Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Deep learning for visible-infrared image fusion and semantic segmentation of wildfire imagery(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-11-23) Ciprián Sánchez, Jorge Francisco; Ochoa Ruiz, Gilberto; puemcuervo, emipsanchez; Martínez Carranza, José; Falcón Morales, Luis Eduardo; School of Engineering and Sciences; Campus Estado de México; Rossi, LucileWildfires stand as one of the most relevant natural disasters worldwide, particularly more so due to climate change and its impact on various societal and environmental levels. In this regard, a significant amount of research has been done to address this issue, deploying a wide variety of technologies and following a multi-disciplinary approach. Notably, computer vision has played a fundamental role in this regard. It can be used to extract and combine information from several imaging modalities regarding fire detection, characterization, and wildfire spread forecasting. In recent years there has been work on Deep Learning (DL)-based fire segmentation, showing promising results. However, it is currently unclear whether the architecture of a model, its loss function, or the image type employed (visible, infrared, or fused) has the most impact on the fire segmentation results. In the field of visible-infrared image fusion, there is a growing interest in DL-based image fusion techniques due to their reduced complexity; however, most DL-based image fusion methods have not been evaluated in the domain of fire imagery. In the present thesis, I select three state-of-the-art (SOTA) DL-based image fusion techniques, assess their performance for the specific task of fire image fusion, and compare the performance of these methods on selected metrics. I also present an extension to one of the said methods, that I called FIRe-GAN, that improves the generation of artificial infrared and fused images. I then evaluate different combinations of SOTA DL architectures, loss functions, and types of images to identify the parameters most relevant to improve the segmentation results. I benchmark them to identify the top-performing ones and compare the best one to traditional fire segmentation techniques. Finally, I evaluate if the addition of attention modules on the best-performing architecture can further improve the segmentation results. To the best of my knowledge, this is the first work that evaluates the impact of the architecture, loss function, and image type in the performance of DL-based wildfire segmentation models and assesses the applicability of DL-based image fusion methods on fire images, proposing a DL model for visible-infrared image fusion optimized for fire imagery.