2. Deep learning for the classification of water and bridges in Airborne Laser Scanner data

Deep learning for the classification of water and bridges in Airborne Laser Scanner data

M-GEO
M-SE
M-SE Core knowledge areas
Spatial Information Science (SIS)
Topic description

In general classes such as Buildings and Vegetation and Terrain are well classified. The classes Bridges and Water are more problematic, even for deep learning algorithms. But what is exactly the reason and how should be deal with these classes?

Topic objectives and methodology

Key challenge in this research is to find out different strategies to improve the classification of water and bridges.