基于背景重建的高光谱图像异常检测

doi:10.16182/j.issn1004731x.joss.19-VR0504

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (7): 1287-1293.doi: 10.16182/j.issn1004731x.joss.19-VR0504

基于背景重建的高光谱图像异常检测

宋晓瑞¹, 邹玲^{2, 3}, 吴玲达¹, 徐万朋^{1, 3}

1. 航天工程大学复杂电子系统仿真实验室,北京 101416;
2. 北京电影学院数字媒体学院,北京 100088;
3. 鹏城实验室,广东深圳 518000

收稿日期:2019-09-06 修回日期:2020-03-16 出版日期:2020-07-25 发布日期:2020-07-15
作者简介:宋晓瑞(1990-),女,山东滨州,博士生,研究方向为高光谱图像处理技术;邹玲(1986-),女,北京,博士,硕导,研究方向为虚拟现实技术。

Hyperspectral Image Anomaly Detection Based on Background Reconstruction

Song Xiaorui¹, Zou Ling^{2, 3}, Wu Lingda¹, Xu Wanpeng^{1, 3}

1. Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing 101416, China;
2. Digital Media School, Beijing Film Academy, Beijing 100088, China;
3. Peng Cheng Laboratory, Shenzhen 518000, China

Received:2019-09-06 Revised:2020-03-16 Online:2020-07-25 Published:2020-07-15

摘要/Abstract

摘要： 针对高光谱图像异常检测中背景信息与异常目标信息难以有效区分,背景预测精度不佳的问题,提出一种新的基于背景重建的高光谱图像异常检测算法。通过字典学习方法获取高光谱图像背景光谱字典,并利用该字典对待检测图像进行稀疏重建,得到预测背景图像。将预测背景图像与原始图像做差后得到残差图像,进而利用局部RX检测算法对残差图像进行遍历,实现异常目标检测。通过对真实高光谱图像场景进行实验,证明了算法的有效性。

关键词: 异常检测, 高光谱, 字典学习, 稀疏表示, 在线学习

Abstract: In the anomaly detection of hyperspectral images (HSIs), aiming at the difficulty of distinguishing the abnormal target from the background and the low accuracy of background prediction, a new HSI anomaly detection algorithm based on background sparse reconstruction is proposed. An online dictionary learning method is used to estimate the background spectral dictionary. The estimated background image is sparse reconstructed by the learning dictionary. The estimated background image is subtracted from the origin image to get the residual image. The anomaly detection is achieved by using the local RX detector to traverse the residual image. The effectiveness of the proposed HSI anomaly detection algorithm based on the background sparse reconstruction is illustrated in a series of real-world data experiments.

Key words: anomaly detection, hyperspectral image (HSI), dictionary learning, sparse representation, online learning

中图分类号:

TP751

宋晓瑞, 邹玲, 吴玲达, 徐万朋. 基于背景重建的高光谱图像异常检测[J]. 系统仿真学报, 2020, 32(7): 1287-1293.

Song Xiaorui, Zou Ling, Wu Lingda, Xu Wanpeng. Hyperspectral Image Anomaly Detection Based on Background Reconstruction[J]. Journal of System Simulation, 2020, 32(7): 1287-1293.

