose estimation.
Michael A. Sipe, David Casasent, "Feature Space Trajectory Methods for Active Computer Vision," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 12, pp. 1634-1643, Dec. 2002, doi:10.1109/TPAMI.2002.1114854
Usage of this product signifies your acceptance of the Terms of Use.