Articulated Motion and Deformable Objects

Manipulation of deformable objects will be discussed. Manipulation of deformable objects is defined as controlling deformation of objects as well as their positions and orientations. The manipulation is a fundamental and important task in many industrial fields. In fact, there exist many operations of deformable objects such as textile fabrics, rubber parts, paper sheets, strings, and foods. In order to realize the manipulation of deformable objects by mechanical systems, an object model is indispensable. It is, however, difficult to build exact model of the deformable objects due to their strong nonlinearity such as friction, hysteresis and parameter variations. Thus, such operations strongly depend on skilled human workers. To overcome this problem, we will propose a robust control strategy using a model based technique. We will build a coarse model of an object for the manipulation and will develop a control method robust to the discrepancy between the object and its model. Experimental results will show the robustness of the proposed method.

[1]  菅沼 明,et al.  Multi-part Object Tracking using Multiple Cameras , 1998 .

[2]  谷口 倫一郎,et al.  Database Development of Multi-Viewpoint Image Sequences for Evaluation of Image Understanding Systems , 1999 .

[3]  Rin-ichiro Taniguchi,et al.  A Real-Time Distributed Video Image Processing System on PC-Cluster , 1999, ACPC.

[4]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[5]  Robert B. Fisher,et al.  Class-based Recognition of 3D Objects Represented by Volumetric Primitives , 1996, BMVC.

[6]  Andrew J. Bulpitt,et al.  Learning spatio-temporal patterns for predicting object behaviour , 2000, Image Vis. Comput..

[7]  Timothy F. Cootes,et al.  Training Models of Shape from Sets of Examples , 1992, BMVC.

[8]  I. Biederman Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[9]  Ioannis A. Kakadiaris,et al.  3D human body model acquisition from multiple views , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[12]  谷口 倫一郎,et al.  A 3D Modeler with Parameter Estimation from Multiview Images , 1999 .

[13]  Dimitris N. Metaxas,et al.  Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  谷口 倫一郎,et al.  Shape and Pose Parameter Estimation of 3D Multi-Part Objects , 1997 .