参考文献 15

[1]	Reed I S, Yu X.Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transactions on Acoustics Speech and Signal Processing (S1558-7916), 1990, 38(10): 1760-1770.
[2]	Molero J M, Garzón E M, García I, et al.Analysis and optimizations of global and local versions of the RX algorithm for anomaly detection in hyperspectral data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (S1939-1404), 2013, 6(2): 801-814.
[3]	Manolakis D, Marden D, Shaw G A.Hyperspectral image processing for automatic target detection applications[J]. Lincoln Laboratory Journal (S0896-4130), 2003, 14(1): 79-116.
[4]	Banerjee A, Burlina P, Diehl C.A support vector method for anomaly detection in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing (S0196-2892), 2006, 44(8): 2282-2291.
[5]	Li W, Du Q, Zhang B.Combined sparse and collaborative representation for hyperspectral target detection[M]. New York: Elsevier Science Inc., 2015.
[6]	Yuan Z, Sun H, Ji K, et al.Local sparsity divergence for hyperspectral anomaly detection[J]. IEEE Geoscience and Remote Sensing Letters (S1545-598X), 2017, 11(10): 1697-1701.
[7]	Xu Y, Wu Z, Li J, et al.Anomaly detection in hyperspectral images based on low-rank and sparse representation[J]. IEEE Transactions on Geoscience and Remote Sensing (S0196-2892), 2016, 54(4): 1990-2000.
[8]	Mairal J, Bach F, Ponce J, et al.Online learning for matrix factorization and sparse coding[J]. Journal of Machine Learning Research (S1532-4435), 2010, 11(1): 19-60.
[9]	Chen S S, Donoho D L, Saunders M A.Atomic decomposition by basis pursuit[J]. SIAM Journal on Scientific Computing (S1064-8275), 1998, 20(1): 33-61.
[10]	Bioucas-Dias J M, Figueiredo M A T. Alternating direction algorithms for constrained sparse regression: Application to hyperspectral unmixing[C]// The Workshop on Hyperspectral Image & Signal Processing: Evolution in Remote Sensing. Reykjavik, Iceland: IEEE, 2010: 1-4.
[11]	张兵, 孙旭. 高光谱图像混合像元分解[M]. 北京: 科学出版社, 2015.Zhang Bing, Sun Xu.Hyperspectral images unmixing [M]. Beijing: Science Press, 2015.
[12]	ABU hyperspectral dataset[EB/OL]. [2019-11-20]. http://jiong.tea.ac.cn/people/xudongkang/Codes.html.
[13]	Kang X, Zhang X, Li S, et al.Hyperspectral anomaly detection with attribute and edge-preserving filters[J]. IEEE Transactions on Geoscience and Remote Sensing (S0196-2892), 2017(99): 1-12.
[14]	Zhu F, Wang Y, Fan B, et al.Spectral Unmixing via Data-Guided Sparsity[J]. IEEE Transactions on Image Processing (S1057-7149), 2014, 23(12): 5412-5427.
[15]	Wei L, Qian D, Bing Z, et al.Combined sparse and collaborative representation for hyperspectral target detection[J]. Pattern Recognition (S0031-3203), 2015, 48(12): 3904-3916.

基于背景重建的高光谱图像异常检测

Hyperspectral Image Anomaly Detection Based on Background Reconstruction

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 15

相关文章 15

编辑推荐

Metrics

本文评价

[1]	秦婉亭, 老松杨, 汤俊, 卢聪. 基于变分自编码器的飓风轨迹异常检测方法[J]. 系统仿真学报, 2021, 33(9): 2191-2201.
[2]	董书琴, 张斌. 面向不平衡数据的网络流量异常检测方法[J]. 系统仿真学报, 2021, 33(3): 679-689.
[3]	刘轩, 李向阳, 何芳, 赵建伟, 张峰干. 基于空谱特征融合的高光谱RX异常检测方法[J]. 系统仿真学报, 2021, 33(12): 2891-2900.
[4]	周金. 联合低秩及稀疏结构特性的毫米波通信下行信道估计[J]. 系统仿真学报, 2021, 33(1): 99-108.
[5]	王鑫, 张春燕, 宁晨. 基于Gestalt优化的红外视频时空显著性检测[J]. 系统仿真学报, 2020, 32(6): 1021-1031.
[6]	王远明, 张珺, 秦远辉, 柴秀娟. 基于多特征融合的指挥手势识别方法研究[J]. 系统仿真学报, 2019, 31(2): 346-352.
[7]	刘三民, 刘余霞. 在线合成增量式数据流分类算法[J]. 系统仿真学报, 2018, 30(6): 2315-2320.
[8]	黎明, 彭秀姣, 王艳. 基于改进的字典学习与稀疏表示的人脸表情识别[J]. 系统仿真学报, 2018, 30(1): 28-36.
[9]	邓丽, 庞洪霖, 王灵, 费敏锐. 分布式聚类在农场环境数据异常检测中的应用[J]. 系统仿真学报, 2017, 29(12): 3035-3041.
[10]	牛为华, 梁贵书, 赵鹏. 基于稀疏表示和M-ELM的断路器故障诊断模型[J]. 系统仿真学报, 2017, 29(11): 2828-2839.
[11]	杨恢先, 刘昭, 刘阳, 刘凡, 贺迪龙. 基于超像素和局部稀疏表示的目标跟踪方法[J]. 系统仿真学报, 2016, 28(5): 1017-1030.
[12]	黄丽韶, 文海英, 顾思思. 基于方法噪声稀疏表字典学习的图像去噪算法[J]. 系统仿真学报, 2016, 28(1): 154-159.
[13]	钱宜婧, 杨旭波. 流体模拟的压缩感知上采样方法研究[J]. 系统仿真学报, 2015, 27(7): 1426-1434.
[14]	高博, 王俊, 张各各. 基于原子曲线拟合的字典学习的信号去噪方法[J]. 系统仿真学报, 2015, 27(12): 2935-2941.
[15]	刘妍, 金鑫, 赵耿, 李晓东, 陈迎亚, 郭魁. 基于稀疏表示的云环境中人脸图像隐秘识别方法[J]. 系统仿真学报, 2015, 27(10): 2291-2298.