Semantic Segmentation of Historical Aerial Images using Deep Learning

Forest monitoring using remotely sensed data is a central task in forestry and ecosystem studies. The long-term assessment of woody vegetation assists, for instance, in change detection and handling environmental hazards. Recently, France has made available its historical aerial images archive, dating from the 1930s, covering the whole country extent, often with more than one revisit time per site. The public availability of such datasets expands the scope of long-term monitoring studies, such as forest monitoring.

The main aim of this study was to investigate deep learning algorithms for performing semantic segmentation of woody vegetation using historical grayscale aerial images in southern-west France. This research's main contribution is to explore deep learning strategies to delineate trees, regardless of their spatial configuration.