黄宇飞,徐嘉,李智慧,张菁

• 1:北京空间飞行器总体设计部
• 2:哈尔滨工程大学计算机科学与技术学院

摘要(Abstract)：

针对传统基于多通道阈值火点判断方法在Landsat 8图像上选取困难的问题,该文提出一种基于机器学习的火点检测算法。该文采用非均衡数据分类框架,通过两个步骤实现火点检测:第一步为非火点排除,通过主分量分析提取特征,采用该文提出的正例优先感知机组合分类器排除掉大多数的非火点;第二步为精确分类,通过线性判别分析变换得到特征,采用加权支持向量机实现准确的火点判别。实验结果表明,该文算法实现了准确率与漏检率的较好折中。

关键词(KeyWords)： 火点检测;正例优先感知机;线性判别分析;加权支持向量机

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51679058);; 北京空间飞行器总体设计部研究项目

作者(Author): 黄宇飞,徐嘉,李智慧,张菁

DOI: 10.16251/j.cnki.1009-2307.2020.10.010

参考文献(References)：

• [1] LI Y,VODACEK A,KREMENS R L,et al.A hybrid contextual approach to wildland fire detection using multispectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(9):2115-2126.
• [2] 何全军,刘诚.MODIS数据自适应火点检测的改进算法[J].遥感学报,2008,12(3):448-453.(HE Quanjun,LIU Cheng.Improved MODIS data adaptive fire detection algorithm[J].Journal of Remote Sensing,2008,12(3):448-453.)
• [3] ZHU Y J,XING L X,PAN J.Method of identifying high-temperature target using shortwave infrared remote sensing data[J].Remote Sensing Information,2011,26(6):33-36.
• [4] SCHROEDER W,OLIVA P,GIGLIO L,et al.The new VIIRS 375 m active fire detection data product:algorithm description and initial assessment[J].Remote Sensing of Environment,2014,143:85-96.
• [5] ANEJIONU O C D,BLACKBURN G A,WHYATT J D.Satellite survey of gas flares:development and application of a Landsat-based technique in the Niger Delta[J].International Journal of Remote Sensing,2014,35(5):1900-1925.
• [6] 杜品,刘明旭,徐婷婷,等.利用Himawari-8数据监测森林火情初探[J].北京大学学报(自然科学版),2018,54(6):1251-1258.(DU Pin,LIU Mingxu,XU Tingting,et al.Application of Himawari-8 data in monitoring forest fire[J].Acta Scientiarum Universitatis Pakinensis,2018,54(6):1251-1258.)
• [7] 何阳,杨进,马勇,等.基于Landsat-8陆地卫星数据的火点检测方法[J].红外与毫米波学报,2016,35(5):600-608.(HE Yang,YANG Jin,MA Yong,et al.A method for fire detection using Landsat-8 data[J].Journal of Infrared and Millimeter Waves,2016,35(5):600-608.)
• [8] SCHROEDER W,OLIVA P,GIGLIO L,et al.Active fire detection using Landsat-8/OLI data[J].Remote Sensing of Environment,2016,185:210-220.
• [9] 李佳,李舒婷,段平,等.基于MODIS的河南省秸秆焚烧遥感监测与分析[J].测绘工程,2018,27(1):42-46.(LI Jia,LI Shuting,DUAN Ping,et al.Remote sensing monitoring and analysis of straw burning in Henan province based on MODIS[J].Engineering of Surveying and Mapping,2018,27(1):42-46.)
• [10] ROY P,GUHA A,KUMAR K V.An approach of surface coal fire detection from ASTER and Landsat-8 thermal data:Jharia coal field,India[J].International Journal of Applied Earth Observation and Geoinformation,2015,39:120-127.
• [11] 许青云,顾伟伟,谢涛,等.秸秆焚烧火点遥感监测算法实现[J].遥感技术与应用,2017,32(4):728-732.(XU Qingyun,GU Weiwei,XIE Tao,et al.CropStraw fire remote sensing monitoring and its algorithm implementation[J].Remote Sensing Technology and Application,2017,32(4):728-732.)
• [12] 肖霞,宋卫国,王彦,等.基于类间方差的MODIS森林火灾火点检测方法[J].光谱学与光谱分析,2010,30(8):2065-2068.(XIAO Xia,SONG Weiguo,WANG Yan,et al.An improved method for forest fire spot detection based on variance between-class[J].Spectroscopy and Spectral Analysis,2010,30(8):2065-2068.)
• [13] KOLTUNOV A,USTIN S L.Early fire detection using non-linear multitemporal prediction of thermal imagery[J].Remote Sensing of Environment,2007,110(1):18-28.
• [14] KATO S,KOUYAMA T,NAKAMURA R,et al.Simultaneous retrieval of temperature and area according to sub-pixel hotspots from nighttime Landsat 8 OLI data[J].Remote Sensing of Environment,2018,204:276-286.
• [15] ZHANG Y,SUN B,XIAO Y,et al.Feature augmentation for imbalanced classification with conditional mixture WGANs[J].Signal Processing (Image Communication),2019,75:89-99.
• [16] CHEN G,GE Z.SVM-tree and SVM-forest algorithms for imbalanced fault classification in industrial processes[J/OL].IFAC Journal of Systems and Control,2019[2019-05-23].https://doi.org/10.1016/j.ifacsc.2019.100052.
• [17] KOZIARSKI M,KRAWCZYK B,WO■ oversampling for noisy imbalanced data classification[J].Neurocomputing,2019,343:19-33.
• [18] WANG Y,YANG L.A robust loss function for classification with imbalanced datasets[J].Neurocomputing,2019,331:40-49.
• [19] KRAWCZYK B,GALAR M,WO■.Dynamic ensemble selection for multi-class classification with one-class classifiers[J].Pattern Recognition,2018,83:34-51.
• [20] GAUTAM C,BALAJI R,SUDHARSAN K,et al.Localized multiple kernel learning for anomaly detection:one-class classification[J].Knowledge-Based Systems,2019,165:241-252.
• [21] FARAJZADEH-ZANJANI M,RAZAVI-FAR R,SAIF M.Efficient sampling techniques for ensemble learning and diagnosing bearing defects under class unbalanced condition[C]//2016 IEEE Symposium Serieson Computational Intelligence.[S.l.]:[s.n.],2016.
• [22] BALAKRISHNAMA S,GANAPATHIRAJU A.Linear discriminant analysis-a brief tutorial[J].Institute for Signal and Information Processing,1998,18:1-8.
• [23] XANTHOPOULOS P,RAZZAGHI T.A weighted support vector machine method for control chart pattern recognition[J].Computers & Industrial Engineering,2014,70:134-149.