R. Chellappa

Learn More
We are interested in restoring a degraded scene while preserving the edges. Edges are represented as line pr& cesses and are estimated along with the intensities in a Maximum A Posien'ori (MAP) framework. Aasumptions regarding the prior and degradation distributions reduce the problem to one of energy function minimization. The energy function is highly(More)
A method for computing optical flow using a neural network is presented. Usually, the measurement primitives used for computing optical flow from successive image frames are the image-intensity values and their spatial and temporal derivatives, and tokens such as edges, corners, and linear features. Conventional methods based on such primitives suffer from(More)
Motion stereo infers depth information from a sequence of image frames. Both batch and recursive neural network algorithms for motion stereo are presented. A discrete neural network is used for representing the disparity field. The batch algorithm first integrates information from all images by embedding them into the bias inputs of the network. Matching is(More)
We describe a computer simulation of atmospheric and target effects on the accuracy of range measurements using pulsed laser radars with p-i-n or avalanche photodiodes for direct detection. The computer simulation produces simulated images as a function of a wide variety of atmospheric, target, and sensor parameters for laser radars with range accuracies(More)
Abstract: Image feature detection is a fundamental issue in many intermediate level vision problems such as stereo, motion correspondence, image registration, and object recognition. In this paper we present an approach to feature detection based on a scale-interaction model. This feature detector is responsive to short lines, line endings, corners and(More)
Title of dissertation: GEOMETRIC STRUCTURES AND OPTIMIZATION ON SPACES OF FINITE FRAMES Nathaniel Strawn, Doctor of Philosophy, 2011 Dissertation directed by: Professor John J. Benedetto Professor Radu V. Balan Department of Mathematics A finite (μ, S)-frame variety consists of the real or complex matrices F = [f1 · · · fN ] with frame operator FF ∗ = S,(More)
Title of Dissertation: VIDEO ANALYSIS UNDER SEVERE OCCLUSIONS Anurag Mittal, Doctor of Philosophy, 2002 Dissertation directed by: Dr. Larry Davis Department of Computer Science Many surveillance sites are heavily crowded. Occlusion is a major factor to be considered in building surveillance systems for these sites. To achieve a certain degree of visibility,(More)