Engineering Commons^™

Human Following Using Kinect V2, Nate J. Titus, Tori M. Handley, Josiah D. Watson

The Research and Scholarship Symposium (2013-2019)

With the emergence of continuously improving imaging and image processing technologies comes the challenge of applying those technologies to create robots that can make navigational decisions based on visual inputs. In this project, a human-following robot is designed and implemented using the Microsoft Kinect v2 system for PC. This system feeds the robot both color and depth information from the environment in front of it, allowing it to navigate obstacles and follow a specific user. The Kinect is used to find the user’s location with respect to the robot, based primarily on what the user is wearing and where the …

Deep Learning Nuclei Detection In Digitized Histology Images By Superpixels, Sudhir Sornapudi, R. Joe Stanley, William V. Stoecker, Haidar Almubarak, Rodney Long, Sameer Antani, George Thoma, Rosemary Zuna, Shelliane R. Frazier

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades.

Methods: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network.

Results: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with …

Spoilage Detection In Raspberry Fruit Based On Spectral Imaging Using Convolutional Neural Networks, Karthik Kuchangi Jothi Prakash

Dissertations

Effective spoilage detection of perishable food items like fruits and vegetables is essential for retailers who stock and sell large quantities of these items. This research is aimed at developing a non-destructive, rapid and accurate method which is based on Spectral Imaging (SI) used in tandem with Convolutional Neural Network (CNN) to predict whether the fruit is fresh or rotten. The study also aims to determine the number of days before which the fruit rots. This research employs a primary, quantitative and inductive methods to investigate the Deep Learning based approach to detect fruit spoilage. Raspberry fruit in particular has …

Target Detection, Tracking, And Localization Using Multi-Spectral Image Fusion And Rf Doppler Differentials, Casey D. Demars

Dissertations, Master's Theses and Master's Reports

It is critical for defense and security applications to have a high probability of detection and low false alarm rate while operating over a wide variety of conditions. Sensor fusion, which is the the process of combining data from two or more sensors, has been utilized to improve the performance of a system by exploiting the strengths of each sensor. This dissertation presents algorithms to fuse multi-sensor data that improves system performance by increasing detection rates, lowering false alarms, and improving track performance. Furthermore, this dissertation presents a framework for comparing algorithm error for image registration which is a critical …

Leveraging 3d Models For Sar-Based Navigation In Gps-Denied Environments, Zachary A. Reid

Browse all Theses and Dissertations

This thesis considers the use of synthetic aperture radar (SAR) to provide absolute platform position information in scenarios where GPS signals may be degraded, jammed, or spoofed. Two algorithms are presented, and both leverage known 3D ground structure in an area of interest, e.g. provided by LIDAR data, to provide georeferenced position information to airborne SAR platforms. The first approach is based on the wide-aperture layover properties of elevated reflectors, while the second approach is based on correlating backprojected imagery with digital elevation imagery. Both of these approaches constitute the system we have designated: SARNAV. Building on 3D backprojection, localization …

Cross Calibration And Validation Of Landsat 8 Oli And Sentinel 2a Msi, M. M. Farhad

Electronic Theses and Dissertations

This work describes a proposed radiometric cross calibration between the Landsat 8 Operational Land Imager (OLI) and Sentinel 2A Multispectral Instrument (MSI) sensors. The cross calibration procedure involves i) correction of the MSI data to account for spectral band differences with the OLI; and ii) correction of BRDF effects in the data from both sensors using a new model accounting for the view zenith/azimuth angles in addition to the solar zenith/view angles. Following application of the spectral and BRDF corrections, standard least-squares linear regression is used to determine the cross calibration gain and offset in each band. Uncertainties related to …

Image Stitching And Matching Tool In The Automated Iterative Reverse Engineer (Aire) Integrated Circuit Analysis Suite, David C. Bowman

Browse all Theses and Dissertations

Due to current market forces, leading-edge semiconductor fabrication plants have moved outside of the US. While this is not a problem at first glance, when it comes to security-sensitive applications, over-production, device cloning, or design alteration becomes a possibility. Since these vulnerabilities exist during the fabrication phase, a Reverse Engineering (RE) step must be introduced to help ensure secure device operation. This thesis proposes several unique methods and a collection of tools to ensure trust assurance in integrated circuit design by detecting fabrication flaws and possible hardware Trojans using several image processing techniques; fused into a singular view of the …

Field-Based Scoring Of Soybean Iron Deficiency Chlorosis Using Rgb Imaging And Statistical Learning, Geng Bai, Shawn Jenkins, Wenan Yuan, George L. Graef, Yufeng Ge

Department of Biological Systems Engineering: Papers and Publications

Iron deficiency chlorosis (IDC) is an abiotic stress in soybean that can cause significant biomass and yield reduction. IDC is characterized by stunted growth and yellowing and interveinal chlorosis of early trifoliate leaves. Scoring IDC severity in the field is conventionally done by visual assessment. The goal of this study was to investigate the usefulness of Red Green Blue (RGB) images of soybean plots captured under the field condition for IDC scoring. A total of 64 soybean lines with four replicates were planted in 6 fields over 2 years. Visual scoring (referred to as Field Score, or FS) was conducted …

Datumate, Purdue Ect Team

ECT Fact Sheets

Datumate is digitally transforming civil engineering processes used in construction, surveying and infrastructure inspection markets with fully automated, highly precise, cost effective and safe tools. It utilizes state-of-the-art image processing and advanced drones and camera technologies dramatically reducing the amount of time surveying crews spend in the field, speeding up construction progress checks and shortening infrastructure inspection duration, while maintaining survey grade accuracy. The intuitive, simple and automated solutions increase productivity by saving field and office time in civil engineering and inspection projects of roads, intersections, stockpile volumes, topography, piping, industrial facilities, bridges, property surveys, building facades, railways, cellular infrastructure …

Convolutional Neural Network Based Localized Classification Of Uterine Cervical Cancer Digital Histology Images, Haidar A. Almubarak, R. Joe Stanley, Rodney Long, Sameer Antani, George Thoma, Rosemary Zuna, Shelliane R. Frazier

Electrical and Computer Engineering Faculty Research & Creative Works

In previous research, we introduced an automated localized, fusion-based algorithm to classify squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN). The approach partitioned the epithelium into 10 segments. Image processing and machine vision algorithms were used to extract features from each segment. The features were then used to classify the segment and the result was fused to classify the whole epithelium. This research extends the previous research by dividing each of the 10 segments into 3 parts and uses a convolutional neural network to classify the 3 parts. The result is then fused to …

Bubble Dynamics And Bed Expansion For Single-Component And Binary Gas-Solid Fluidization Systems, Bowen Han

Electronic Thesis and Dissertation Repository

Gas-solid fluidized beds are widely used in industrial dry coal preparation to separate waste from coal (still a primarily important energy source worldwide). It is the density difference between coal and the waste that enables the separation. Experiments were carried out in a two dimensional gas-solid fluidized bed. Filtered air at room temperature was used as the fluidizing gas, while magnetite, sand (two types) and FCC catalyst particles belonging to Geldart groups A and B were used as bed particles. Image processing and Matlab were applied for bubble size and velocity measurements. Bubble properties and bed expansion in fluidized beds …

Image-Based Compression Method Of Three-Dimensional Range Data With Texture, Xia Chen, Tyler Bell, Song Zhang

The Summer Undergraduate Research Fellowship (SURF) Symposium

Recently, high speed and high accuracy three-dimensional (3D) scanning techniques and commercially available 3D scanning devices have made real-time 3D shape measurement and reconstruction possible. The conventional mesh representation of 3D geometry, however, results in large file sizes, causing difficulties for its storage and transmission. Methods for compressing scanned 3D data therefore become desired. This paper proposes a novel compression method which stores 3D range data within the color channels of a regular 2D output image. Our method encodes the 3D range data’s respective normalized phase map, generated by a virtual stereovision system, into two of the output image’s color …

Image Processing And Understanding Based On Graph Similarity Testing: Algorithm Design And Software Development, Jieqi Kang

Doctoral Dissertations

Image processing and understanding is a key task in the human visual system. Among all related topics, content based image retrieval and classification is the most typical and important problem. Successful image retrieval/classification models require an effective fundamental step of image representation and feature extraction. While traditional methods are not capable of capturing all structural information on the image, using graph to represent the image is not only biologically plausible but also has certain advantages. Graphs have been widely used in image related applications. Traditional graph-based image analysis models include pixel-based graph-cut techniques for image segmentation, low-level and high-level image …

Histological Quantification In Temporal Lobe Epilepsy, Charlotte Anne Blinston

Electronic Thesis and Dissertation Repository

Approximately 30 percent of epilepsy patients suffer from refractory temporal lobe epilepsy which is commonly treated with resection of the epileptogenic tissue. However, surgical treatment presents many challenges in locating the epileptogenic focus and thus not all patients become seizure-free following surgery. Advances in techniques can lead to improved localization of the epileptogenic zone and may be validated by correlating MRI with neuropathology of the excised cortical tissue. Focal cortical dysplasias are a neuropathological group of cortical malformations that are often found in cases of refractory epilepsy, however, they are subtle and difficult to quantify. The purpose of this research …

Image Processing With Dipole-Coupled Nanomagnets: Noise Suppression And Edge Enhancement Detection, Md Ahsanul Abeed, Ayan Kumar Biswas, Mamun Al-Rashid, Jayasimha Atulasimha, Supriyo Bandyopadhyay

Electrical and Computer Engineering Publications

Hardware-based image processing offers speed and convenience not found in software-centric approaches. Here, we show theoretically that a 2-D periodic array of dipole-coupled elliptical nanomagnets, delineated on a piezoelectric substrate, can act as a dynamical system for specific image processing functions. Each nanomagnet has two stable magnetization states that encode pixel color (black or white). An image containing black and white pixels is first converted to voltage states and then mapped into the magnetization states of a nanomagnet array with magneto-tunneling junctions (MTJs). The same MTJs are employed to read out the processed pixel colors later. Dipole interaction between the …

Indoor Mapping Drone, Benjamin J. Plevny, Andrew Armstrong, Miguel Lopez, Davidson Okpara

Williams Honors College, Honors Research Projects

This project addresses the need for an autonomous indoor mapping system that will create a 3D map of an unknown physical environment in real time. The aerial system moves and avoids obstacles autonomously, without the need for human remote control or observation. An aerial system produces a map of an unknown indoor environment by transmitting data received from the aerial device’s sensors. The transmission occurs over a wireless channel from the aerial device to a remote server for processing and storage of the data. As the transmission is done in real time, the aerial system does not require hardware for …

Analysis Of 3d Cone-Beam Ct Image Reconstruction Performance On A Fpga, Devin Held

Electronic Thesis and Dissertation Repository

Efficient and accurate tomographic image reconstruction has been an intensive topic of research due to the increasing everyday usage in areas such as radiology, biology, and materials science. Computed tomography (CT) scans are used to analyze internal structures through capture of x-ray images. Cone-beam CT scans project a cone-shaped x-ray to capture 2D image data from a single focal point, rotating around the object. CT scans are prone to multiple artifacts, including motion blur, streaks, and pixel irregularities, therefore must be run through image reconstruction software to reduce visual artifacts. The most common algorithm used is the Feldkamp, Davis, and …

Video Annotation By Crowd Workers With Privacy-Preserving Local Disclosure, Apeksha Dipak Kumavat

Open Access Theses

Advancements in computer vision are still not reliable enough for detecting video content including humans and their actions. Microtask crowdsourcing on task markets such as Amazon Mechnical Turk and Upwork can bring humans into the loop. However, engaging crowd workers to annotate non-public video footage risks revealing the identities of people in the video who may have a right to anonymity.

This thesis demonstrates how we can engage untrusted crowd workers to detect behaviors and objects, while robustly concealing the identities of all faces. We developed a web-based system that presents obfuscated videos to crowd workers, and provides them with …

An Emg-Based Patient Monitoring System Using Zynq Soc Device, Farhad Fallahlalehzari

UNLV Theses, Dissertations, Professional Papers, and Capstones

This thesis describes the design, development, and testing of an EMG-based patient monitoring system using the Zynq device. Zynq is a system on chip device designed by Xilinx which consists of an ARM dual cortex-A9 processor as well as an FPGA integrated into one chip. This work also analyzes the performance of image-processing algorithms on this system and compares that performance to more traditional PC-based systems. Image processing algorithms, such as Sobel edge detection, dilation and erosion, could be used in conjunction with a camera for the patient monitoring purposes. These algorithms often perform sub-optimally on processors because of their …

A Multimodal Investigation In Eye Movements, Raj Jaswal

Dissertations

While functional magnetic resonance imaging (fMRI) has identified which regions of interest (ROIs) are functionally active during a vergence movement (inward or outward eye rotation), task-modulated coactivation between ROIs is less understood. This study tests the following hypotheses: (1) significant task-modulated coactivation would be observed between the frontal eye fields (FEFs), the posterior parietal cortex (PPC), and the cerebellar vermis (CV); (2) significantly more functional activity and task-modulated coactivation would be observed in binocularly normal controls (BNCs) compared with convergence insufficiency (CI) subjects; and (3) after vergence training, the functional activity and task-modulated coactivation would increase in CIs compared with …

Error Resilient Video Coding Using Bitstream Syntax And Iterative Microscopy Image Segmentation, Neeraj Jayant Gadgil

Open Access Dissertations

There has been a dramatic increase in the amount of video traffic over the Internet in past several years. For applications like real-time video streaming and video conferencing, retransmission of lost packets is often not permitted. Popular video coding standards such as H.26x and VPx make use of spatial-temporal correlations for compression, typically making compressed bitstreams vulnerable to errors. We propose several adaptive spatial-temporal error concealment approaches for subsampling-based multiple description video coding. These adaptive methods are based on motion and mode information extracted from the H.26x video bitstreams. We also present an error resilience method using data duplication in …

Visual Clutter Study For Pedestrian Using Large Scale Naturalistic Driving Data, Kai Yang

Open Access Dissertations

Some of the pedestrian crashes are due to driver’s late or difficult perception of pedestrian’s appearance. Recognition of pedestrians during driving is a complex cognitive activity. Visual clutter analysis can be used to study the factors that affect human visual search efficiency and help design advanced driver assistant system for better decision making and user experience. In this thesis, we propose the pedestrian perception evaluation model which can quantitatively analyze the pedestrian perception difficulty using naturalistic driving data. An efficient detection framework was developed to locate pedestrians within large scale naturalistic driving data. Visual clutter analysis was used to study …

Image Quality Estimation: Soft-Ware For Objective Evaluation, He Liu

Open Access Theses

Digital images are widely used in our daily lives and the quality of images is important to the viewing experience. Low quality images may be blurry or contain noise or compression artifacts. Humans can easily estimate image quality, but it is not practical to use human subjects to measure image quality in real applications. Image Quality Estimators (QE) are algorithms that evaluate image qualities automatically. These QEs compute scores of any input images to represent their qualities. This thesis mainly focuses on evaluating the performance of QEs. Two approaches used in this work are objective software analysis and the subjective …

Ground Vehicle Platooning Control And Sensing In An Adversarial Environment, Samuel A. Mitchell

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

In the past few years, automated cars have ceased to be part of science fiction, and have instead become a technology that has been implemented, with partially automated systems currently available to customers.

One benefit of automated vehicle technology is the consistent driving patterns due to automation, instead of the inconsistency of distractible humans. Passengers of automated vehicles will be exposed to much less danger than the passengers of human-driven vehicles.

These statements will only be true as automated vehicle systems are scrutinized by experts to find flaws in the system. Security enthusiasts have already hijacked control of an automated …

Automatic Detection Of Cone Photoreceptors In Split Detector Adaptive Optics Scanning Light Ophthalmoscope Images, David Cunefare, Robert F. Cooper, Brian P. Higgins, David F. Katz, Alfredo Dubra, Joseph Carroll, Sina Farsiu

Biomedical Engineering Faculty Research and Publications

Quantitative analysis of the cone photoreceptor mosaic in the living retina is potentially useful for early diagnosis and prognosis of many ocular diseases. Non-confocal split detector based adaptive optics scanning light ophthalmoscope (AOSLO) imaging reveals the cone photoreceptor inner segment mosaics often not visualized on confocal AOSLO imaging. Despite recent advances in automated cone segmentation algorithms for confocal AOSLO imagery, quantitative analysis of split detector AOSLO images is currently a time-consuming manual process. In this paper, we present the fully automatic adaptive filtering and local detection (AFLD) method for detecting cones in split detector AOSLO images. We validated our algorithm …

Image Processing Of Triple Shock Wave Evolution, Katherine Yarbrough

Mechanical and Aerospace Engineering Theses

Shock diamonds occur in over- or under- expanded supersonic flow. They occur in the unsteady jet of a pulse detonation engine, displaying an array of complex features. Due to the highly transient nature of the flow, it must be captured using high-speed cinematography. A study of image processing of shock reflection in unsteady flow is presented. Using a computer-based environment, a method was developed to process images of shock waves to pinpoint where the shock wave starts. Using mathematical methods, such as Abel transforms, a computer code, written in Matlab, was developed to accurately transform the images to detect density …

Registration And Segmentation Of Multimodality Images For Post Processing Of Skeleton In Preclinical Oncology Studies, Vineeth Radhakrishnan

Masters Theses

Advancements in medical imaging techniques provide biomedical researchers with quality anatomical and functional information inside preclinical subjects in the fields of cancer, osteopathic, cardiovascular, and neurodegenerative research. The throughput of the preclinical imaging studies is a critical factor which determines the pace of small animal medical research. The time involved in manual analysis of large amount of imaging data prior to data interpretation by the researcher, limits the number of studies in a time frame.

In the proposed solution, an automated image segmentation method was used to segment individual vertebrae in mice. Individual vertebrae of MOBY atlas were manually segmented …

Geosynchronous Binary Object Detection, Patrick B. Cunningham

Theses and Dissertations

This paper will compare competing methods for optically detecting binary objects. This is mostly intended for use in Space Situational Awareness (SSA), though has the potential to be used in other applications. The first method referred to as, “Single Object Detection” is a versatile algorithm which is currently used to detect extraterrestrial objects. However, it does not take into account interference by a nearby object. Therefore a second algorithm is investigated, referred to as “Binary Object Detection”, which does. The binary detection algorithm proved to have a comparable or superior Receiver Operating Characteristic (ROC) curve (based upon the area under …

Integrity Determination For Image Rendering Vision Navigation, Sean M. Calhoun

Theses and Dissertations

This research addresses the lack of quantitative integrity approaches for vision navigation, relying on the use of image or image rendering techniques. The ability to provide quantifiable integrity is a critical aspect for utilization of vision systems as a viable means of precision navigation. This research describes the development of two unique approaches for determining uncertainty and integrity for a vision based, precision, relative navigation system, and is based on the concept of using a single camera vision system, such as an electro-optical (EO) or infrared imaging (IR) sensor, to monitor for unacceptably large and potentially unsafe relative navigation errors. …

Effects Of Intraframe Distortion On Measures Of Cone Mosaic Geometry From Adaptive Optics Scanning Light Ophthalmoscopy, Robert F. Cooper, Yusufu N. Sulai, Adam M. Dubis, Toco Y.P. Chui, Richard B. Rosen, Michel Michaelides, Alfredo Dubra, Joseph Carroll

Biomedical Engineering Faculty Research and Publications

Purpose: To characterize the effects of intraframe distortion due to involuntary eye motion on measures of cone mosaic geometry derived from adaptive optics scanning light ophthalmoscope (AOSLO) images.

Methods: We acquired AOSLO image sequences from 20 subjects at 1.0, 2.0, and 5.08 temporal from fixation. An expert grader manually selected 10 minimally distorted reference frames from each 150-frame sequence for subsequent registration. Cone mosaic geometry was measured in all registered images (n ¼ 600) using multiple metrics, and the repeatability of these metrics was used to assess the impact of the distortions from each reference frame. In nine additional subjects, …