Search
Now showing items 1-10 of 34
Physics-driven variational methods for computer vision and shape-based imaging
(Georgia Institute of Technology, 2014-05-13)
In this dissertation, novel variational optical-flow and active-contour methods are investigated to address challenging problems in computer vision and shape-based imaging. Starting from traditional applications of these ...
Adaptive shadow removal for variable environmental conditions
(Georgia Institute of Technology, 2017-04-28)
The motivation for this research is to provide a quantitative model for improving shadow detection in arbitrary environments. Many computer vision applications extract foreground pixels to capture moving objects in a scene. ...
Scene flow for autonomous navigation
(Georgia Institute of Technology, 2018-04-30)
Today, there are various different paradigms for vision based autonomous navigation: mediated perception approaches that parse an entire scene to make driving decision, a direct perception approach that estimates the ...
Computer vision for driver assistance systems
(Georgia Institute of Technology, 2018-04-26)
The objective of the proposed thesis is to illustrate the training, validation and evaluation of vehicle detection algorithms using computer vision and deep learning methods, and vehicle tracking in video sequences. Object ...
Leap segmentation in mobile image and video analysis
(Georgia Institute of Technology, 2013-08-29)
As demand for real-time image processing increases, the need to improve the efficiency of image processing systems is growing. The process of image segmentation is often used in preprocessing stages of computer vision ...
Appearance-based vehicle localization across seasons in a metric map
(Georgia Institute of Technology, 2016-08-09)
Great strides have been made in recent years in developing the necessary technologies to make autonomous cars a reality. However, a number of challenges remain, a major one being that of accurate vehicle localization. This ...
Under-ice relative pose estimation and ice anomaly mapping with an unmanned underwater vehicle
(Georgia Institute of Technology, 2015-10-27)
Under-ice regions in both the Arctic and Antarctica are of great interest to many domains of science including biology, climate science, and planetary science. Great environmental and technical challenges face researchers ...
Vision-based autonomous navigation in medium level representation
(Georgia Institute of Technology, 2017-12-05)
Autonomous navigation for a mobile robot is required to operate in cluttered, unstruc-
tured environment at high speeds with efficient data gathering. Given the payload con-
straints and long-range sensing requirements, ...
Visual attention for high speed driving
(Georgia Institute of Technology, 2018-12-04)
Coupling of control and perception is an especially difficult problem. This thesis investigates this problem in the context of aggressive off-road driving. By jointly developing a robust 1:5 scale platform and leveraging ...
Automated benchmarking of surgical skills using machine learning
(Georgia Institute of Technology, 2018-11-09)
Surgical trainees are required to acquire specific skills during the course of their residency before performing real surgeries. Surgical training involves constant practice of skills and seeking feedback from supervising ...