Next Article in Journal
Combining a Two Source Energy Balance Model Driven by MODIS and MSG-SEVIRI Products with an Aggregation Approach to Estimate Turbulent Fluxes over Sparse and Heterogeneous Vegetation in Sahel Region (Niger)
Next Article in Special Issue
CraterIDNet: An End-to-End Fully Convolutional Neural Network for Crater Detection and Identification in Remotely Sensed Planetary Images
Previous Article in Journal
Assessment of Irrigation Performance in Large River Basins under Data Scarce Environment—A Case of Kabul River Basin, Afghanistan
Previous Article in Special Issue
Performance Evaluation of Single-Label and Multi-Label Remote Sensing Image Retrieval Using a Dense Labeling Dataset
Open AccessArticle

Land Cover Segmentation of Airborne LiDAR Data Using Stochastic Atrous Network

1
Faculty of Science and Technology, Norwegian University of Life Sciences, 1432 Ås, Norway
2
Division of Survey and Statistics, Norwegian Institute of Bioeconomy Research, 1431 Ås, Norway
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(6), 973; https://doi.org/10.3390/rs10060973
Received: 30 April 2018 / Revised: 15 June 2018 / Accepted: 17 June 2018 / Published: 19 June 2018
(This article belongs to the Special Issue Deep Learning for Remote Sensing)
Inspired by the success of deep learning techniques in dense-label prediction and the increasing availability of high precision airborne light detection and ranging (LiDAR) data, we present a research process that compares a collection of well-proven semantic segmentation architectures based on the deep learning approach. Our investigation concludes with the proposition of some novel deep learning architectures for generating detailed land resource maps by employing a semantic segmentation approach. The contribution of our work is threefold. (1) First, we implement the multiclass version of the intersection-over-union (IoU) loss function that contributes to handling highly imbalanced datasets and preventing overfitting. (2) Thereafter, we propose a novel deep learning architecture integrating the deep atrous network architecture with the stochastic depth approach for speeding up the learning process, and impose a regularization effect. (3) Finally, we introduce an early fusion deep layer that combines image-based and LiDAR-derived features. In a benchmark study carried out using the Follo 2014 LiDAR data and the NIBIO AR5 land resources dataset, we compare our proposals to other deep learning architectures. A quantitative comparison shows that our best proposal provides more than 5% relative improvement in terms of mean intersection-over-union over the atrous network, providing a basis for a more frequent and improved use of LiDAR data for automatic land cover segmentation. View Full-Text
Keywords: land cover segmentation; stochastic depth atrous network; IoU loss function; airborne LiDAR data; deep learning data fusion land cover segmentation; stochastic depth atrous network; IoU loss function; airborne LiDAR data; deep learning data fusion
Show Figures

Graphical abstract

MDPI and ACS Style

Arief, H.A.; Strand, G.-H.; Tveite, H.; Indahl, U.G. Land Cover Segmentation of Airborne LiDAR Data Using Stochastic Atrous Network. Remote Sens. 2018, 10, 973.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop