Theses and Dissertations

Spring 2016

Zhang, Xi

Visual tracking serves an important role in a wide variety of applications like video surveillance, robotic manipulation and augmented reality. The goal of tracking in the last two cases here is to efficiently and accurately locate the object in each frame of an image sequence/stream, with the...

Fall 2013

Popuri, Karteek

Medical image registration and segmentation are challenging because, medical images are generally corrupted by noise, image artifacts and the various anatomical regions of interest in medical images often do not have distinct sharp boundaries. However, these anatomical regions frequently...

Spring 2023

Johnstonbaugh, Kerrick

Choosing an appropriate action representation is an integral part of solving robotic manipulation problems. Published approaches include latent action models, which train context-conditioned neural networks to map lowdimensional latent actions to high-dimensional actuation commands. Such models...

Spring 2023

Petrich, Laura C.

Wheelchair-mounted robotic manipulators have the potential to help the elderly and individuals living with disabilities carry out their activities of daily living independently. While robotics researchers focus on assistive tasks from the perspective of various control schemes and motion types, ...

Fall 2023

Karimi, Amirmohammad

In classic reinforcement learning(RL) for continuous control, agents make decisions at discrete and fixed time intervals. The duration between decisions becomes a crucial hyperparameter. Setting it too short may increase the problem’s difficulty by requiring the agent to make numerous decisions...

Fall 2011

Birkbeck, Neil Aylon Charles

Photo-realistic renderings of humans are required for real-time graphics applications, and accurate human models are useful in applications such as model-based tracking. Non-rigid deformations of humans, e.g., deforming cloth and muscle bulging, are hard to model geometrically and are inefficient...

Spring 2018

Zhang, Zichen

Semantic segmentation is about classifying every pixel in an image. In recent years, methods based on Fully Convolutional Networks (FCN) have dominated this field in terms of segmentation accuracy. We are interested in tackling the challenges that these methods are faced with. First, it is...

Fall 2018

He, Shida

Semi-dense SLAM systems have become popular in the last few years. They can produce much denser point clouds than sparse SLAM while being computationally efficient (using only CPU). In previous works, the surface of the viewed scene was reconstructed in real-time by combining sparse SLAM system...

Fall 2011

Lovi, David Israel

This thesis addresses the problem of automatic real-time 3D reconstruction of general scenes from monocular video. Whereas many impressively accurate reconstruction techniques exist in the multi-view stereo literature, most are slow offline batch methods designed to work in highly calibrated...

Fall 2021

Jin, Jun

This thesis studies how to enable a real-world robot to efficiently learn a new task by watching human demonstration videos. We propose to introduce a geometric task structure as an interpretable inductive bias to the learning problem. We aim to learn a representation that geometrically encodes...