UPM Institutional Repository

Land cover classification from fused DSM and UAV images using convolutional neural networks


Citation

Al-Najjar, Husam A. H. and Kalantar, Bahareh and Pradhan, Biswajeet and Saeidi, Vahideh and Abdul Halin, Alfian and Ueda, Naonori and Mansor, Shattri (2019) Land cover classification from fused DSM and UAV images using convolutional neural networks. Remote Sensing, 11 (12). art. no. 1461. pp. 1-18. ISSN 2072-4292

Abstract

In recent years, remote sensing researchers have investigated the use of different modalities (or combinations of modalities) for classification tasks. Such modalities can be extracted via a diverse range of sensors and images. Currently, there are no (or only a few) studies that have been done to increase the land cover classification accuracy via unmanned aerial vehicle (UAV)–digital surface model (DSM) fused datasets. Therefore, this study looks at improving the accuracy of these datasets by exploiting convolutional neural networks (CNNs). In this work, we focus on the fusion of DSM and UAV images for land use/land cover mapping via classification into seven classes: bare land, buildings, dense vegetation/trees, grassland, paved roads, shadows, and water bodies. Specifically, we investigated the effectiveness of the two datasets with the aim of inspecting whether the fused DSM yields remarkable outcomes for land cover classification. The datasets were: (i) only orthomosaic image data (Red, Green and Blue channel data), and (ii) a fusion of the orthomosaic image and DSM data, where the final classification was performed using a CNN. CNN, as a classification method, is promising due to hierarchical learning structure, regulating and weight sharing with respect to training data, generalization, optimization and parameters reduction, automatic feature extraction and robust discrimination ability with high performance. The experimental results show that a CNN trained on the fused dataset obtains better results with Kappa index of ~0.98, an average accuracy of 0.97 and final overall accuracy of 0.98. Comparing accuracies between the CNN with DSM result and the CNN without DSM result for the overall accuracy, average accuracy and Kappa index revealed an improvement of 1.2%, 1.8% and 1.5%, respectively. Accordingly, adding the heights of features such as buildings and trees improved the differentiation between vegetation specifically where plants were dense.


Download File

[img] Text
38354.pdf
Restricted to Repository staff only

Download (8MB)
Official URL or Download Paper: https://www.mdpi.com/2072-4292/11/12/1461

Additional Metadata

Item Type: Article
Divisions: Faculty of Computer Science and Information Technology
Faculty of Engineering
DOI Number: https://doi.org/10.3390/rs11121461
Publisher: MDPI
Keywords: Land cover classification; Remote sensing; GIS; UAV; Deep-learning; Fusion
Depositing User: Nabilah Mustapa
Date Deposited: 04 May 2020 16:22
Last Modified: 04 May 2020 16:22
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.3390/rs11121461
URI: http://psasir.upm.edu.my/id/eprint/38354
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item