Engineering Commons^™

Design And Verification Environment For High-Performance Video-Based Embedded Systems, Michael Mefenza Nentedem

Graduate Theses and Dissertations

In this dissertation, a method and a tool to enable design and verification of computation demanding embedded vision-based systems is presented. Starting with an executable specification in OpenCV, we provide subsequent refinements and verification down to a system-on-chip prototype into an FPGA-Based smart camera. At each level of abstraction, properties of image processing applications are used along with structure composition to provide a generic architecture that can be automatically verified and mapped to the lower abstraction level. The result is a framework that encapsulates the computer vision library OpenCV at the highest level, integrates Accelera's System-C/TLM with UVM and QEMU-OS …

Integrating Pavement Crack Detection And Analysis Using Autonomous Unmanned Aerial Vehicle Imagery, Patrick J. Grandsaert

Theses and Dissertations

Efficient, reliable data is necessary to make informed decisions on how to best manage aging road assets. This research explores a new method to automate the collection, processing, and analysis of transportation networks using Unmanned Aerial Vehicles and Computer Vision technology. While there are current methodologies to accomplish road assessment manually and semi-autonomously, this research is a proof of concept to obtain the road assessment faster and cheaper with a vision for little to no human interaction required. This research evaluates the strengths of applying UAV technology to pavement assessments and identifies where further work is needed. Furthermore, it validates …

A Monocular Slam Method To Estimate Relative Pose During Satellite Proximity Operations, Scott J. Kelly

Theses and Dissertations

Automated satellite proximity operations is an increasingly relevant area of mission operations for the US Air Force with potential to significantly enhance space situational awareness (SSA). Simultaneous localization and mapping (SLAM) is a computer vision method of constructing and updating a 3D map while keeping track of the location and orientation of the imaging agent inside the map. The main objective of this research effort is to design a monocular SLAM method customized for the space environment. The method developed in this research will be implemented in an indoor proximity operations simulation laboratory. A run-time analysis is performed, showing near …

Extraction Of Pictorial Energy Information From Campus Unmetered Buildings Using Image Processing Techniques, Yachen Tang

Dissertations, Master's Theses and Master's Reports - Open

In recent years, advanced metering infrastructure (AMI) has been the main research focus due to the traditional power grid has been restricted to meet development requirements. There has been an ongoing effort to increase the number of AMI devices that provide real-time data readings to improve system observability. Deployed AMI across distribution secondary networks provides load and consumption information for individual households which can improve grid management. Significant upgrade costs associated with retrofitting existing meters with network-capable sensing can be made more economical by using image processing methods to extract usage information from images of the existing meters. This thesis …

Analytical Study Of Computer Vision-Based Pavement Crack Quantification Using Machine Learning Techniques, Soroush Mokhtari

Electronic Theses and Dissertations

Image-based techniques are a promising non-destructive approach for road pavement condition evaluation. The main objective of this study is to extract, quantify and evaluate important surface defects, such as cracks, using an automated computer vision-based system to provide a better understanding of the pavement deterioration process. To achieve this objective, an automated crack-recognition software was developed, employing a series of image processing algorithms of crack extraction, crack grouping, and crack detection. Bottom-hat morphological technique was used to remove the random background of pavement images and extract cracks, selectively based on their shapes, sizes, and intensities using a relatively small number …

Thermographic Investigation Of Laser Metal Deposition, Sreekar Karnati

Masters Theses

"Laser metal deposition as an additive manufacturing technique has been proven to possess the capability for fabricating complex, intricate geometries and excellent material properties through material deposition. Accurate manufacture of such geometric features would require precise control over the material deposition process. The need of the hour are process monitoring and analyses mechanisms that are crucial in ascertaining the occurrence of the intended actions during deposition while also serving as effective learning tools. The current work involved developing and incorporating an Infra-Red (IR) camera as a process monitoring tool for laser metal deposition. Using the IR camera the thermal dynamics …

Computer Aided Detection Of Oral Lesions On Ct Images, Shaikat Mahmood Galib

Masters Theses

"Oral lesions are important findings on computed tomography images. They are difficult to detect on CT images because of low contrast, arbitrary orientation of objects, complicated topology and lack of clear lines indicating lesions. In this thesis, a fully automatic method to detect oral lesions from dental CT images is proposed to identify (1) Closed boundary lesions and (2) Bone deformation lesions. Two algorithms were developed to recognize these two types of lesions, which cover most of the lesion types that can be found on CT images. The results were validated using a dataset of 52 patients. Using non training …

Automated Image Interpretation For Science Autonomy In Robotic Planetary Exploration, Raymond Francis

Electronic Thesis and Dissertation Repository

Advances in the capabilities of robotic planetary exploration missions have increased the wealth of scientific data they produce, presenting challenges for mission science and operations imposed by the limits of interplanetary radio communications. These data budget pressures can be relieved by increased robotic autonomy, both for onboard operations tasks and for decision- making in response to science data.

This thesis presents new techniques in automated image interpretation for natural scenes of relevance to planetary science and exploration, and elaborates autonomy scenarios under which they could be used to extend the reach and performance of exploration missions on planetary surfaces.

Two …

Cervical Cancer Histology Image Feature Extraction And Classification, Peng Guo

Masters Theses

"Cervical cancer, the second most common cancer affecting women worldwide and the most common in developing countries can be cured if detected early and treated. Expert pathologists routinely visually examine histology slides for cervix tissue abnormality assessment. In previous research, an automated, localized, fusion-based approach was investigated for classifying squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on image analysis of 62 digitized histology images obtained through the National Library of Medicine. In this research, CIN grade assessments from two pathologists are analyzed and are used to facilitate atypical cell concentration feature development …

Enhanced Sonar Array Target Localization Using Time-Frequency Interference Phenomena, Jordan Almon Shibley

Dissertations and Theses

The ability of traditional active sonar processing methods to detect targets is often limited by clutter and reverberation from ocean environments. Similarly, multipath arrivals from radiating sources such as ships and submarines are received at sensors in passive sonar systems. Reverberation and multipath signals introduce constructive and destructive interference patterns in received spectrograms in both active and passive sonar applications that vary with target range and frequency. The characterization and use of interference phenomena can provide insights into environmental parameters and target movement in conjunction with standard processing methods including spectrograms and array beamforming.

This thesis focuses on utilizing the …

Studies On Microscopic Flow Structure Inside A Rectangular Circulating Fluidized Bed Through Image Analysis, Jingsi Yang

Electronic Thesis and Dissertation Repository

The microscopic flow structure is studied systematically and comprehensively through a visualization system in a narrow rectangular circulating fluidized bed (CFB) transparent Plexiglas riser with a height of 7.6 m and a cross section of 19 mm × 114 mm. A visualization system consisting of a high-speed video camera, a light source, and image processing and analyzing programs is designed and developed to enable the flow structure to be visualized directly and studied quantitatively. FCC particles of 67 μm are used as the bed materials under different operating conditions with superficial gas velocity (U_g) and solids circulation rate …

Geometric Modeling Of Non-Rigid 3d Shapes : Theory And Application To Object Recognition., Mostafa Abdelrahman

Electronic Theses and Dissertations

One of the major goals of computer vision is the development of flexible and efficient methods for shape representation. This is true, especially for non-rigid 3D shapes where a great variety of shapes are produced as a result of deformations of a non-rigid object. Modeling these non-rigid shapes is a very challenging problem. Being able to analyze the properties of such shapes and describe their behavior is the key issue in research. Also, considering photometric features can play an important role in many shape analysis applications, such as shape matching and correspondence because it contains rich information about the visual …

Application Of Image Processing And Finite Element Analysis In Modeling Chloride Diffusion In Concrete, Arash Razmjoo

All Dissertations

Utilizing numerical simulation models to predict the long-term mechanical and transport behavior of concrete structures is becoming increasingly popular. The majority of these models have been developed using laboratory test data that consider concrete as a homogeneous material with spherical aggregates. These models could not be a represented of real concrete because it has no primitive shaped aggregate besides that the porosity size and distribution varies from point to point. In this study a novel method for more accurate prediction of the chloride diffusion in concrete was developed. A general framework of the quantitative computed tomography (QCT) and finite element …

Enhanced Diagnostic Accuracy Of Mammograms On A Mobile Device, Sharanya Padmanabhan

Open Access Theses

With the death of a woman every 13 minutes in the US, and one every minute worldwide, due to breast cancer, the need for early detection cannot be overstated. Mammography is a boon for both early detection and screening of breast tumors. It is an imaging system that uses low dose (9mrem) x-rays for examining the breasts, by the electrons reflected from the tissues (thermoelectric effect). However, there are 20% false positives and 10% false negatives in current practice. Hence, there is a critical need for enhancing the accuracy of these mammograms. Towards this, this thesis was aimed at enhancing …

Vision-Based Sensing And Optimal Control For Low-Cost And Small Satellite Platforms, Bradley Sease

Electronic Theses and Dissertations

Current trends in spacecraft are leading to smaller, more inexpensive options whenever possible. This shift has been primarily pursued for the opportunity to open a new frontier for technologies with a small financial obligation. Limited power, processing, pointing, and communication capabilities are all common issues which must be considered when miniaturizing systems and implementing low-cost components. This thesis addresses some of these concerns by applying two methods, in attitude estimation and control. Additionally, these methods are not restricted to only small, inexpensive satellites, but offer a benefit to large-scale spacecraft as well. First, star cameras are examined for the tendency …

Process Study And Control Of Electron Beam Melting Technology Using Infrared Thermography, Jorge Mireles

Open Access Theses & Dissertations

An IR camera was installed in an Arcam A2 system (Arcam AB, Mölndal, Sweeden) and layer-by-layer image acquisition was achieved. The camera's capability to detect manufacturing defects was evaluated by implementing computer vision techniques using LabVIEW measurement and programming software (National Instruments, Austin, TX). Thermal maps acquired by the IR camera allowed layer-by-layer part temperature to be recorded. A core objective of this research was to study the impact of processing temperature on EBM-fabricated Ti-6Al-4V parts and achieve controlled mechanical properties. In this research, build variations were achieved by modifying parameters that change processing temperature from the standard processing temperature. …

Feature Extraction Through K-Means Segmentation For Melanoma Detection, Snigdha Priya Bommadevara

Masters Theses

"Malignant melanoma is responsible for 75% of the deaths caused due to skin cancer annually. However, melanoma detection can be possible through feature extraction and pattern classification, which can lower the risk, if the melanoma is detected at an early stage. Clustering is one of the most useful tools used to differentiate features that can contribute to melanoma. This research work uses the k-means clustering algorithm for implementation of color segmentation. However, k-means clustering requires a predefined value of k, i.e., the number of clusters must be specified at the beginning of the run. This research uses a predefined value …

Digital Image-Based Frameworks For Monitoring And Controlling Of Particulate Systems, Bing Zhang

LSU Doctoral Dissertations

Particulate processes have been widely involved in various industries and most products in the chemical industry today are manufactured as particulates. Previous research and practise illustrate that the final product quality can be influenced by particle properties such as size and shape which are related to operating conditions. Online characterization of these particles is an important step for maintaining desired product quality in particulate processes. Image-based characterization method for the purpose of monitoring and control particulate processes is very promising and attractive. The development of a digital image-based framework, in the context of this research, can be envisioned in two …

