基于滤波张量分析的高光谱目标检测方法

doi:10.7523/j.ucas.2020.0060

摘要/Abstract

摘要： 现有的高光谱图像目标检测算法大都把各个波段不加区分地对待，从而不能充分利用图像波段的物理信息。将高光谱图像按照成像机理的不同首先分为几个不同的波段范围（比如可见光、近红外、短波红外等），并通过将高光谱图像的不同波段范围与多时相遥感数据的时相维进行对应，将最近发展的一个多时相目标检测算法——滤波张量分析（filter tensor analysis，FTA）引入高光谱目标检测中，提出一种面向单时相高光谱图像的分波段FTA算法。针对高光谱图像的实验表明，与传统的单时相目标检测算法相比，分波段FTA算法取得了很好的检测效果。

关键词: 高光谱图像, 目标检测, FTA, 分波段, CEM

Abstract: Most of the existing target detection algorithms for hyperspectral images treat each band indiscriminately, so the physical information of the image band cannot be fully utilized. In this paper, the hyperspectral images are firstly divided into several different waveband ranges (such as visible light, near infrared, shortwave infrared, etc.) according to the different imaging mechanisms. A recently developed multi-temporal target detection algorithm:FTA (filter tensor analysis) is introduced into the hyperspectral target detection by combining the different waveband ranges of the hyperspectral images with the time-phase dimension of multi-temporal remote sensing data correspondingly. Based on the new approach, a band-divided FTA algorithm for single-temporal hyperspectral images is proposed. Experiments on hyperspectral images prove that the band-divided FTA algorithm can achieve better results in target detection than the traditional single-phase target detection algorithm.

Key words: hyperspectral image, target detection, FTA, band-divided, CEM

中图分类号:

TP751.1

杨帅, 计璐艳, 耿修瑞. 基于滤波张量分析的高光谱目标检测方法[J]. 中国科学院大学学报, 2022, 39(5): 684-694.

YANG Shuai, JI Luyan, GENG Xiurui. Hyperspectral target detection method based on filter tensor analysis[J]. Journal of University of Chinese Academy of Sciences, 2022, 39(5): 684-694.

