Land Cover Classification using Very High Spatial Resolution Remote Sensing Data and Deep Learning

The paper describes the process of training a convolutional neural network to segment land into its labelled land cover types such as grass, water, forest and buildings. This segmentation can promote automated updating of topographical maps since doing this manually is a time-consuming process, which is prone to human error. The aim of the study is to evaluate the application of U-net convolutional neural network for land cover classification using countrywide aerial data. U-net neural network architecture has initially been developed for use in biomedical image segmentation and it is one of the most widely used CNN architectures for image segmentation. Training data have been prepared using colour infrared images of Ventspils town and its digital surface model (DSM). Forest, buildings, water, roads and other land plots have been selected as classes, into which the image has been segmented. As a result, images have been segmented with an overall accuracy of 82.9 % with especially high average accuracy for the forest and water classes.