Wang, Junling, Fan, Xijian, Yang, Xubing, Tjahjadi, Tardi and Wang, Yupeng (2022) Semi-supervised learning for forest fire segmentation using UAV imagery. Forests, 13 (10). 1573. doi:10.3390/f13101573 ISSN 1999-4907.

Preview

PDF WRAP-Semi-supervised-learning-forest-fire-segmentation-UAV-imagery-22.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (5Mb) | Preview

Request Changes to record.

Abstract

Unmanned aerial vehicles (UAVs) are an efficient tool for monitoring forest fire due to its advantages, e.g., cost-saving, lightweight, flexible, etc. Semantic segmentation can provide a model aircraft to rapidly and accurately determine the location of a forest fire. However, training a semantic segmentation model requires a large number of labeled images, which is labor-intensive and time-consuming to generate. To address the lack of labeled images, we propose, in this paper, a semi-supervised learning-based segmentation network, SemiFSNet. By taking into account the unique characteristics of UAV-acquired imagery of forest fire, the proposed method first uses occlusion-aware data augmentation for labeled data to increase the robustness of the trained model. In SemiFSNet, a dynamic encoder network replaces the ordinary convolution with dynamic convolution, thus enabling the learned feature to better represent the fire feature with varying size and shape. To mitigate the impact of complex scene background, we also propose a feature refinement module by integrating an attention mechanism to highlight the salient feature information, thus improving the performance of the segmentation network. Additionally, consistency regularization is introduced to exploit the rich information that unlabeled data contain, thus aiding the semi-supervised learning. To validate the effectiveness of the proposed method, extensive experiments were conducted on the Flame dataset and Corsican dataset. The experimental results show that the proposed model outperforms state-of-the-art methods and is competitive to its fully supervised learning counterpart.

Item Type:	Journal Article
Subjects:	Q Science > Q Science (General) S Agriculture > SD Forestry T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Science, Engineering and Medicine > Engineering > Engineering
Library of Congress Subject Headings (LCSH):	Forest fires, Forest fires -- Detection , Forest fires -- Prevention and control, Drone aircraft, Supervised learning (Machine learning) , Semantic Web, Image segmentation , Neural networks (Computer science)
Journal or Publication Title:	Forests
Publisher:	MDPI
ISSN:	1999-4907
Official Date:	26 September 2022
Dates:	Date Event 26 September 2022 Published 22 September 2022 Accepted
Volume:	13
Number:	10
Article Number:	1573
DOI:	10.3390/f13101573
Status:	Peer Reviewed
Publication Status:	Published
Access rights to Published version:	Open Access (Creative Commons)
Description:	This article belongs to the Special Issue Deep Learning Techniques for Forest Parameter Retrieval and Accurate Tree Modeling from Remote Sensing Data
Date of first compliant deposit:	27 September 2022
Date of first compliant Open Access:	27 September 2022
RIOXX Funder/Project Grant:	Project/Grant ID RIOXX Funder Name Funder ID 2020-KF-22-04 State Key Laboratory of Robotics http://dx.doi.org/10.13039/501100011259 2020-KF-22-04 Department of Science and Technology of Liaoning Province http://dx.doi.org/10.13039/501100012131 61902187 [NSFC] National Natural Science Foundation of China http://dx.doi.org/10.13039/501100001809 KYCX22_1105 Graduate Research and Innovation Projects of Jiangsu Province http://dx.doi.org/10.13039/501100012154
Related URLs:	Publisher

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads