Hyperspectral Remote Sensing
Hyperspectral remote sensing utilizes imagery containing hundreds of narrow spectral bands to identify materials on Earth's surface with high precision, primarily aiming for accurate classification and object detection. Current research heavily focuses on improving classification accuracy through advanced deep learning architectures, such as convolutional neural networks (CNNs), transformers, and hybrid models combining their strengths, often incorporating techniques like band selection and pansharpening to enhance data quality. These advancements are significantly impacting various fields, including agriculture (crop type identification), archaeology (detecting subsurface features), and environmental monitoring (oil spill detection), by providing more detailed and reliable information from remotely sensed data.
Papers
A Novel Filter Approach for Band Selection and Classification of Hyperspectral Remotely Sensed Images Using Normalized Mutual Information and Support Vector Machines
Hasna Nhaila, Asma Elmaizi, Elkebir Sarhrouni, Ahmed Hammouch
Supervised classification methods applied to airborne hyperspectral images: Comparative study using mutual information
Hasna Nhaila, Asma Elmaizi, Elkebir Sarhrouni, Ahmed Hammouch