YOLO Convolutional neural network for building damage detection in hydrometeorological disasters using satellite imagery

Natural disasters pose a continuous threat to populations worldwide, with hydrometeorological disasters standing out due to their unpredictability, rapid onset, and significant destructive capacity. Consequently, countries invest substantial resources in implementing pre- and post-disaster measures, including prevention, and reconstruction. Developing countries, however, face stronger budgetary constraints and continuously depend on international support, having a limited and fluctuating ability to implement optimal disaster response strategies, affecting their response capabilities and timeliness, both of which are crucial for saving lives. This paper addressed these challenges by training and implementing YOLO (You Only Look Once) Convolutional Neural Network version 8 models, using high-resolution satellite images from the Maxar GeoEye-1 satellite. Additionally, this paper tested the viability of publicly publishing the model to be accessed via a REST API, providing a low-cost tool for quickly identifying damaged buildings following natural disasters, and enhancing the efficiency and effectiveness of disaster response efforts.

• Autores: Moreno González, César Luis
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2024
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/74680
• Acceso en línea: https://hdl.handle.net/1992/74680
• Palabra clave: Machine Learning; Deep Learning; Computer Vision; Detection Models; Natural Disasters; Hydrometeorological Disasters; Ingeniería
• Rights: embargoedAccess
• License: https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf