Digital Commons Network^™

Accuracy Assessment Of Measuring Linear And Areal Features In Aerial Imagery, I-Kuai Hung, David L. Kulhavy, Daniel R. Unger, Reid A. Viegut, Yanli Zhang, Nicholas C. Schiwitz

International Journal of Geospatial and Environmental Research

As part of natural resource education in the Arthur Temple College of Forestry and Agriculture at Stephen F. Austin State University (SFASU), students were instructed to take areal and linear measurements of grounds remotely using available platforms including aerial orthomosaic derived from UAS (unmanned aerial system) acquired imagery, Google Earth Pro, and Pictometry. The onscreen measurement was conducted at five different map scales, 1/1000, 1/2000, 1/3000, 1/4000, and 1/5000. Accuracy of the measurements was assessed by comparing the onscreen measurements to ground truth data verified with a measuring tape. Results show that measurements based on the UAS were more accurate …

Deep Learning Of High-Resolution Aerial Imagery For Coastal Marsh Change Detection: A Comparative Study, Grayson R. Morgan, Cuizhen Wang, Zhenlong Li, Steven R. Schill, Daniel R. Morgan

Faculty Publications

Deep learning techniques are increasingly being recognized as effective image classifiers. Aside from their successful performance in past studies, the accuracies have varied in complex environments, in comparison with the popularly of applied machine learning classifiers. This study seeks to explore the feasibility of using a U-Net deep learning architecture to classify bi-temporal, high-resolution, county-scale aerial images to determine the spatial extent and changes of land cover classes that directly or indirectly impact tidal marsh. The image set used in the analysis is a collection of a 1-m resolution collection of National Agriculture Imagery Program (NAIP) tiles from 2009 and …

Advanced Photogrammetric Modeling Of Dranoc Kullas Using Small Unmanned Aircraft Systems, George Gebert, Liam Griffin, Justin Lawlor, Lauren Davis, Kylee Vander Velde, Sami Ali

Student Works

Small unmanned aircraft systems (sUAS), also known as drones, offer new capabilities for cultural heritage preservation activities. Student researchers from Embry-Riddle Aeronautical University have applied photogrammetric techniques based upon sUAS captured imagery to assist with historical site documentation and cultural heritage preservation in the Republic of Kosovo. Imagery from three locations -- Isniq, Dranoc and Junik -- highlight this work. Student researchers created georectified orthomosaics and 3D virtual objects. At each of these three locations the object of interest was a type of building known as a kulla. These kullas are fortified homes built for protecting large families and are …

The Use Of Aerial Rgb Imagery And Lidar In Comparing Ecological Habitats And Geomorphic Features On A Natural Versus Man-Made Barrier Island, Carlton P. Anderson, Gregory A. Carter, William R. Funderburk

Faculty Publications

The Mississippi (MS) barrier island chain along the northern Gulf of Mexico coastline is subject to rapid changes in habitat, geomorphology and elevation by natural and anthropogenic disturbances. The purpose of this study was to compare habitat type coverage with respective elevation, geomorphic features and short-term change between the naturally-formed East Ship Island and the man-made Sand Island. Ground surveys, multi-year remotely-sensed data, habitat classifications and digital elevation models were used to quantify short-term habitat and geomorphic change, as well as to examine the relationships between habitat types and micro-elevation. Habitat types and species composition were the same on both …

Object-Based Classification Of Earthquake Damage From High-Resolution Optical Imagery Using Machine Learning, James Bialas

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

Object-based approaches to the segmentation and supervised classification of remotely-sensed images yield more promising results compared to traditional pixel-based approaches. However, the development of an object-based approach presents challenges in terms of algorithm selection and parameter tuning. Subjective methods and trial and error are often used, but time consuming and yield less than optimal results. Objective methods are warranted, especially for rapid deployment in time sensitive applications such as earthquake induced damage assessment.

Our research takes a systematic approach to evaluating object-based image segmentation and machine learning algorithms for the classification of earthquake damage in remotely-sensed imagery using Trimble’s eCognition …