creators_name: Stocker, Alan creators_name: Douglas, Rodney type: confpaper datestamp: 1999-04-26 lastmod: 2011-03-11 08:53:39 metadata_visibility: show title: Computation of Smooth Optical Flow in a Feedback Connected Analog Network ispublished: inpress subjects: comp-neuro-sci subjects: comp-sci-mach-vis full_text_status: public keywords: energy minimzation, optical flow, intensity constraint, aVLSI, neuromorphic, vision sensor, motion detection, constraint solving, analog network, real-time, collective computatio abstract: In 1986, Tanner and Mead \cite{Tanner_Mead86} implemented an interesting constraint satisfaction circuit for global motion sensing in aVLSI. We report here a new and improved aVLSI implementation that provides smooth optical flow as well as global motion in a two dimensional visual field. The computation of optical flow is an ill-posed problem, which expresses itself as the aperture problem. However, the optical flow can be estimated by the use of regularization methods, in which additional constraints are introduced in terms of a global energy functional that must be minimized. We show how the algorithmic constraints of Horn and Schunck \cite{Horn_Schunck81} on computing smooth optical flow can be mapped onto the physical constraints of an equivalent electronic network. date: 1998 date_type: published publisher: MIT Press, Cambridge refereed: FALSE citation: Stocker, Alan and Douglas, Rodney (1998) Computation of Smooth Optical Flow in a Feedback Connected Analog Network. [Conference Paper] (In Press) document_url: http://cogprints.org/82/1/nips98.ps document_url: http://cogprints.org/82/5/nips98.pdf