, Variational optic flow computation with a spatio-temporal smoothness constraint, Journal of Mathematical Imaging and Vision 14 (2001), 245--255.  Home/Search   Document Details and Download   Summary   Related Articles

....the location and z # [0, Z] is the time. We are looking for the optic flow field # u(x,y,z) v(x,y,z) # which describes the correspondence of image structures at di#erent times. Variational methods constitute one possibility to solve the optic flow problem; see e.g. 8, 14, 22, 37] In [38] a method is considered which is based on the following two assumptions: 1. Image structures do not change their grey value over time. Therefore, along their path (x(z) y(z) one obtains (19) 0 = df(x(z) y(z) z) dz = f x u f y v f z . 2. As second assumption we impose a spatio temporal ....

....see that the recovered optic flow field gives a quite realistic description of the person s movement towards the camera. Figure 3. a) Left: One frame of a hallway sequence with 256 256 16 pixels. A person is approaching the camera. b) Middle: Detail. c) Right: Computed optic flow. From [38] . 5. Geodesic Active Contours 5.1. Basic Idea and Theoretical Properties Active contours [18] play an important role in interactive image segmentation, in particular for medical applications. The basic idea is that the user specifies an initial guess of an interesting contour (organ, tumour, ....

, Variational optic flow computation with a spatio-temporal smoothness constraint, Journal of Mathematical Imaging and Vision 14 (2001), 245--255.

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