Under$tanding echanisms: from Images to aviors

This paper presents a new method for recognizing mechanisms and describing their behaviors from image sequences showing their relations. It uses a simple and expressive language for describing the behavior of fured-axes mechanisms. The language symbolically captures the important aspects of the kinematics and the simple dynamics of the mechanism. We show how this language combined with a vision system can automatically identifL mechanisms and their behaviors from a sequence of images.

[1]  Leo Joskowicz.  Mechanism comparison and classification for design , 1990 .

[2]  Alessandro Verri,et al.  Against Quantitative Optical Flow , 1987 .

[3]  Xinhua Zhuang,et al.  Optic Flow Field Segmentation and Motion Estimation Using a Robust Genetic Partitioning Algorithm , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Ehud Rivlin,et al.  Function From Motion , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Murray Shanahan,et al.  Default Reasoning about Spatial Occupancy , 1995, Artif. Intell..

[6]  Matthew Brand,et al.  Physics-Based Visual Understanding , 1997, Comput. Vis. Image Underst..

[7]  Leo Joskowicz,et al.  A representation language for mechanical behavior , 1996, Artif. Intell. Eng..

[8]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[9]  Leo Joskowicz,et al.  Computational Kinematics , 1991, Artif. Intell..

[10]  Narendra Ahuja,et al.  Motion and Structure From Two Perspective Views: Algorithms, Error Analysis, and Error Estimation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Lawrence Birnbaum,et al.  Sensible Scenes: Visual Understanding of Complex Structures through Causal Analysis , 1993, AAAI.

[12]  Ramesh C. Jain,et al.  Determining Motion Parameters for Scenes with Translation and Rotation , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Rama Chellappa,et al.  Estimation of Object Motion Parameters from Noisy Images , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.