Full-Waveform Airborne LiDAR Data Classification Using Convolutional Neural Networks

Stefano Zorzi, Eleonora Maset, Andrea Fusiello, Fabio Crosilla

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Point cloud classification is one of the most important and time-consuming stages of airborne LiDAR (Light Detection and Ranging) data processing, playing a key role in the generation of cartographic products. This paper describes an innovative algorithm to perform LiDAR point-cloud classification, which relies on Convolutional Neural Networks (CNNs) and takes advantage of full-waveform data registered by modern laser scanners. The proposed method consists of two steps. First, a simple CNN is used to preprocess each waveform, providing a compact representation of the data. By exploiting the coordinates of the points associated with the waveforms, output vectors generated by the first CNN are then mapped into an image that is subsequently segmented by a Fully Convolutional Network (FCN): a label is assigned to each pixel and, consequently, to the point falling in the pixel. In this way, spatial positions and geometrical relationships between neighboring data are taken into account. These particular architectures allow to accurately identify even challenging classes such as power line and transmission tower.
Original languageEnglish
Pages (from-to)8255-8261
JournalIEEE transactions on geoscience and remote sensing
Volume57
Issue number10
DOIs
Publication statusPublished - 2019

    Fingerprint

Cite this