Infrared Image
Infrared (IR) images capture thermal radiation, offering unique advantages in low-light or adverse weather conditions. Current research focuses on improving IR image quality through noise reduction, fusion with visible light images (often using GANs, UNets, and Transformers), and developing efficient object detection and segmentation models (like YOLO and Mask R-CNN adaptations) specifically tailored for IR data's characteristics. These advancements are crucial for applications ranging from autonomous driving and wildlife monitoring to medical imaging and industrial inspection, enabling enhanced scene understanding and improved performance in challenging environments.
Papers
IR image databases generation under target intrinsic thermal variability constraints
Jerome Gilles, Stephane Landeau, Tristan Dagobert, Philippe Chevalier, Christian Bolut
Génération de bases de données images IR sous contraintes avec variabilité thermique intrinsèque des cibles
Jerome Gilles, Stephane Landeau, Tristan Dagobert, Philippe Chevalier, Christian Bolut