D. Metaxas and D. Terzopouilos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....can be used to rectify a video to correct for camera roll. We estimate parameters of a rigid body motion with an optimization that seeks to match the resulting motion with the frames of the video sequence. Rather than operating in a feed forward manner, as is typical of object tracking techniques [16,17, 7,4], we cast the problem in a global optimization framework that optimizes over all frames at once. Using this framework, we show how it is possible to simultaneously compute the object, camera, and environment parameters from video data. Unlike previous analytical methods [15,14] our method does ....

....the inertial parameters. The problem of simultaneously recovering the physical parameters of the object, camera, and environment from a single camera has not been previously addressed. 554 K.S. Bhat et al. Our work is closely related to prior work on model based tracking in computer vision [11,5,21,4,7,24,17,16]. However, the notion of a dynamic model in the tracking literature is different from the one presented here. We use ordinary differential equations to model the non linear rotational dynamics of tumbling rigid bodies, and extract its parameters from video. These parameters include initial ....

[Article contains additional citation context not shown here]

D. Metaxas and D.Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Trans. Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

....placed in a mutually orthogonal configuration. The person under observation is requested to perform a set of movements according to a protocol that incrementally reveals the structure of the human body. Once the model has been acquired, the tracking is performed using the physics based framework [24]. Based on the expected body position, the difference between the predicted and actual images is used to calculate forces that are applied to the model. The dynamics are modeled using the extended Kalman filter. The tracking result, a new body pose, is a result of the applied forces acting on the ....

D. Metaxas, D. Terzopoulos, "Shape and Nonrigid Motion Estimation through Physics-Based Synthesis", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 6, June 1993, p. 580-591

.... formulated regularization terms based on physical analogy of a membrane under tension and a thin plate under tension [124] Metaxas and Terzopoulos extended this work into deformable superquadrics and introduced it to the computer vision and computer graphics fields and later to the medical area [82, 81]. The deformable superquadrics of Metaxas and Terzopoulos are based on Lagrangian dynamics. Their sti#ness matrix K combines global and local sti#ness coe#cients. The position of a point on the surface of the model relative to the center depends on the global deformation g and the local ....

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Recognition and Machine Intelligence, 15(6):580--591, 1993.

....monitoring and surveillance, in biomedical image analysis, in human computer interfaces, etc. 1] For these tracking tasks, a common approach is the use of the Kalman filter or extended Kalman filter. While some researchers employ physical snakes as system models in the (extended) Kalman filter [2,3,4], others use constant velocity motion models or learned motion models from training image sequences [5,6] All the research mentioned above assumed that the probability distributions of the states are Gaussian, and therefore, the means and covariances, computed recursively with a set of ....

D. Metaxas, D. Terzopouilos, "Shape and Nonrigid Motion Estimation through Physics-Based Synthesis," IEEE Trans. PAMI, vol. 15, no. 6, pp. 580-591, 1993.

....so that a different type of model can be invoked. Superquadrics, which are an extension of basic quadric surfaces and solids, satisfy most of the criteria. They have been considered as volumetric primitives for shape representation in computer graphics [1] and computer vision [16] 20] 21] [14], 6] The reason being that they are convenient part level models that can further be deformed and glued together to model articulated objects. A superquadric surface is defined by the following implicit equation Fxyz x a y a z , 16 oe # # # # # # # # # # # # # # # # ....

D. Metaxas and D. Terzopoulos, "Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 6, pp. 580-591, 1993.

No context found.

D.Metaxas and D.Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. PAMI, 15(6):580-591, 1993.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

No context found.

D. Metaxas and D. Terzopoulos," Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis" IEEE Trans. Pattern Analysis and Machine Intelligence, 15(6):580--591, June, 1993.

