Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
A fundamental problem in computer vision is to partition an image into meaningful segments. While image segmentation is required by many applications, the thesis focuses on segmentation of computed tomography (CT) images for analysis and quality control of composite materials. The key research contribution of this thesis is a novel...
This thesis addresses a fundamental computer vision problem, that of action recognition. The goal of action recognition is to recognize a class of human actions in a given video. Action recognition has a wide range of applications, including automated surveillance, sports video analysis, internet-based searches etc. The main challenge is...
A general discrete-time, adaptive, multidimensional framework is introduced
for estimating the motion of one or several object features from their successive
non-linear projections on an image plane. The motion model consists of
a set of linear difference equations with parameters estimated recursively from
a non-linear observation equation. The model dimensionality...
Remote-access computer file serials, often referred to simply as electronic serials, possess characteristics that challenge our definition of the term “serial” and our ability to catalog them according to the established cataloging code. These challenges are reflected in the library science literature, where cataloging and indexing issues have generated thoughtful...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
This report presents an efficient method for semi-supervised video object segmentation – the problem of identifying foreground pixels occupied by a target object. The target is specified by the ground-truth mask in the first video frame. While the state of the art achieves a segmentation accuracy greater than 80%, it...
A comprehensive system to locate and track objects in two or three
dimensional space, using non-contact video sensing techniques is described. The
need exists to be able to quantify range and proximity of objects that would be
difficult or impossible to measure using standard contact based sensor technology.
Available video...
Gusset plates are an important component of bridges. They are thick sheets of steel that join steel members together using fasteners and also strengthen their joint. Transportation agencies regularly evaluate and rate their inventories of gusset plate connections using visual inspection, which is very costly. To address this issue, we...
In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...