Engineering Commons^™

Sc-Fuse: A Feature Fusion Approach For Unpaved Road Detection From Remotely Sensed Images, Aniruddh Saxena

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Road network extraction from remote sensing imagery is crucial for numerous applications, ranging from autonomous navigation to urban and rural planning. A particularly challenging aspect is the detection of unpaved roads, often underrepresented in research and data. These roads display variability in texture, width, shape, and surroundings, making their detection quite complex. This thesis addresses these challenges by creating a specialized dataset and introducing the SC-Fuse model.

Our custom dataset comprises high resolution remote sensing imagery which primarily targets unpaved roads of the American Midwest. To capture the diverse seasonal variation and their impact, the dataset includes images from different …

Power Outage And Environmental Justice In Winter Storm Uri: An Analytical Workflow Based On Nighttime Light Remote Sensing, Jinwen Xu, Yi Qiang, Heng Cai, Lei Zou

GIS Center

The intensity of extreme weather events has been increasing, posing a unique threat to society and highlighting the importance of our electrical power system, a key component in our infrastructure. In severe weather events, quickly identifying power outage impact zones and affected communities is crucial for informed disaster response. However, a lack of household-level power outage data impedes timely and precise assessments. To address these challenges, we introduced an analytical workflow using NASA’s Black Marble daily nighttime light (NTL) images to detect power outages from the 2021 Winter Storm Uri. This workflow includes adjustments to mitigate viewing angle and snow …

Chatgpt As Metamorphosis Designer For The Future Of Artificial Intelligence (Ai): A Conceptual Investigation, Amarjit Kumar Singh (Library Assistant), Dr. Pankaj Mathur (Deputy Librarian)

Library Philosophy and Practice (e-journal)

Abstract

Purpose: The purpose of this research paper is to explore ChatGPT’s potential as an innovative designer tool for the future development of artificial intelligence. Specifically, this conceptual investigation aims to analyze ChatGPT’s capabilities as a tool for designing and developing near about human intelligent systems for futuristic used and developed in the field of Artificial Intelligence (AI). Also with the helps of this paper, researchers are analyzed the strengths and weaknesses of ChatGPT as a tool, and identify possible areas for improvement in its development and implementation. This investigation focused on the various features and functions of ChatGPT that …

Impact Of Atmospheric Correction On Classification And Quantification Of Seagrass Density From Worldview-2 Imagery, Victoria J. Hill, Richard C. Zimmerman, Paul Bissett, David Kohler, Blake Schaeffer, Megan Coffer, Jiang Li, Kazi Aminul Islam

OES Faculty Publications

Mapping the seagrass distribution and density in the underwater landscape can improve global Blue Carbon estimates. However, atmospheric absorption and scattering introduce errors in space-based sensors’ retrieval of sea surface reflectance, affecting seagrass presence, density, and above-ground carbon (AGC_seagrass) estimates. This study assessed atmospheric correction’s impact on mapping seagrass using WorldView-2 satellite imagery from Saint Joseph Bay, Saint George Sound, and Keaton Beach in Florida, USA. Coincident in situ measurements of water-leaving radiance (L_w), optical properties, and seagrass leaf area index (LAI) were collected. Seagrass classification and the retrieval of LAI were compared after empirical line …

Composite Style Pixel And Point Convolution-Based Deep Fusion Neural Network Architecture For The Semantic Segmentation Of Hyperspectral And Lidar Data, Kevin T. Decker, Brett J. Borghetti

Faculty Publications

Multimodal hyperspectral and lidar data sets provide complementary spectral and structural data. Joint processing and exploitation to produce semantically labeled pixel maps through semantic segmentation has proven useful for a variety of decision tasks. In this work, we identify two areas of improvement over previous approaches and present a proof of concept network implementing these improvements. First, rather than using a late fusion style architecture as in prior work, our approach implements a composite style fusion architecture to allow for the simultaneous generation of multimodal features and the learning of fused features during encoding. Second, our approach processes the higher …

A Comparison Of Sporadic-E Occurrence Rates Using Gps Radio Occultation And Ionosonde Measurements, Rodney Carmona, Omar A. Nava, Eugene V. Dao, Daniel J. Emmons

Faculty Publications

Sporadic-E (E_s) occurrence rates from Global Position Satellite radio occultation (GPS-RO) measurements have shown to vary by a factor of five between studies, motivating the need for a comparison with ground-based measurements. In an attempt to find accurate GPS-RO techniques for detecting E_s formation, occurrence rates derived using five previously developed GPS-RO techniques are compared to ionosonde measurements over an eight-year period from 2010–2017. GPS-RO measurements within 170 km of a ionosonde site are used to calculate E_s occurrence rates and compared to the ground-truth ionosonde measurements. The techniques are compared individually for each ionosonde site …

Machine Learning Land Cover And Land Use Classification Of 4-Band Satellite Imagery, Lorelei Turner [*], Torrey J. Wagner, Paul Auclair, Brent T. Langhals

Faculty Publications

Land-cover and land-use classification generates categories of terrestrial features, such as water or trees, which can be used to track how land is used. This work applies classical, ensemble and neural network machine learning algorithms to a multispectral remote sensing dataset containing 405,000 28x28 pixel image patches in 4 electromagnetic frequency bands. For each algorithm, model metrics and prediction execution time were evaluated, resulting in two families of models; fast and precise. The prediction time for an 81,000-patch group of predictions wasmodels, and >5s for the precise models, and there was not a significant change in prediction time when a …

Arithfusion: An Arithmetic Deep Model For Temporal Remote Sensing Image Fusion, Md Reshad Ul Hoque, Jian Wu, Chiman Kwan, Krzysztof Koperski, Jiang Li

Electrical & Computer Engineering Faculty Publications

Different satellite images may consist of variable numbers of channels which have different resolutions, and each satellite has a unique revisit period. For example, the Landsat-8 satellite images have 30 m resolution in their multispectral channels, the Sentinel-2 satellite images have 10 m resolution in the pan-sharp channel, and the National Agriculture Imagery Program (NAIP) aerial images have 1 m resolution. In this study, we propose a simple yet effective arithmetic deep model for multimodal temporal remote sensing image fusion. The proposed model takes both low- and high-resolution remote sensing images at t₁ together with low-resolution images at a …

Assessing The Vertical Displacement Of The Grand Ethiopian Renaissance Dam During Its Filling Using Dinsar Technology And Its Potential Acute Consequences On The Downstream Countries, Hesham El-Askary, Amr Fawzy, Rejoice Thomas, Wenzhao Li, Nicholas Lahaye, Erik Linstead, Thomas Piechota, Daniele Struppa, Mohamed Abdelaty Sayed

Mathematics, Physics, and Computer Science Faculty Articles and Research

The Grand Ethiopian Renaissance Dam (GERD), formerly known as the Millennium Dam, is currently under construction and has been filling at a fast rate without sufficient known analysis on possible impacts on the body of the structure. The filling of GERD not only has an impact on the Blue Nile Basin hydrology, water storage and flow but also poses massive risks in case of collapse. Rosaries Dam located in Sudan at only 116 km downstream of GERD, along with the 20 million Sudanese benefiting from that dam, would be seriously threatened in case of the collapse of GERD. In this …

Unmanned Aircraft Systems For Archaeology Using Photogrammetry And Lidar In Southwestern United States, Imai Bates-Domingo, Alexandra Gates, Patrick Hunter, Blake Neal, Kyle Snowden, Destin Webster

Study America

Researchers can use small unmanned aircraft systems (sUAS), also known as drones, to make observations of historical sites, help interpret locations, and make new discoveries that may not be visible to the naked eye. A student team from Embry-Riddle Aeronautical University gathered data for historical site documentation in New Mexico using the DJI Phantom 4 Pro V2, DJI Mavic Pro 2, DJI M210 and DJI M600, and senseFly eBee. Utilizing these drones, student analysts were able to take the data gathered and create georectified orthomosaic images and 3D virtual objects. At Tularosa Canyon, at a site known as the Creekside …

Creating A Field-Wide Forage Canopy Model Using Uavs And Photogrammetry Processing, Cameron Minch, Joseph S. Dvorak, Joshua J. Jackson, Stuart Tucker Sheffield

Biosystems and Agricultural Engineering Faculty Publications

Alfalfa canopy structure reveals useful information for managing this forage crop, but manual measurements are impractical at field-scale. Photogrammetry processing with images from Unmanned Aerial Vehicles (UAVs) can create a field-wide three-dimensional model of the crop canopy. The goal of this study was to determine the appropriate flight parameters for the UAV that would enable reliable generation of canopy models at all stages of alfalfa growth. Flights were conducted over two separate fields on four different dates using three different flight parameters. This provided a total of 24 flights. The flight parameters considered were the following: 30 m altitude with …

A Quantitative Validation Of Multi-Modal Image Fusion And Segmentation For Object Detection And Tracking, Nicholas Lahaye, Michael J. Garay, Brian D. Bue, Hesham El-Askary, Erik Linstead

Mathematics, Physics, and Computer Science Faculty Articles and Research

In previous works, we have shown the efficacy of using Deep Belief Networks, paired with clustering, to identify distinct classes of objects within remotely sensed data via cluster analysis and qualitative analysis of the output data in comparison with reference data. In this paper, we quantitatively validate the methodology against datasets currently being generated and used within the remote sensing community, as well as show the capabilities and benefits of the data fusion methodologies used. The experiments run take the output of our unsupervised fusion and segmentation methodology and map them to various labeled datasets at different levels of global …

Detecting Recent Crop Phenology Dynamics In Corn And Soybean Cropping Systems Of Kentucky, Yanjun Yang, Bo Tao, Liang Liang, Yawen Huang, Christopher J. Matocha, Chad D. Lee, Michael Sama, Bassil El Masri, Wei Ren

Geography Faculty Publications

Accurate phenological information is essential for monitoring crop development, predicting crop yield, and enhancing resilience to cope with climate change. This study employed a curve-change-based dynamic threshold approach on NDVI (Normalized Differential Vegetation Index) time series to detect the planting and harvesting dates for corn and soybean in Kentucky, a typical climatic transition zone, from 2000 to 2018. We compared satellite-based estimates with ground observations and performed trend analyses of crop phenological stages over the study period to analyze their relationships with climate change and crop yields. Our results showed that corn and soybean planting dates were delayed by 0.01 …

Statistical Analysis And Comparison Of Optical Classification Of Atmospheric Aerosol Lidar Data, Mohammed Alqawba, Norou Diawara, Kwasi G. Afrifa, Mohamed I. Elbakary, Mecit Cetin, Khan Iftekharuddin

Mathematics & Statistics Faculty Publications

In this article, we present a new study for the analysis and classification of atmospheric aerosols in remote sensing LIDAR data. Information on particle size and associated properties are extracted from these remote sensing atmospheric data which are collected by a ground-based LIDAR system. This study first considers optical LIDAR parameter-based classification methods for clustering and classification of different types of harmful aerosol particles in the atmosphere. Since accurate methods for aerosol prediction behaviors are based upon observed data, computational approaches must overcome design limitations, and consider appropriate calibration and estimation accuracy. Consequently, two statistical methods based on generalized linear …

Viability And Application Of Mounting Personal Pid Voc Sensors To Small Unmanned Aircraft Systems, Cheryl Lynn Marcham, Scott Burgess, Joseph Cerreta, Patti J. Clark, James P. Solti, Brandon Breault, Joshua G. Marcham

Publications

Using a UAS-mounted sensor to allow for a rapid response to areas that may be difficult to reach or potentially dangerous to human health can increase the situational awareness of first responders of an aircraft crash site through the remote detection, identification, and quantification of airborne hazardous materials. The primary purpose of this research was to evaluate the remote sensing viability and application of integrating existing commercial-off-the-shelf (COTS) sensors with small unmanned aircraft system (UAS) technology to detect potentially hazardous airborne contaminants in emergency leak or spill response situations. By mounting the personal photoionization detector (PID) with volatile organic compound …

A 3d Point Cloud Deep Learning Approach Using Lidar To Identify Ancient Maya Archaeological Sites, Heather Richards-Rissetto, David Newton, Aziza Al Zadjali

Department of Anthropology: Faculty Publications

Airborne light detection and ranging (LIDAR) systems allow archaeologists to capture 3D data of anthropogenic landscapes with a level of precision that permits the identification of archaeological sites in difficult to reach and inaccessible regions. These benefits have come with a deluge of LIDAR data that requires significant and costly manual labor to interpret and analyze. In order to address this challenge, researchers have explored the use of state-of-the-art automated object recognition algorithms from the field of deep learning with success. This previous research, however, has been limited to the exploration of deep learning processes that work with only 2D …

Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing [*], Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola

Faculty Publications

Atmospheric compensation of long-wave infrared (LWIR) hyperspectral imagery is investigated in this article using set representations learned by a neural network. This approach relies on synthetic at-sensor radiance data derived from collected radiosondes and a diverse database of measured emissivity spectra sampled at a range of surface temperatures. The network loss function relies on LWIR radiative transfer equations to update model parameters. Atmospheric predictions are made on a set of diverse pixels extracted from the scene, without knowledge of blackbody pixels or pixel temperatures. The network architecture utilizes permutation-invariant layers to predict a set representation, similar to the work performed …

Assessing Land Deformation And Sea Encroachment In The Nile Delta, Egypt, Esayas Gebremichael

Research and Creative Activities Poster Day

Persistent scatterer interferometric analyses were conducted on a stack of 84 Envisat ASAR scenes spanning 7 years (2004 to 2010) over the entire Nile Delta of Egypt and surroundings to monitor the ongoing spatial and temporal land deformation, identify the factors controlling the deformation, and model the interplay between sea level rise and land subsidence to identify areas and populations threatened by sea encroachment by the end of the 21st century. Findings include: (1) general patterns of subsidence in the northern delta, near-steady (none) subsidence in the southern delta, separated by a previously mapped flexure zone undergoing uplift; (2) high …

Unmanned Aerial Systems: Research, Development, Education & Training At Embry-Riddle Aeronautical University, Michael P. Hickey

Publications

With technological breakthroughs in miniaturized aircraft-related components, including but not limited to communications, computer systems and sensors, state-of-the-art unmanned aerial systems (UAS) have become a reality. This fast-growing industry is anticipating and responding to a myriad of societal applications that will provide new and more cost-effective solutions that previous technologies could not, or will replace activities that involved humans in flight with associated risks.

Embry-Riddle Aeronautical University has a long history of aviation-related research and education, and is heavily engaged in UAS activities. This document provides a summary of these activities, and is divided into two parts. The first part …

Using Virtual Reality And Photogrammetry To Enrich 3d Object Identity, Cole Juckette, Heather Richards-Rissetto, Hector Eluid Guerra Aldana, Norman Martinez

Department of Anthropology: Faculty Publications

The creation of digital 3D models for cultural heritage is commonplace. With the advent of efficient and cost effective technologies archaeologists are making a plethora of digital assets. This paper evaluates the identity of 3D digital assets and explores how to enhance or expand that identity by integrating photogrammetric models into VR. We propose that when a digital object acquires spatial context from its virtual surroundings, it gains an identity in relation to that virtual space, the same way that embedding the object with metadata gives it a specific identity through its relationship to other information. We explore this concept …

Fpga-Based On-Board Geometric Calibration For Linear Ccd Array Sensors, Guoqing Zhou, Linjun Jiang, Jingjin Huang, Rongting Zhang, Dequan Liu, Xiang Zhou, Oktay Baysal

Mechanical & Aerospace Engineering Faculty Publications

With increasing demands in real-time or near real-time remotely sensed imagery applications in such as military deployments, quick response to terrorist attacks and disaster rescue, the on-board geometric calibration problem has attracted the attention of many scientists in recent years. This paper presents an on-board geometric calibration method for linear CCD sensor arrays using FPGA chips. The proposed method mainly consists of four modules—Input Data, Coefficient Calculation, Adjustment Computation and Comparison—in which the parallel computations for building the observation equations and least squares adjustment, are implemented using FPGA chips, for which a decomposed matrix inversion method is presented. A Xilinx …

Assessment Of Spatiotemporal Fusion Algorithms For Planet And Worldview Images, Chiman Kwan, Xiaolin Zhu, Feng Gao, Bryan Chou, Daniel Perez, Jinag Li, Yuzhong Shen, Krzysztof Koperski, Giovanni Marchisio

Electrical & Computer Engineering Faculty Publications

Although Worldview-2 (WV) images (non-pansharpened) have 2-m resolution, the re-visit times for the same areas may be seven days or more. In contrast, Planet images are collected using small satellites that can cover the whole Earth almost daily. However, the resolution of Planet images is 3.125 m. It would be ideal to fuse these two satellites images to generate high spatial resolution (2 m) and high temporal resolution (1 or 2 days) images for applications such as damage assessment, border monitoring, etc. that require quick decisions. In this paper, we evaluate three approaches to fusing Worldview (WV) and Planet images. …

How Useful Is Gsv As An Environmental Observation Tool? An Analysis Of The Evidence So Far., Katherine Nesse, Leah Airt

SPU Works

Researchers in many disciplines have turned to Google Street View to replace pedestrian- or carbased in-person observation of streetscapes. It is most prevalent within the research literature on the relationship between neighborhood environments and public health but has been used as diverse as disaster recovery, ecology and wildlife habitat, and urban design. Evaluations of the tool have found that the results of GSV-based observation are similar to the results from in-person observation although the similarity depends on the type of characteristic being observed. Larger, permanent and discrete features showed more consistency between the two methods and smaller, transient and judgmental …

Airborne Lidar Acquisition, Post-Processing And Accuracy-Checking For A 3d Webgis Of Copan, Honduras, Jennifer Von Schwerin, Heather Richards-Rissetto, Fabio Remondino, Maria Grazia Spera, Michael Auer, Nicolas Billen, Lukas Loos, Laura Stelson, Markus Reindel

Department of Anthropology: Faculty Publications

Archaeological projects increasingly collect airborne LiDAR data to use as a remote sensing tool for survey and analysis. Publication possibilities for LiDAR datasets, however, are limited due to the large size and often proprietary nature of the data. Fortunately, web-based, geographic information systems (WebGIS) that can securely manage temporal and spatial data hold great promise as virtual research environments for working with and publishing LiDAR data. To test this and to obtain new data for archaeological research, in 2013, the MayaArch3D Project (www.mayaarch3d.org) collected LiDAR data for the archaeological site of Copan, Honduras. Results include: 1) more accurate archaeological maps, …

Remote Sensing Of Hidden Objects, Mark G. Hoelscher, Michael A. Marciniak

AFIT Patents

An apparatus and method are provided for creating an indirect image of an object. The apparatus includes a light source and an imaging system. Light emitted from the light source is reflected by a first non-specular surface toward the object. Light reflected by the object is further reflected by a second non-specular surface toward the imaging system. The imaging system is configured to create the indirect image from the reflected light.

Sparse Coding Based Dense Feature Representation Model For Hyperspectral Image Classification, Ender Oguslu, Guoqing Zhou, Zezhong Zheng, Khan Iftekharuddin, Jiang Li

Electrical & Computer Engineering Faculty Publications

We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the l₁/l_q regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear …

Mapping Licit And Illicit Mining Activity In The Madre De Dios Region Of Peru, Arthur Elmes, Josué Gabriel Yarlequé Ipanaqué, John Rogan, Nicholas Cuba, Anthony J. Bebbington

Geography

Since the early 2000s, the Madre de Dios Region of southern Peru has experienced rapid expansion of both licit and illicit mining activities, in the form of artisanal and small-scale mining (ASM). ASM typically takes place in remote, inaccessible locations and is therefore difficult to monitor in situ. This paper explores the utility of Landsat-5 imagery via decision tree classification to determine ASM locations in Madre de Dios. Spectral mixture analysis was used to unmix Landsat imagery, using WorldView and QuickBird l imagery to aid spectral endmember selection and validate AMS maps. The ASM maps had an overall area-weighted accuracy …

Hyperspectral Image Classification Using A Spectral-Spatial Sparse Coding Model, Ender Oguslu, Guoqing Zhou, Jiang Li, Lorenzo Bruzzone (Ed.)

Electrical & Computer Engineering Faculty Publications

We present a sparse coding based spectral-spatial classification model for hyperspectral image (HSI) datasets. The proposed method consists of an efficient sparse coding method in which the l₁/l_q regularized multi-class logistic regression technique was utilized to achieve a compact representation of hyperspectral image pixels for land cover classification. We applied the proposed algorithm to a HSI dataset collected at the Kennedy Space Center and compared our algorithm to a recently proposed method, Gaussian process maximum likelihood (GP-ML) classifier. Experimental results show that the proposed method can achieve significantly better performances than the GP-ML classifier when training data …

Modeling Acoustic Scattering From The Seabed Using Transport Theory, Jorge Quijano, Lisa M. Zurk

Electrical and Computer Engineering Faculty Publications and Presentations

Radiative Transfer (RT) theory has established itself as an important tool for electromagnetic remote sensing in parallel plane geometries with random distributions of scatterers, and most recently it has also been proposed as a model for the propagation of elastic waves in layered ocean sediments. In this work the capabilities of this model are illustrated, as the RT method is used to predict backscattering strength from laboratory models of random media. The RT model is characterized by its flexibility on accommodating scatterers in a broad variety of sizes, shapes, and acoustic contrast relative to the background media. Additionally, this formulation …

Vegetation Identification Based On Satellite Imagery, Vamsi K.R. Mantena, Ramu Pedada, Srinivas Jakkula, Yuzhong Shen, Jiang Li, Hamid R. Arabnia (Ed.)

Electrical & Computer Engineering Faculty Publications

Automatic vegetation identification plays an important role in many applications including remote sensing and high performance flight simulations. This paper presents a method to automatically identify vegetation based upon satellite imagery. First, we utilize the ISODATA algorithm to cluster pixels in the images where the number of clusters is determined by the algorithm. We then apply morphological operations to the clustered images to smooth the boundaries between clusters and to fill holes inside clusters. After that, we compute six features for each cluster. These six features then go through a feature selection algorithm and three of them are determined to …