参考文献

[1] 杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展[J].遥感学报,2016,20(2):236-256.DOI:10.11834/jrs.20165022.
[2] Sun K, Geng X R, Ji L Y, et al. A new band selection method for hyperspectral image based on data quality[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2697-2703.DOI:10.1109/JSTARS.2014.2320299.
[3] 孙康,耿修瑞,唐海蓉,等.一种基于非线性主成分分析的高光谱图像目标检测方法[J].测绘通报,2015(1):105-108.DOI:10.13474/j.cnki.11-2246.2015.0022.
[4] 陈功伟,赵思颖,倪才英.高光谱监测技术在重金属污染土壤上的应用[J].中国科学院大学学报,2019,36(4):560-566.DOI:10.7523/j.issn.2095-6134.2019.04.016.
[5] 张姗.归一化植被指数研究[J].绿色科技,2019(20):25-28.DOI:10.16663/j.cnki.lskj.2019.20.009.
[6] McFEETERS S K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.DOI:10.1080/01431169608948714.
[7] 许卫东,尹球,匡定波.地物光谱匹配模型比较研究[J].红外与毫米波学报,2005,24(4):296-300.DOI:10.3321/j.issn:1001-9014.2005.04.013.
[8] Liu Y, Lu S, Lu X T,et al. Classification of urban hyperspectral remote sensing imagery based on optimized spectral angle mapping[J]. Journal of the Indian Society of Remote Sensing, 2019, 47(2):289-294.DOI:10.1007/s12524-018-0929-1.
[9] 贺霖,潘泉,邸韡,等.高光谱图像目标检测研究进展[J].电子学报,2009,37(9):2016-2024.DOI:10.3321/j.issn:0372-2112.2009.09.024.
[10] 耿修瑞. 高光谱遥感图像目标探测与分类技术研究[D].北京:中国科学院研究生院(遥感应用研究所), 2005.
[11] Ren H, Chang C I. Automatic spectral target recognition in hyperspectral imagery[J].IEEE Transactions on Aerospace and Electronic Systems, 2003, 39(4):1232-1249.DOI:10.1109/TAES.2003.1261124.
[12] Ren H, Chang C I. A generalized orthogonal subspace projection approach to unsupervised multispectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(6):2515-2528.
[13] Du Q, Chang C I.Interference subspace projection approach to subpixel target detection[C]//Aerospace/Defense Sensing, Simulation, and Controls. Proc SPIE 4381, Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VII, Orlando, FL, USA. 2001, 4381:570-577.DOI:10.1117/12.437049.
[14] Tu T M, Chen C H, Chang C I.A noise subspace projection approach to target signature detection and extraction in an unknown background for hyperspectral images[J].IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(1):171-181.DOI:10.1109/36.655327.
[15] 寻丽娜,方勇华,李新.基于CEM的高光谱图像小目标检测算法[J].光电工程,2007,34(7):18-21.DOI:10.3969/j.issn.1003-501X.2007.07.004.
[16] Manolakis D G,Shaw G A. Directionally constrained or constrained energy minimization adaptive matched filter:theory and practice[C]//International Symposium on Optical Science and Technology. Proc SPIE 4480, Imaging Spectrometry VII, San Diego, CA, USA. 2002, 4480:57-64.DOI:10.1117/12.453327.
[17] Kraut S, Scharf L L.The CFAR adaptive subspace detector is a scale-invariant GLRT[J].IEEE Transactions on Signal Processing,1999,47(9):2538-2541.
[18] Geng X R,Ji L Y, Sun K. Clever eye algorithm for target detection of remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2016,114:32-39.DOI:10.1016/j.isprsjprs.2015.10.014.
[19] 唐意东, 黄树彩, 凌强, 等.高光谱图像自适应核联合表示异常检测[J].强激光与粒子束, 2015, 27(9):091008.DOI:10.11884/HPLPB201527.091008.
[20] Kwon H, Nasrabadi N M. Kernel spectral matched filter for hyperspectral imagery[J]. International Journal of Computer Vision, 2007, 71(2):127-141.DOI:10.1007/s11263-006-6689-3.
[21] 张小荣,胡炳樑,潘志斌,等.基于张量表示的高光谱图像目标检测[J].光学精密工程,2019,27(2):488-498.DOI:10.3788/OPE.20192702.0488.
[22] Geng X R, Yang W T, Ji L Y,et al. A piecewise linear strategy of target detection for multispectral/hyperspectral image[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(3):951-961.DOI:10.1109/JSTARS.2018.2791920.
[23] Xiao X M, Boles S, Liu J Y, et al. Characterization of forest types in Northeastern China, using multi-temporal SPOT-4 VEGETATION sensor data[J]. Remote Sensing of Environment, 2002, 82(2/3):335-348.DOI:10.1016/S0034-4257(02)00051-2.
[24] Xiao X M, Boles S, Liu J Y, et al. Mapping paddy rice agriculture in Southern China using multi-temporal MODIS images[J]. Remote Sensing of Environment, 2005, 95(4):480-492.DOI:10.1016/j.rse.2004.12.009.
[25] Geng X R, Ji L Y, Zhao Y C. Filter tensor analysis:a tool for multi-temporal remote sensing target detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 151:290-301.DOI:10.1016/j.isprsjprs.2019.03.008.
[26] Xi Y X, Ji L Y, Geng X R. Pen culture detection using filter tensor analysis with multi-temporal landsat imagery[J]. Remote Sensing,2020,12(6):1018.DOI:10.3390/rs12061018.
[27] Green A A, Berman M, Switzer P, et al.A transformation for ordering multispectral data in terms of image quality with implications for noise removal[J].IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(1):65-74.DOI:10.1109/36.3001.
[28] Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8):861-874.DOI:10.1016/j.patrec.2005.10.010.
[29] 汪云云,陈松灿.基于AUC的分类器评价和设计综述[J].模式识别与人工智能,2011,24(1):64-71.DOI:10.16451/j.cnki.issn1003-6059.2011.01.014.