Engineering Commons^™

Self-Describing Fiducials For Gps-Denied Navigation Of Unmanned Aerial Vehicles, Amanda J. Strate

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Accurate estimation of an Unmanned Aerial Vehicle’s (UAV’s) location is critical for the operation of the UAV when it is controlled completely by its onboard processor. This can be particularly challenging in environments in which GPS is not available (GPS-denied). Many of the options previously explored for estimation of a UAV’s location without the use of GPS require more sophisticated processors than can feasibly be mounted on a UAV because of weight, size, and power restrictions. Many options are also aimed at indoor operation without the range capabilities to scale to outdoor operations. This research explores an alternative method of …

Autonomous Drone-Based Sensor Package Deployment To The Underside Of Structures, Sabrina Rose Carroll

Theses and Dissertations

The objective of this project is to design, develop and experimentally test an Unmanned Aircraft System (UAS, commonly known as a drone) for the deployment of sensor packages to the underside of structures. This work begins with an in-depth review of existing automation techniques for various drone applications focusing on applications requiring interaction with the environment. Further reviewed is the impact of structures above the UAS during flight on the behavior of the aircraft.

Considering these topics, the development of a custom drone is presented to address the difficulties of delivering a package to the underside of a structure. Starting …

Using Drone-Based Fully Convolutional Network For The Determination Of Construction Site Elevations, Sisi Han

Master's Theses (2009 -)

This thesis presents the research results of using the Fully Convolutional Network (FCN) model to densely match pixels and accurately determine elevations utilizing low-high ortho-images on a construction site. The research project has three major tasks. First, this researcher developed the FCN model to build up the relations between the reference pixels’ patches from the low-ortho-image and the target pixels’ patches from the high-ortho-image, which are approximate 2:1 scale relations. The developed FCN model has two convolutional blocks and one max-pooling layer in the middle. 286,292 samples of well-matched reference patches and target patches were collected for training the FCN …

Determination Of Elevations For Excavation Operations Using Drone Technologies, Yuhan Jiang

Dissertations (1934 -)

Using deep learning technology to rapidly estimate depth information from a single image has been studied in many situations, but it is new in construction site elevation determinations, and challenges are not limited to the lack of datasets. This dissertation presents the research results of utilizing drone ortho-imaging and deep learning to estimate construction site elevations for excavation operations. It provides two flexible options of fast elevation determination including a low-high-ortho-image-pair-based method and a single-frame-ortho-image-based method. The success of this research project advanced the ortho-imaging utilization in construction surveying, strengthened CNNs (convolutional neural networks) to work with large scale images, …

Automated Drone Calibration System, Jackie Kelly Jong-Mee Paik, Zach Nathan Richter, Tyler Wilson Van Den Berg, Ryan Alexander Zhan, Matthew Ward Carlson

Mechanical Engineering

The final design review of the Inspired Flight Calibration Team senior project will detail the process used to complete a verification prototype of a drone calibration device and discuss lessons learned and suggestions for improving this device. Going from brainstorming and conceptual prototyping all the way through verification prototyping and testing, we were able to design a gyroscopic device that met Inspired Flight’s needs for the flight sensor calibration of their drones. The mechanical design involved comprehensive CAD models and hands-on manufacturing. The mechatronics side of the project worked heavily with electrical wiring and writing custom software to communicate and …

Diseño De Un Protocolo De Recolección, Procesamiento Y Análisis De Imágenes Vis Y Satelitales Para Aforar Sedimientos En Suspensión Aplicado Al Río Negro, Nicolas Mateo Gomez Benavides, Natalia Vanessa Gil Medina

Ingeniería Civil

Actualmente la cuantificación de sedimentos en suspensión demanda la extracción de muestras en campo y su procesamiento en laboratorio, lo cual implica restricciones logísticas y económicas, que con este trabajo pretendieron ser superadas, utilizando técnicas de visión artificial para determinar la carga de sedimentos a partir de fotografías. El protocolo propuesto para la captura y escalado de imágenes tomadas con drone durante vuelos entre 1 y 150 metros de altura, permite cuantificar su carga sólida y caracterizar morfológicamente el rio. Mediante un modelo potencial que relaciona el área que se captura en la imagen respecto a la altura de vuelo …