XClose

UCL Department of Civil, Environmental and Geomatic Engineering

Home
Menu

Building segmentation using Convolutional Neural Networks for fused airborne lidar and image data

We develop a novel pipeline which uses Active Contour models and fused image-lidar data to achieve state-of-the-art accuracy in aerial building segmentation using CNNs.

Colourized and rasterized airborne LIDAR scene

6 June 2019

Manually labelling buildings for segmentation is a time-consuming task. We show that readily available GIS mapping data such as that from the Ordnance Survey (UK) can be used as training data. Further, we develop a novel pipeline which uses Active Contour models and fused image-lidar data to achieve state-of-the-art accuracy in aerial building segmentation.


People


Publication

Publisher link