Browsing College of Engineering (MU) by Thesis Advisor "DeSouza, Guilherme"
Now showing items 18 of 8

Applications of parallel computing in robotics problems
(University of MissouriColumbia, 2013)Many typical robotics problems involve search in highdimensional spaces, where realtime execution is hard to be achieved. This thesis presents two case studies of parallel computation in such robotics problems. More ... 
A biologically inspired optical flow system for motion detection and object identification
(University of MissouriColumbia, 2007)Optical flow is possibly the best known method for motion segmentation. However its application is restricted to offline processing as it requires extensive computational resources and time. This thesis explores an optical ... 
Cellular neural network virtual machine for graphics hardware with applications in image processing
(University of MissouriColumbia, 2009)The inherent massive parallelism of cellular neural networks makes them an ideal computational platform for kernelbased algorithms and image processing. Generalpurpose GPUs provide similar massive parallelism, but it can ... 
A compact representation for 3D animation using octrees and affine transformation
(University of MissouriColumbia, 2009)We present a new and compact 3D representation for nonrigid objects using motion vectors between two consecutive frames. Our method relies on an Octree to recursively partition the object into smaller parts. Each part is ... 
A modelbased, generative and stochastic method for human motion capture using hierarchical particle filters
(University of MissouriColumbia, 2011)Searching in probability spaces can prove to be an impractical task due to the high dimensionality of the state vector. In the context of tracking human pose through image features in video sequences, the number of ... 
Pattern recognition of mixed signals using guided underdetermined source signal separation
(University of MissouriColumbia, 2011)In typical problems involving pattern recognition, the challenge lies in selecting a good set of features and in devising a reliable algorithm to recognize any particular vector of such features. In general, even when noise ... 
Planar detection using modified expectation maximization
(University of MissouriColumbia, 2011)In this work the task of planar detection in an image pair is cast as an incomplete data problem where the parameters to be estimated are the ones that define the homographies induced by the planar regions in the scene. ... 
Target geolocation from airborne video without terrain data
(University of MissouriColumbia, 2010)The task of geolocating targets from airborne video is required for many applications in surveillance, law enforcement, reconnaissance, etc. The usual approaches to target geolocation involve terrain data, single target ...