Lefschetz Center for Dynamical Systems Seminar
LEMS and Electrical Science Seminar
Brown Applied Mathematics Pattern Theory and Vision Seminar
Abstract: We develop a probabilistic theory for the temporal integration of motion. The input data is temporally grouped and used to predict and estimate motion flows. The theory is implemented by a parallel network model, derived from the theory, which has similarities to the cortex. The theory is inspired by, and gives qualitative agreement with, psychophysical data involving motion outliers and occluders.
Brown Applied Mathematics Pattern Theory and Vision Seminar
Brown Analysis Seminar
Brown University Graduate School, Dissertation Defense Information
Applied Mathematics Colloquium
Joint LEMS/Applied Mathematics Seminar
Abstract: A heretofore unsolved challenge is the completely automatic and accurate estimation of road boundaries in aerial images when the roads may be partially or completely locally occluded and clutter may be prevalent. In this talk I introduce a roadfinder that is effective in meeting this challenge. The roadfinder begins with one or more seeds on each long road, and then accurately estimates the remaining boundaries, which can be found completely automatically by the algorithm. The algorithm is robust to missing boundary edges on one side of the road and on both sides of the road simultaneously. These arise from shadows and occlusion by trees, small structures, etc. It is also robust to clutter within the road caused by cars or trucks, and to clutter resulting from intersecting or close parallel roads. The algorithm is based on simple clutter and occlusion models and a combined Multihypothesis Generalized Kalman Filter (MGKF).
PDE Seminar
Department of Mathematics Colloquium
<--- 1997 Index