Accueil de Wenzhi LIAO, post-doctorant à iMinds-Telin-IPI, Ghent University (Belgique)

Recent advances in sensors technology have led to an increased availability of imagery at very high spatial resolutions. Many techniques are developed to explore the spatial information of the high resolution imagery, in particular, mathematical morphology is one of the most popular methods. In this research, we will combine morphological attribute profiles (from Gipsa-lab) and partial reconstruction (from iMinds-Telin-IPI) to exploit the spatial information of very high spatial resolution imagery. Our proposed method can not only model as much geometrical characteristics as MAPs, but also overcome over-reconstruction problems.