This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Function From Motion
June 1996 (vol. 18 no. 6)
pp. 579-591

Abstract—In order for a robot to operate autonomously in its environment, it must be able to perceive its environment and take actions based on these perceptions. Recognizing the functionalities of objects is an important component of this ability. In this paper, we look into a new area of functionality recognition: determining the function of an object from its motion. Given a sequence of images of a known object performing some function, we attempt to determine what that function is. We show that the motion of an object, when combined with information about the object and its normal uses, provides us with strong constraints on possible functions that the object might be performing.

[1] I. Biederman, "Human Image Understanding: Recent Research and a Theory," Comp. Vision, Graphics and Image Processing, vol. 32, pp. 29-73, 1985.
[2] L. Bogoni and R. Bajcsy, "Active Investigation of Functionality," Proc. CVPR Workshop on Visual Behaviors,Seattle, Wash., June 1994.
[3] M. Brady, P.E. Agre, D.J. Braunegg, and J. Connell II, "The Mechanic's Mate," Proc. Sixth European Conf. on Artificial Intelligence, pp. 79-94, 1984.
[4] D. Dementhon and L. Davis, "Model-Based Object Pose in 25 Lines of Code," Int'l J. Comp. Vision, vol. 15, pp. 123-141, 1995.
[5] P. Freeman and A. Newell, "A Model for Functional Reasoning in Design," Proc. Int'l Joint Conf. Artificial Intelligence, pp. 621-640, Aug. 1971.
[6] K. Green, D. Eggert, L. Stark, and K. Bowyer, "Generic Recognition of Articulated Objects by Reasoning About Functionality," Proc. AAAI-94 Workshop on Representing and Reasoning About Device Function, pp. 56-64, 1994.
[7] K. Gould and M. Shah, "The Trajectory Primal Sketch: A Multi-Scale Scheme for Representing Motion Characteristics," Proc. IEEE Conf. Comp. Vision and Pattern Recognition, pp. 79-85, June 1989.
[8] J. Hodges, "Naive Mechanics—A Computational Model of Device Use and Function in Design Improvisation," IEEE Expert, vol. 7, pp. 14-27, 1992.
[9] B.K.P. Horn and B.G. Schunck, "Determining Optical Flow," Artificial Intelligence, vol. 17, pp. 189-203, 1981.
[10] J.R. Kender and D.G. Freudenstein, "What Is a Degenerate View?" Proc. DARPA Image Understanding Workshop, pp. 589-598, 1987.
[11] K. Kise, H. Hattori, T. Kitahashi, and K. Fukunaga, "Representing and Recognizing Simple Hand-Tools Based on Their Functions," Proc. Asian Conf. Comp. Vision, pp. 656-659, 1993.
[12] T. Kitahashi, N. Abe, S. Dan, K. Kanada, and H. Ogawa, "A Function-Based Model of an Object for Image Understanding," H. Jaakkola and S. Ohusuga eds, Advances in Information Modeling and Knowledge Bases, pp. 91-97, 1991.
[13] H. Murase and S.K. Nayar, "Learning Object Models From Appearance," Proc. National Conf. Artificial Intelligence, pp. 836-843,Washington, D.C., July 1993.
[14] R. Polana and R. Nelson, "Detecting Activities," Proc. IEEE Conf. Comp. Vision and Pattern Recognition, pp. 2-7,New York, June 1993.
[15] E. Rivlin, S.J. Dickinson, and A. Rosenfeld, "Recognition by Functional Parts," Proc. IEEE Conf. Comp. Vision and Pattern Recognition, pp. 267-274,Seattle, Wash., June 1994.
[16] E. Rivlin, A. Rosenfeld, and D. Perlis, "Recognition of Object Functionality in Goal-Directed Robotics," Proc. AAAI Workshop Reasoning About Function, 1993.
[17] F. Solina and R. Bajcsy, "Shape and Function," Proc. SPIE Conf. Intelligent Robots and Comp. Vision, vol. 726, pp. 284-291, 1983.
[18] L. Stark and K. Bowyer, "Achieving Generalized Object Recognition Through Reasoning About Association of Function to Structure," IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 13, pp. 1097-1,104, 1,991.
[19] L. Stark and K. Bowyer, "Generic Recognition Through Qualitative Reasoning About 3D Shape and Object Function," Proc. IEEE Conf. Comp. Vision and Pattern Recognition, pp. 251-256,Maui, Hawaii, 1991.
[20] L. Stark and K. Bowyer, "Indexing Function-Based Categories for Generic Recognition," Proc. IEEE Conf. Comp. Vision and Pattern Recognition, pp. 795-797,Champaign, Ill., June 1992.
[21] L. Stark, A. Hoover, D. Goldgof, and K. Bowyer, "Function Based Recognition From Incomplete Knowledge of Shape," Proc. IEEE Workshop Qualitative Vision, pp. 11-22,New York, 1993.
[22] S. Ullman and R. Basri, "Recognition by Linear Combinations of Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 992-1006, 1991.
[23] L. Vaina and M. Jaulent, "Object Structure and Action Requirements: A Compatibility Model for Functional Recognition," Int'l J. Intelligent Systems, vol. 6, pp. 313-336, 1991.
[24] A. Verri and T. Poggio, "Against Quantitative Optical Flow," Proc. Int'l Conf. Comp. Vision, pp. 171-180,London, England, June 1987.
[25] P.H. Winston, T.O. Binford, B. Katz, and M. Lowry, "Learning Physical Descriptions From Functional Descriptions, Examples, and Precedents," Proc. National Conf. Artificial Intelligence, pp. 433-439, 1983.

Index Terms:
Object recognition, action perception, functionality, motion, normal flow.
Citation:
Zoran Duric, Jeffrey A. Fayman, Ehud Rivlin, "Function From Motion," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 579-591, June 1996, doi:10.1109/34.506409
Usage of this product signifies your acceptance of the Terms of Use.