Date depot: 6 avril 2021 Titre: UAV Aerial Images Enhancement Directrice de thèse: Maria TROCAN (LISITE) Encadrante : Patricia CONDE-CESPEDES (LISITE) Domaine scientifique: Sciences et technologies de l'information et de la communication Thématique CNRS : Non defini Resumé: Unmanned aerial vehicle (UAV) -vision applications are increasingly widespread in recent years mostly in photogrammetric and remote-sensing applications such as traffic infrastructure, hydraulic engineering, media broadcast, and police tracking, etc. However, UAVs usually have limitations regarding their flight time. In order to monitor a large geographic area in a short time, flights must be performed at higher altitudes. This implies a loss of spatial resolution because cameras have limitations in terms of their optics and the size of the pixels. As a result, the obtained images have low resolution and are sometimes blurred. Besides, the aerial flight factors and image compression process caused by the loss of high-frequency components may affect (may worsen) the color tone, brightness informative range, contrast and object visibility on the final image. To improve the quality of such images, the image enhancement is an indispensable post-processing method. The task of reconstructing high-resolution images given low-resolution images is called image super-resolution (SR). The principle of image enhancement is to process a given blurred image so that it is more suitable for visual quality or image analysis.