Automated Semantic Content Extraction From Images, Mahdi Arab Khazaeli

LSU Doctoral Dissertations

In this study, an automatic semantic segmentation and object recognition methodology is implemented which bridges the semantic gap between low level features of image content and high level conceptual meaning. Semantically understanding an image is essential in modeling autonomous robots, targeting customers in marketing or reverse engineering of building information modeling in the construction industry. To achieve an understanding of a room from a single image we proposed a new object recognition framework which has four major components: segmentation, scene detection, conceptual cueing and object recognition. The new segmentation methodology developed in this research extends Felzenswalb's cost function to include …

Feature Extraction Through Median-Split Algorithm Segmentation For Melanoma Detection, Venkata Sai Narasimha Kaushik Ghantasala

Masters Theses

""Detection of melanoma remains an empirical clinical science. New tools for automatic discrimination of melanoma from benign lesions in digitized dermoscopy images may allow an improvement in early detection of melanoma. This research implements a fast version of the median split algorithm in an open source format and applied to four-color splitting of the lesion area to capture the architectural disorder apparent in melanoma colors. This version of the median split algorithm splits colors along the color axis with maximum range". For a dermoscopy set of 888 images, K-means clustering algorithm is compared with a median split algorithm to find …

A Novel Method For Determining Acetabular Orientation, Sean Higgins

Theses and Dissertations

Enhanced knowledge of the acetabulum is of paramount importance in the diagnostic, planning, and execution stages of procedures and treatments targeting the hip joint. The convoluted and highly variable morphology of the structures comprising the bony pelvis make ascertaining measures of the acetabulum challenging. Furthermore, current methods for determining acetabular orientation assume symmetry between the separate halves of the pelvis by utilizing a coordinate system based on bilateral landmarks. The purpose of this study was to determine the three-dimensional orientation of the entire acetabulum. For this research, an improved programmatic method was developed for determining acetabular orientation using three-dimensional data. …

Quantitative Biomechanical Evaluation Of Upper Extremity: Strain Behavior Of The Humerus Diaphysis Under Loading, Prateek Grover

Dissertations (1934 -)

While mechanical behavior of the adult human lower extremity long bones under loading has been studied extensively, the same is not true for the adult human humerus. Mechanical data reported for cadaveric humeri and anatomic humerus models are limited to stiffness and rigidity. Strain characteristics of the humerus diaphysis as a function of loading provide a valuable addition to the currently limited knowledge. The objective of this dissertation was to accomplish this goal, using numerical/finite element (FE) methods applied to a standard anatomic humerus model (Reference-Humerus) that was developed from the NIH Visible Human Project for this purpose. Four phases …

Framework Development For Construction Safety Visualization, Kishor Shrestha

UNLV Theses, Dissertations, Professional Papers, and Capstones

Throughout the history of the construction industry, many fatalities and injuries have occurred in construction sites. One of the major causes of accidents is unsafe site conditions; basically, this is due to inadequate supervision. To improve upon the traditional supervision approach, this study proposes a `Framework Development for Construction Safety Visualization' approach. In addition to this, a computer vision Edge Detection Algorithm was developed and tested to convert construction site still images into edges of the objects in the images. The framework development of this study uses computer vision, robot vision, image compression, pattern recognition, internet transmission, network communication, and …

Developing Novel Methods To Characterize Liquid Dispersion In A Fluidized Bed, Masoumeh Farkhondehkavaki

Electronic Thesis and Dissertation Repository

The performance of several important industrial processes, such as fluid coking or fluid catalytic cracking, is dependent on the good distribution of liquid feed sprayed into a fluidized bed of hot inert or catalytic particles, respectively.

Liquid injected into a fluidized bed is distributed in three different ways: (i) free moisture, or liquid coating individual particles; (ii) wet micro-agglomerates, which are fluidized; and (iii) wet macro-agglomerates, which settle to the bottom of the bed. This study develops and evaluates various methods for the determination of this moisture.

In the study using electrical techniques, two different kinds of electrodes geometries are …

Enhanced Image-Aided Navigation Algorithm With Automatic Calibration And Affine Distortion Prediction, Juan D. Jurado

Theses and Dissertations

This research aims at improving two key steps within the image aided navigation process: camera calibration and landmark tracking. The camera calibration step is improved by automating the point correspondence calculation within the standard camera calibration algorithm, thereby reducing the required time for calibration while maintaining the output model accuracy. The feature landmark tracking step is improved by digitally simulating affine distortions on input images in order to calculate more accurate feature descriptors for improved feature matching in high relative viewpoint change. These techniques are experimentally demonstrated in an outdoor environment with a consumer-grade inertial sensor and three imaging sensors, …

Spectral Detection Of Human Skin In Vis-Swir Hyperspectral Imagery Without Radiometric Calibration, Andrew P. Beisley

Theses and Dissertations

Many spectral detection algorithms require precise ground truth measurements that are hand-selected in the image to apply radiometric calibration, converting image pixels into estimated reflectance vectors. That process is impractical for mobile, real-time hyperspectral target detection systems, which cannot empirically derive a pixel-to-reflectance relationship from objects in the image. Implementing automatic target recognition on high-speed snapshot hyperspectral cameras requires the ability to spectrally detect targets without performing radiometric calibration. This thesis demonstrates human skin detection on hyperspectral data collected at a high frame rate without using calibration panels, even as the illumination in the scene changes. Compared to an established …

Traumatic Brain Injury Assessment Using The Integration Of Pattern Recognition Methods And Finite Element Analysis, Aghazadeh Babak Seyed

Theses and Dissertations

The overall goal of this research is to develop methods and algorithms to investigate the severity of Traumatic brain injury (TBI) and to estimate the intracranial pressure (ICP) level non-invasively. Brain x-ray computed tomography (CT) images and artificial intelligence methods are employed to estimate the level of ICP. Fully anisotropic complex wavelet transform features are proposed to extract directional textural features from brain images. Different feature selection and classification methods are tested to find the optimal feature vector and estimate the ICP using support vector regression. By using systematic feature extraction, selection and classification, promising results on ICP estimation are …

Accelerating Pattern Recognition Algorithms On Parallel Computing Architectures, Kenneth Rice

All Dissertations

The move to more parallel computing architectures places more responsibility on the programmer to achieve greater performance. The programmer must now have a greater understanding of the underlying architecture and the inherent algorithmic parallelism. Using parallel computing architectures for exploiting algorithmic parallelism can be a complex task. This dissertation demonstrates various techniques for using parallel computing architectures to exploit algorithmic parallelism. Specifically, three pattern recognition (PR) approaches are examined for acceleration across multiple parallel computing architectures, namely field programmable gate arrays (FPGAs) and general purpose graphical processing units (GPGPUs).
Phase-only filter correlation for fingerprint identification was studied as the first …

Measuring Digital System Latency From Sensing To Actuation At Continuous 1 Millisecond Resolution, Weixin Wu

All Theses

This thesis describes a new method for measuring the end-to-end latency between sensing and actuation in a digital computing system. Compared to previous work, which generally measures the latency at 16-33 ms intervals or at discrete events separated by hundreds of ms, our new method measures the latency continuously at 1 millisecond resolution. This allows for the observation of variations in latency over sub 1 s periods, instead of relying upon averages of measurements. We have applied our method to two systems, the ?rst using a camera for sensing and an LCD monitor for actuation, and the second using an …

Automated Visual Monitoring Of Machining Equipment, Timothy Wayne Ragland

Masters Theses

Metalworking equipment is designed to modify a sheet, rod, or block of metal material in order to shape it for a specific application. This equipment can operate on the metal by bending it, drilling through it, or by cutting it. For small-scale operations, many tools require a significant amount of manual input. Unless the operator has extensive training and experience, the manual input may not be precise enough for fine details that may be needed in some applications. For example, with a bending brake, obtaining an accurate angle for the bend may be quite difficult. For a particular application, an …