....Grants N00014 92 J 1647 and DAAH 049510067 , NSF Grants CISE CDA 88 22719, MIP94 20397, IRI93 09917 and MIP94 20393. researchers assume prior segmentation of the image data into parts [12] and then fit deformable models that can adapt to data from humans with different anthropometric dimensions [11, 9]. Thus, the process of segmentation and the process of shape and motion estimation are decoupled, leading to possible inaccuracies and lack of robustness. Moreover, no technique exists to automatically acquire a concise 2D model of the human body and its parts using vision sensors. Finally, the ....

....the body parts recovered by the algorithm. The edges of the graph denote which parts are connected by joints. Step 2: If not all the frames of the motion sequence have been processed fit the models of the list to the image data using the physics based shape and motion estimation framework [9] and execute steps 3 and 4. Otherwise, output . Step 3: For each model in a: if the Parametric Composition Invocation Criterion is satisfied (e.g. this criterion is satisfied when the subject lifts her arm towards the horizontal position, as the apparent contour of the arm protrudes from ....

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580--591, June 1993.

....by Zheng and Chellapa[44] Keywords: Physics based modeling, shape from shading, deformable models, illuminant estimation, diffuse reflectance. 1. Introduction The integration of visual cues within a physics based deformable model framework has been attempted recently by several researchers [6, 26, 9] due to its potential for improved shape estimation. In all previous attempts, illumination constraints such as those appearing in the shape from shading problem, have never been considered. This is due to the nonlinear nature of the constraints and the fact that numerically robust methods for ....

....regardless of their type. This theory amounts to the use of Lagrange multipliers and a Baumgarte stabilization approach [2] to allow for the robust integration of those constraints. This approach, which is a generalization of the previously developed methodology for linear holonomic constraints [26], allows the incorporation of illumination constraints into deformable models. Furthermore, we showhow to handle large systems of constraints on physics based models, by proposing a fast technique for the computation of constraint forces. In particular, we demonstrate how any type of illumination ....

[Article contains additional citation context not shown here]

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. PAMI, 15(6):580--591, June 1993.

No context found.

D. Metaxas and D. Terzopouilos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physicsbased synthesis. IEEE Trans. Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

No context found.

D.N. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

No context found.

D. Metaxas and D. Terzopoulos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Patt. Anal. Mach. Intell., vol. 15, pp. 580--591, 1993.

No context found.

Dimitris Metaxas and Dimitris Terzopoulos. Shape and non-rigid motion estimation through physics-based synthesis. IEEE Trans. Pattern Analysis and Machine Intelligence, 15(6):580--591, 1993.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physicsbased synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580--591, June 1993.

No context found.

Metaxas, D. and Terzopoulos, D. 1993. Shape and nonrigid motion estimation through physics-based synthesis, IEEE Trans. Pattern Analysis and Machine Intelligence, 15(6):580--591.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. PAMI, 15(6):580 -- 591, 1993.

No context found.

Demetri Metaxas and Demetri Terzopoulos. Shape and non-rigid motion estimation through physics-based synthesis. IEEE Transaction on Pattern Analysis and Machine Intelligence, 15, June 1993.

No context found.

D. Metaxas and D. Terzopoulos, "Shape and Nonrigid Motion Estimation through Physics-based Synthesis", IEEE Transactions of Pattern Analysis and Machine Intelligence, vol. 15, no. 6, pp. 580--591, 1993.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580 -- 591, June 1993.

No context found.

D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):580--591 , June 1993.

No context found.

Metaxas, D. and Terzopoulos, D. Shape and non-rigid motion estimation through physics-based synthesis. IEEE Trans. Pattern Analysis and Machine Intelligence, 15:580591, 1993.

No context found.

Demetri Metaxas and Demetri Terzopoulos. Shape and non-rigid motion estimation through physics-based synthesis. IEEE Transaction on Pattern Analysis and Machine Intelligence, 15, June 1993.

No context found.

D. Metaxas and D. Terzopoulos, "Shape and nonrigid motion estimation through physic-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. , pp. 580--591, June 1993.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC