Computer Sciences Commons^™

Representation Learning With Adversarial Latent Autoencoders, Stanislav Pidhorskyi M.S.

Graduate Theses, Dissertations, and Problem Reports

A large number of deep learning methods applied to computer vision problems require encoder-decoder maps. These methods include, but are not limited to, self-representation learning, generalization, few-shot learning, and novelty detection. Encoder-decoder maps are also useful for photo manipulation, photo editing, superresolution, etc. Encoder-decoder maps are typically learned using autoencoder networks.
Traditionally, autoencoder reciprocity is achieved in the image-space using pixel-wise
similarity loss, which has a widely known flaw of producing non-realistic reconstructions. This flaw is typical for the Variational Autoencoder (VAE) family and is not only limited to pixel-wise similarity losses, but is common to all methods relying upon …

A Study Of Face Embedding In Face Recognition, Khanh Duc Le

Master's Theses

Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.

By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with …

Exploring Cyber-Physical Systems, Misbah Uddin Mohammed

Graduate Research Theses & Dissertations

The advances in IOT, Computer Vision, AI and Machine Learning have made these technologies ubiquitous to our daily lives. From Smart Phones to Connected Vehicles, Cyber Physical systems have been interspersed into everything we interact in today’s world. The aim or this thesis was to explore these advances in Cyber Physical Systems and analyze the different sectors they were affecting. We then hand-picked certain domains and explored further by carrying out practical projects using some of the latest software and hardware resources available. Technologies like Amazon Alexa services, NVIDIA Jetson boards, TensorFlow, OpenCV, NodeJS were heavily employed in our various …

Automatic Identification Of Animals In The Wild: A Comparative Study Between C-Capsule Networks And Deep Convolutional Neural Networks., Joel Kamdem Teto, Ying Xie

Master of Science in Computer Science Theses

The evolution of machine learning and computer vision in technology has driven a lot of

improvements and innovation into several domains. We see it being applied for credit decisions, insurance quotes, malware detection, fraud detection, email composition, and any other area having enough information to allow the machine to learn patterns. Over the years the number of sensors, cameras, and cognitive pieces of equipment placed in the wilderness has been growing exponentially. However, the resources (human) to leverage these data into something meaningful are not improving at the same rate. For instance, a team of scientist volunteers took 8.4 years, …

Integration Of Robotic Perception, Action, And Memory, Li Yang Ku

Doctoral Dissertations

In the book "On Intelligence", Hawkins states that intelligence should be measured by the capacity to memorize and predict patterns. I further suggest that the ability to predict action consequences based on perception and memory is essential for robots to demonstrate intelligent behaviors in unstructured environments. However, traditional approaches generally represent action and perception separately---as computer vision modules that recognize objects and as planners that execute actions based on labels and poses. I propose here a more integrated approach where action and perception are combined in a memory model, in which a sequence of actions can be planned based on …

Investigating Dataset Distinctiveness, Andrew Ulmer, Kent W. Gauen, Yung-Hsiang Lu, Zohar R. Kapach, Daniel P. Merrick

The Summer Undergraduate Research Fellowship (SURF) Symposium

Just as a human might struggle to interpret another human’s handwriting, a computer vision program might fail when asked to perform one task in two different domains. To be more specific, visualize a self-driving car as a human driver who had only ever driven on clear, sunny days, during daylight hours. This driver – the self-driving car – would inevitably face a significant challenge when asked to drive when it is violently raining or foggy during the night, putting the safety of its passengers in danger. An extensive understanding of the data we use to teach computer vision models – …

A Machine Learning Framework To Classify Mosquito Species From Smart-Phone Images, Mona Minakshi

USF Tampa Graduate Theses and Dissertations

Mosquito borne diseases have been a constant scourge across the globe resulting in numerous diseases with debilitating consequences, and also death. To derive trends on population of mosquitoes in an area, trained personnel lay traps, and after collecting trapped specimens, they spend hours under a microscope to inspect each specimen for identifying the actual species and logging it. This is vital, because multiple species of mosquitoes can reside in any area, and the vectors that some of them carry are not the same ones carried by others. The species identification process is naturally laborious, and imposes severe cognitive burden, since …

Sports Analytics With Computer Vision, Colby T. Jeffries

Senior Independent Study Theses

Computer vision in sports analytics is a relatively new development. With multi-million dollar systems like STATS’s SportVu, professional basketball teams are able to collect extremely fine-detailed data better than ever before. This concept can be scaled down to provide similar statistics collection to college and high school basketball teams. Here we investigate the creation of such a system using open-source technologies and less expensive hardware. In addition, using a similar technology, we examine basketball free throws to see whether a shooter’s form has a specific relationship to a shot’s outcome. A system that learns this relationship could be used to …

Real-Time Vision-Based Lane Detection With 1d Haar Wavelet Transform On Raspberry Pi, Vikas Reddy Sudini

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Rapid progress is being made towards the realization of autonomous cars. Since the technology is in its early stages, human intervention is still necessary in order to ensure hazard-free operation of autonomous driving systems. Substantial research efforts are underway to enhance driver and passenger safety in autonomous cars. Toward that end GreedyHaarSpiker, a real-time vision-based lane detection algorithm is proposed for road lane detection in different weather conditions. The algorithm has been implemented in Python 2.7 with OpenCV 3.0 and tested on a Raspberry Pi 3 Model B ARMv8 1GB RAM coupled to a Raspberry Pi camera board v2. To …

An Approach To Robust Homing With Stereovision, Fuqiang Fu, Damian Lyons

Faculty Publications

Visual Homing is a bioinspired approach to robot navigation which can be fast and uses few assumptions. However, visual homing in a cluttered and unstructured outdoor environment offers several challenges to homing methods that have been developed for primarily indoor environments. One issue is that any current image during homing may be tilted with respect to the home image. The second is that moving through a cluttered scene during homing may cause obstacles to interfere between the home scene and location and the current scene and location. In this paper, we introduce a robust method to improve a previous developed …

Investigating High Speed Localization Microscopy Through Experimental Methods, Data Processing Methods, And Applications Of Localization Microscopy To Biological Questions, Andrew J. Nelson

Electronic Theses and Dissertations

Fluorescence Photoactivation Localization Microscopy(FPALM) and other super resolution localization microscopy techniques can resolve structures with nanoscale resolution. Unlike techniques of electron microscopy, they are also compatible with live cell and live animal studies, making FPALM and related techniques ideal for answering questions about the dynamic nature of molecular biology in living systems. Many processes in biology occur on rapid sub second time scales requiring the imaging technique to be capable of resolving these processes not just with a high enough spatial resolution, but with an appropriate temporal resolution. To that end, this Dissertation in part investigates high speed FPALM as …

3d Sem Surface Reconstruction: An Optimized, Adaptive, And Intelligent Approach, Ahmad Pahlavan Tafti

Theses and Dissertations

Structural analysis of microscopic objects is a longstanding topic in several scientific disciplines, including biological, mechanical, and material sciences. The scanning electron microscope (SEM), as a promising imaging equipment has been around to determine the surface properties (e.g., compositions or geometries) of specimens by achieving increased magnification, contrast, and resolution greater than one nanometer. Whereas SEM micrographs still remain two-dimensional (2D), many research and educational questions truly require knowledge and information about their three-dimensional (3D) surface structures. Having 3D surfaces from SEM images would provide true anatomic shapes of micro samples which would allow for quantitative measurements and informative visualization …

Pedestrian Detection Using Basic Polyline: A Geometric Framework For Pedestrian Detection, Liang Gongbo

Masters Theses & Specialist Projects

Pedestrian detection has been an active research area for computer vision in recently years. It has many applications that could improve our lives, such as video surveillance security, auto-driving assistance systems, etc. The approaches of pedestrian detection could be roughly categorized into two categories, shape-based approaches and appearance-based approaches. In the literature, most of approaches are appearance-based. Shape-based approaches are usually integrated with an appearance-based approach to speed up a detection process.

In this thesis, I propose a shape-based pedestrian detection framework using the geometric features of human to detect pedestrians. This framework includes three main steps. Give a static …

Feature Encoding Strategies For Multi-View Image Classification, Kyle Doerr

Electronic Thesis and Dissertation Repository

Machine vision systems can vary greatly in size and complexity depending on the task at hand. However, the purpose of inspection, quality and reliability remains the same. This work sets out to bridge the gap between traditional machine vision and computer vision. By applying powerful computer vision techniques, we are able to achieve more robust solutions in manufacturing settings. This thesis presents a framework for applying powerful new image classification techniques used for image retrieval in the Bag of Words (BoW) framework. In addition, an exhaustive evaluation of commonly used feature pooling approaches is conducted with results showing that spatial …

Calculating Staircase Slope From A Single Image, Nicholas Joseph Clarke

Master's Theses

Realistic modeling of a 3D environment has grown in popularity due to the increasing realm of practical applications. Whether for practical navigation purposes, entertainment value, or architectural standardization, the ability to determine the dimensions of a room is becoming more and more important. One of the trickier, but critical, features within any multistory environment is the staircase. Staircases are difficult to model because of their uneven surface and various depth aspects. Coupling this need is a variety of ways to reach this goal. Unfortunately, many such methods rely upon specialized sensory equipment, multiple calibrated cameras, or other such impractical setups. …

Geological Object Recognition In Extraterrestrial Environments, Gregory M. Elfers

Electronic Thesis and Dissertation Repository

On July 4 1997, the landing of NASA’s Pathnder probe and its rover Sojourner marked the beginning of a new era in space exploration; robots with the ability to move have made up the vanguard of human extraterrestrial exploration ever since. With Sojourners landing, for the rst time, a ground traversing robot was at a distance too far from earth to make direct human control practical. This has given rise to the development of autonomous systems to improve the e?ciency of these robots,in both their ability to move,and their ability to make decisions regarding their environment. Computer Vision comprises a …

Long Range Motion Estimation And Applications, Laura Sevilla-Lara

Doctoral Dissertations

Finding correspondences between images underlies many computer vision problems, such as op- tical flow, tracking, stereovision and alignment. Finding these correspondences involves formulating a matching function and optimizing it. This optimization process is often gradient descent, which avoids exhaustive search, but relies on the assumption of being in the basin of attraction of the right local minimum. This is often the case when the displacement is small, and current methods obtain very accurate results for small motions. However, when the motion is large and the matching function is abrupt this assumption is less likely to be true. One traditional way …

Element Detection In Japanese Comic Book Panels, Toshihiro Kuboi

Master's Theses

Comic books are a unique and increasingly popular form of entertainment combining visual and textual elements of communication. This work pertains to making comic books more accessible. Specifically, this paper explains how we detect elements such as speech bubbles present in Japanese comic book panels. Some applications of the work presented in this paper are automatic detection of text and its transformation into audio or into other languages. Automatic detection of elements can also allow reasoning and analysis at a deeper semantic level than what’s possible today. Our approach uses an expert system and a machine learning system. The expert …

Monocular Pose Estimation And Shape Reconstruction Of Quasi-Articulated Objects With Consumer Depth Camera, Mao Ye

Theses and Dissertations--Computer Science

Quasi-articulated objects, such as human beings, are among the most commonly seen objects in our daily lives. Extensive research have been dedicated to 3D shape reconstruction and motion analysis for this type of objects for decades. A major motivation is their wide applications, such as in entertainment, surveillance and health care. Most of existing studies relied on one or more regular video cameras. In recent years, commodity depth sensors have become more and more widely available. The geometric measurements delivered by the depth sensors provide significantly valuable information for these tasks. In this dissertation, we propose three algorithms for monocular …

Automatic Classification Of Epilepsy Lesions, Junwei Sun

Electronic Thesis and Dissertation Repository

Epilepsy is a common and diverse set of chronic neurological disorders characterized by seizures. Epileptic seizures result from abnormal, excessive or hypersynchronous neuronal activity in the brain. Seizure types are organized firstly according to whether the source of the seizure within the brain is localized or distributed. In this work, our objective is to validate the use of MRI (Magnetic Resonance Imaging) for localizing seizure focus for improved surgical planning. We apply computer vision and machine learning techniques to tackle the problem of epilepsy lesion classification. First datasets of digitized histology images from brain cortexes of different patients are obtained …

Classic Mosaics And Visual Correspondence Via Graph-Cut Based Energy Optimization, Yu Liu

Electronic Thesis and Dissertation Repository

Computer graphics and computer vision were traditionally two distinct research fields focusing on opposite topics. Lately, they have been increasingly borrowing ideas and tools from each other. In this thesis, we investigate two problems in computer vision and graphics that rely on the same tool, namely energy optimization with graph cuts.

In the area of computer graphics, we address the problem of generating artificial classic mosaics, still and animated. The main purpose of artificial mosaics is to help a user to create digital art. First we reformulate our previous static mosaic work in a more principled global optimization framework. Then, …