University of West Florida Expert Available to Discuss Research on using VQA Method to Assess Damage Following Natural Disasters

Feasibility of Visual Question Answering (VQA) for Post-Disaster Damage Detection Using Aerial Footage

Natural disasters are a major source of significant damage and costly repairs around the world, and the occurrence of them has increased significantly in the past decade. After a natural disaster, there is usually a significant amount of damage, and with that, there are also a lot of costs involved with repairing. Oftentimes, post-disaster damage detection is usually performed manually by human operators. Taking into consideration all the areas one has to closely look into, as well as the difficult terrain and places with hard access, it becomes easy to understand how incredibly difficult it is for a surveyor to identify every single possible damage. Because of that, it has become essential to find new creative solutions for damage detection and classification in the case of natural disasters, especially hurricanes. This study focuses on the feasibility of using a Visual Question Answering (VQA) method for post-disaster damage detection, using aerial footage taken from an Unmanned Aerial Vehicle (UAV). Our case study on our custom dataset collected after Hurricane Sally shows successful results using VQA for post-disaster damage detection applications.

 

Biography:
Dr. Hakki Erhan Sevil received his Doctor of Philosophy degree in Mechanical Engineering from the University of Texas at Arlington (UTA), and his Bachelor of Science and Master of Science degrees in Mechanical Engineering from Izmir Institute of Technology. He had over 4 years of research experience at Izmir Institute of Technology, and he was a Visiting Researcher in Service Automation and Systems Analysis (Service d’Automatique et d’Analyse des Systemes – SAAS) Laboratory at Universite Libre de Bruxelles (ULB) in 2009. Between 2009 and 2013, he was conducting research in Computer-Aided Control System Design Laboratory (CACSDL) and Autonomous Vehicles Laboratory (AVL) at UTA. Before joining University of West Florida (UWF) in 2018, he has worked as a Research Scientist in the Automation & Intelligent Systems Division at the University of Texas at Arlington Research Institute (UTARI) between 2014 and 2018. His research interests include robotics, guidance and navigation, fault detection and isolation, bio-inspired and evolutionary computational methods, and distributed behavior models for multi-agent systems. Dr. Sevil has authored/co-authored more than 45 journal and conference papers, and book chapters, and he has been involved in 10 funded projects as a researcher. Besides working on the funded projects as key personnel, Dr. Sevil also has been the PI and Co-PI of various internal and external projects, sponsored by agencies, including NSF, NASA, ARL, and ONR. His recent work includes resilient and intelligent robotic systems, cooperative multiagent systems, computer vision applications for mobile robots, and advanced guidance and navigation techniques Degrees & Institutions: Ph.D. Mechanical Engineering, University of Texas at Arlington M.S. Mechanical Engineering, Izmir Institute of Technology B.S. Mechanical Engineering, Izmir Institute of Technology