Improving Wildfire Severity Classification of Deep Learning U-Nets from Satellite Images

被引:9
作者
Monaco, Simone [1 ]
Pasini, Andrea [1 ]
Apiletti, Daniele [1 ]
Colomba, Luca [1 ]
Garza, Paolo [1 ]
Baralis, Elena [1 ]
机构
[1] Politecn Torino, Dept Control & Comp Engn, Turin, Italy
来源
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2020年
关键词
Burned Area delineation; Convolutional Neural Network; Deep learning; Supervised Learning; Semantic segmentation;
D O I
10.1109/BigData50022.2020.9377867
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Uncontrolled wildfires are dangerous events capable of harming people safety. To contrast their increasing impact in recent years, a key task is an accurate detection of the affected areas and their damage assessment from satellite images. Current state-of-the-art solutions address such problem through a double convolutional neural network able to automatically detect wildfires in satellite acquisitions and associate a damage index from a defined scale. However, such deep-learning model performance is strongly dependent on many factors. In this work, we specifically focus on a key parameter, i.e., the loss function, exploited in the underlying neural networks. Besides the state-of-the-art solutions based on the Dice-MSE, among the many loss functions proposed in literature, we focus on the Binary Cross-Entropy (BCE) and the Intersection over Union (IoU), as two representatives of the distribution-based and region-based categories, respectively. Experiments show that the BCE loss function coupled with a double-step U-Net architecture provides better results than current state-of-the-art solutions on a public labeled dataset of European wildfires.
引用
收藏
页码:5786 / 5788
页数:3
相关论文
共 16 条
[1]  
[Anonymous], 2006, FIREMON FIRE EFFECTS
[2]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[3]   Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning [J].
Ban, Yifang ;
Zhang, Puzhao ;
Nascetti, Andrea ;
Bevington, Alexandre R. ;
Wulder, Michael A. .
SCIENTIFIC REPORTS, 2020, 10 (01)
[4]  
Chen LB, 2017, IEEE INT SYMP NANO, P1, DOI 10.1109/NANOARCH.2017.8053709
[5]  
European Union, 2009, COP SENT 2 MISS 2020
[6]   Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data [J].
Farasin, Alessandro ;
Colomba, Luca ;
Garza, Paolo .
APPLIED SCIENCES-BASEL, 2020, 10 (12)
[7]   A survey of loss functions for semantic segmentation [J].
Jadon, Shruti .
2020 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB), 2020, :115-121
[8]   A Comparative Study of 2D Image Segmentation Algorithms for Traumatic Brain Lesions Using CT Data from the ProTECTIII Multicenter Clinical Trial [J].
Jadon, Shruti ;
Leary, Owen P. ;
Pan, Ian ;
Harder, Tyler J. ;
Wright, David W. ;
Merck, Lisa H. ;
Merck, Derek .
MEDICAL IMAGING 2020: IMAGING INFORMATICS FOR HEALTHCARE, RESEARCH, AND APPLICATIONS, 2020, 11318
[9]  
Ma J., 2020, ARXIV200513449
[10]   Quantifying burn severity in a heterogeneous landscape with a relative version of the delta Normalized Burn Ratio (dNBR) [J].
Miller, Jay D. ;
Thode, Andrea E. .
REMOTE SENSING OF ENVIRONMENT, 2007, 109 (01) :66-80