Multi source remote sensing

Remote sensing data analysis has gained attention in recent years due to the development of a wide range of sensing technologies. Among the different types of analysis, particular attention has been given to classification which consists of assigning a label to each pixel in order to generate a thematic land-cover map. Disparate features either from the same (e.g., spectral and spatial information) or different sensors (e.g., hyperspectral and LiDAR) are often combined as they can provide complementary information, and therefore improve the classification performance. My work is to develop effective supervised classification frameworks to fully utilize the multi-source data, with the goal of generating accurate classification maps. ​​