H.-H. Nagel and W. Enkelmann, 'n investigation of smoothness constraints fi*r the estimation of displacement vector fields from image sequences." IEEE Trans. PAMI 8:565-593. 1986.  Home/Search   Document Not in Database   Summary   Related Articles

....[25] Second, by characterizing the level of uncertainty in the flow. it allows us to evaluate the potential accuracy of the algorithm independent of how flow is obtained. Finally, bivariate Gaussian distributions can capture the distinctions between knowing zero, one, or both components of flow [1, 11, 22], and therefore subsume the notion of the aper ture problem. The problem of optical flow estimation has been studied extensively. Early approaches used the ratio of the spatial and temporal image derivatives [12] while more recent approaches have used correlation between images [11 or ....

....flow was that which minimized the total error 82 = jf(8,2 a28, dx dy where a is a blending constant. More recently, this approach has been formalized using the theory of regularization [31] and extended to use two dimensional confidence measures equivalent to local covariance estimates [1, 22]. For our application, smoothing is done on the disparity field, using the inverse variance of the disparity Kalman Filter based Algorithms for Estimating Depth from hnage Sequences 217 estimate as the confidence in each measurement. The smoother we use is the generalized piecewise continuous ....

H.-H. Nagel and W. Enkelmann, 'n investigation of smoothness constraints fi*r the estimation of displacement vector fields from image sequences." IEEE Trans. PAMI 8:565-593. 1986.

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