Library
local_library Home Repository

Classification of airborne laser scanning point cloud using point-based convolutional neural network

Journal Article (2021)
Author(s)

Jianfeng Zhu (Chang'an University, Jiangxi College of Applied Technology)

Lichun Sui (Chang'an University)

Yufu Zang (Nanjing University of Information Science and Technology, TU Delft - Optical and Laser Remote Sensing)

He Zheng (Jiangxi College of Applied Technology)

Wei Jiang (Jiangxi College of Applied Technology)

Mianqing Zhong (Lanzhou Jiaotong University)

Fei Ma (Chang'an University)

Research Group
Optical and Laser Remote Sensing
DOI related publication
https://doi.org/10.3390/ijgi10070444
More Info
expand_more
Publication Year
2021
Language
English
Research Group
Optical and Laser Remote Sensing
Issue number
7
Volume number
10
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.