Using Aspect Graphs to Control the Recovery and Tracking of Deformable Models

Active or deformable models have emerged as a popular modeling paradigm in computer vision. These models have the exibility to adapt themselves to the image data, o ering the potential for both generic object recognition and non-rigid object tracking. Because these active models are underconstrained, however, deformable shape recovery often requires manual segmentation or good model initialization, while active contour trackers have been able to track only an object's translation in the image. In this paper, we report our current progress in using a part-based aspect graph representation of an object [14] to provide the missing constraints on data-driven deformable model recovery and tracking processes. Appears in International Journal of Pattern Recognition and Arti cial Intelligence, Vol. 11, No. 1, February, 1997, pp 115{142. (special issue containing selected papers from the Workshop on Spatial Computing: Representation, Interpretation and Applications, Curtin University of Technology, Perth, Western Australia, December 2{3, 1995.)

[1]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1994, Comput. Vis. Image Underst..

[2]  Sven J. Dickinson,et al.  A Representation for Qualitative 3-D Object Recognition Integrating Object-Centered and Viewer-Centered Models , 1990 .

[3]  R. Chellappa,et al.  Recursive 3-D motion estimation from a monocular image sequence , 1990 .

[4]  Azriel Rosenfeld,et al.  From volumes to views: An approach to 3-D object recognition , 1992, CVGIP Image Underst..

[5]  Sven J. Dickinson,et al.  Founded by Benjamin Franklin in 1740 The Institute For Research In Cognitive Science Physics-Based Tracking of 3 D Objects in 2 D Image Sequences , 1994 .

[6]  Dimitris N. Metaxas.  Shape and Nonrigid Motion Estimation , 1997 .

[7]  Dimitris N. Metaxas,et al.  Physics-based modelling of nonrigid objects for vision and graphics , 1993 .

[8]  Rachid Deriche,et al.  Tracking line segments , 1990, Image Vis. Comput..

[9]  Demetri Terzopoulos,et al.  Constraints on Deformable Models: Recovering 3D Shape and Nonrigid Motion , 1988, Artif. Intell..

[10]  Dimitris N. Metaxas,et al.  Dynamic 3D models with local and global deformations: deformable superquadrics , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[11]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Andrew Blake,et al.  Parallel Implementation of Lagrangian Dynamics for Real-time Snakes , 1991, BMVC.

[13]  Sven J. Dickinson,et al.  Integration of quantitative and qualitative techniques for deformable model fitting from orthographic, perspective, and stereo projections , 1993, 1993 (4th) International Conference on Computer Vision.

[14]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[15]  Sven J. Dickinson,et al.  A New Approach to Tracking 3D Objects in 2D Image Sequences , 1994, AAAI.

[16]  R. Cipolla,et al.  Motion planning using image divergence and deformation , 1993 .

[17]  Sven J. Dickinson,et al.  Qualitative tracking of 3-D objects using active contour networks , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[19]  Alex Pentland,et al.  Closed-form solutions for physically-based shape modeling and recognition , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.