薛园园,黄远程,苏远超

• 1:西安科技大学

摘要(Abstract)：

针对孤立森林算法在高光谱影像异常目标检测中易产生大量虚警的问题,该文将异常目标在空间分布的稀缺性与目标光谱的差异性两个先验结合,提出了一种空间加权的孤立森林异常目标检测方法。首先利用孤立森林算法计算目标的光谱异常度,得到初步的检测结果;然后分析初步结果中目标区域的连通面积,以连通域面积为变量,基于高斯核计算目标的空间稀缺性,得到目标的空间权重属性;最后将表达空间稀缺性的属性与光谱异常度加权相乘,实现了对异常目标的准确检测。在五组高光谱数据集上的实验结果表明,该方法具有较好的检测性能。

关键词(KeyWords)： 高光谱影像;孤立森林;空间加权;异常目标检测

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金青年基金项目(42001319)

作者(Author): 薛园园,黄远程,苏远超

DOI: 10.16251/j.cnki.1009-2307.2021.07.013

参考文献(References)：

• [1] 张兵.高光谱图像处理与信息提取前沿[J].遥感学报，2016,20(5):1062-90.(ZHANG Bing.Advancement of hyperspectral image processing and information extraction[J].Journal of Remote Sensing,2016,20(5):1062-90.)
• [2] 冉琼，于浩洋，高连如，等.结合超像元和子空间投影支持向量机的高光谱图像分类[J].中国图象图形学报，2018,23(1):95-105.(RAN Qiong,YU Haoyang,GAO Lianru,et al.Superpixel and subspace projection-based support vector machines for hyperspectral image classification[J].Journal of Image and Graphics,2018,23(1):95-105.)
• [3] 陈亨，邓非.分解式三维卷积神经网络的高光谱遥感影像分类[J].测绘科学，2020,45(8):96-102,29.(CHEN Heng,DENG Fei.Hyperspectral remote sensing image classification based on decomposed three-dimensional convolutional neural network[J].Science of Surveying and Mapping,2020,45(8):96-102,29.)
• [4] HUYAN N,ZHANG X,ZHOU H,et al.Hyperspectral anomaly detection via background and potential anomaly dictionaries construction[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(4):2263-76.
• [5] 童庆禧，张兵，张立福.中国高光谱遥感的前沿进展[J].遥感学报，2016,20(5):689-707.(TONG Qingxi,ZHANG Bing,ZHANG Lifu.Current progress of hyperspectral remote sensing in China[J].Journal of Remote Sensing,2016,20(5):689-707.)
• [6] 孙林，鲍金河，刘一超.高光谱图像目标检测算法分析[J].测绘科学，2012,37(1):131-132.(SUN Lin,BAO Jinhe,LIU Yichao.A summary on the development of current target detection algorithms for hyperspectral imagery[J].Science of Surveying and Mapping,2012,37(1):131-132.)
• [7] REED I S,YU X.Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J].IEEE Transactions on Acoustics Speech & Signal Processing,38(10):1760-1770.
• [8] LING Q,GUO Y L,LIN Z P,et al.A constrained sparse representation model for hyperspectral anomaly detection[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(4):2358-2371.
• [9] LI J,ZHANG H,ZHANG L,et al.Hyperspectral anomaly detection by the use of background joint sparse representation[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2523-2533.
• [10] YANG Y X,ZHANG J Q,SONG S Z,et al.Low-rank and sparse matrix decomposition with orthogonal subspace projection-based background suppression for hyperspectral anomaly detection[J].IEEE Geoscience and Remote Sensing Letters,2020,17(8):1378-1382.
• [11] XU Y C,DU B,ZHANG L P,et al.A low-rank and sparse matrix decomposition-based dictionary reconstruction and anomaly extraction framework for hyperspectral anomaly detection[J].IEEE Geoscience and Remote Sensing Letters,2020,17(7):1248-1252.
• [12] LIU F T,TING K M,ZHOU Z H.Isolation forest[C]//Data Mining,2008.ICDM’08.Eighth IEEE International Conference on.[S.l.]:IEEE,2009.
• [13] OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems Man & Cybernetics,2007,9(1):62-66.
• [14] TIAN J,YU W Y,XIE S L.On the kernel function selection of nonlocal filtering for image denoising[C]//International Conference on Machine Learning & Cybernetics.[S.l.]:IEEE,2008.
• [15] KANG X,ZHANG X,LI S,et al.Hyperspectral anomaly detection with attribute and edge-preserving filters[J].IEEE Transactions on Geoscience & Remote Sensing,2017,55(10):5600-5611.
• [16] 黄远程，钟燕飞，赵野鹤，等.联合盲分解与稀疏表达的高光谱图像异常目标检测[J].武汉大学学报(信息科学版),2015,40(9):1144-1150.(HUANG Yuancheng,ZHONG Yanfei,ZHAO Yehe,et al.Joint Blind Unmixing and sparse representation for anomaly detection in hyperspectral image[J].Geomatics and Information Science of Wuhan University,2015,40(9):1144-1150.)
• [17] 王强辉，华文深，黄富瑜，等.基于近似后验信息的高光谱异常检测[J].光谱学与光谱分析，2020,40(8):2538-2545.(WANG Qianghui,HUA Wenshen,HUANG Fuyu,et al.Hyperspectral anomaly detection based on approximate posterior information[J].Spectroscopy and Spectral Analysis,2020,40(8):2538-2545.)
• [18] 王志威，谭琨，王雪，等.基于光谱空间重构的非监督最邻近规则子空间的高光谱异常检测[J].光子学报，2020,49(6):80-91.(WANG Zhiwei,TAN Kun,WANG Xue,et al.Unsupervised nearest regularized subspace based on spectral space reconstruction for hyperspectral anomaly detection[J].Acta Photonica Sinica,2020,49(6):80-91.)
• [19] CHANG S,DU B,ZHANG L.BASO:A background-anomaly component projection and separation optimized filter for anomaly detection in hyperspectral images[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(7):3747-61.