Terzopoulos, D.: Physically-based fusion of visual data over space, time and scale. In Aggarwal, J., ed.: Multisensor Fusion for Computer Vision. Springer-Verlag (1993) 63--69  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of each estimate: y 1 , y 2 ) p(y 1 x)p(y 2 x)p(x) 1) The combined estimate x is the maximum a posteriori estimate of x obtained from this distribution. Examples of frameworks for cue integration that are defined this way include Kalman filters [5, 6] and physically based frameworks [15, 16]. These probabilistic approaches are demonstrated pictorially in Figure 2(b) showing how the combined estimate x weights together the individual results based on their reliabilities, and produces an estimate which has less uncertainty (depicted as an ellipsoid with its mean at its center) than ....

Terzopoulos, D.: Physically-based fusion of visual data over space, time and scale. In Aggarwal, J., ed.: Multisensor Fusion for Computer Vision. Springer-Verlag (1993) 63--69

....situations, 21) is solved iteratively. This is also comparable to using a Kalman filter to combine sources together (or an iterated extended Kalman filter in the non linear case) In a deformable model framework, this approach is achieved by adding together weighted combinations of forces [46, 48] or energies [18] derived from data sources. The dynamic system produces a weighted least squares estimate similar to (21) as it converges. With hard constraints, instead of combining solutions as above, we solve a constrained system: the equation originally used to solve for flow, B qm I t = ....

D. Terzopoulos. Physically-based fusion of visual data over space, time and scale. In J. Aggarwal, editor, Multisensor Fusion for Computer Vision, pages 63--69. Springer-Verlag, 1993. 41

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