Fully Convolutional Networks for Ground Classification from Airborne Laser Scanner data
Lists
Only you see this
Abstract
We present an efficient procedure to classify airborne laser scanner data into ground and non-ground. The classification is performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on AHN-3 data resulting in 4.02% of total error, 2.15% of type I error and 6.14% of type II error. We show that this method can be extended to further classify the point cloud into buildings and vegetation.
BibTeX
@inproceedings{rizaldy2018fully,
author = {Aldino Rizaldy and Claudio Persello and Caroline Gevaert and Sander Oude Elberink and George Vosselman},
title = {{Fully Convolutional Networks for Ground Classification from Airborne Laser Scanner data}},
booktitle = {University},
year = {2018},
}Loading related content...