摘要
高光谱图像异常检测作为一种无监督的目标检测,主要存在异常目标类型多样化、异常与背景不易区分、以及检测精度受场景影响大等难题。针对以上问题,本文提出了一种基于空谱多路自编码器的高光谱图像异常检测方法。首先,提出一种加权空谱Gabor滤波方法,提取高光谱图像的多尺度空谱特征;其次,采用多路自编码器降低多尺度空谱特征在光谱维的冗余度,提取空谱特征中的主要信息;最后,利用得到的主要空谱特征,结合形态学滤波与双曲正切函数进行特征增强,以提高异常与背景噪声的区分度。本文提出的方法是一种即插即用的异常检测方法,无需额外的参数输入;多路自编码器提取了多尺度主要空谱特征,以应对异常目标类型多样化的难题;通过特征增强提高了背景与异常的区分度。将本文提出的方法与9种流行的异常检测方法相比,在5个高光谱数据集上进行验证,通过对比异常检测结果图、接收机操作特性(Receiver Operating Characteristic,ROC)曲线、ROC曲线下覆盖的面积AUC(Area Under Curve)以及异常像元与背景像元的箱型图等评价指标,证明了本文方法优于其他9种方法。
Hyperspectral anomaly detection is a type of unsupervised target detection that is crucial in the national economy and attracts the attention of numerous researchers.However,hyperspectral anomaly detection faces several challenges,such as diversified anomaly targets,difficulty in distinguishing anomalies from the background,and low detection accuracy.A hyperspectral anomaly detection method based on multichannel autoencoders is proposed to form a high-dimensional spatial-spectral feature space to address the above challenges.First,weighted spatial-spectral Gabor kernels with different scales and directions are proposed to extract the spatial-spectral features from hyperspectral images.These Gabor kernels are then redefined to increase the gap between the central and surrounding values in the kernels.The spatial-spectral features are extracted by weighted spatial-spectral Gabor kernels to form a high-dimensional spatial-spectral feature space.Second,multichannel autoencoders reduce the redundancy of multiscale spatial-spectral features in spectral dimension,extract the principal features from high-dimensional spatial-spectral feature space,and transform them into the principal feature representation space.Finally,a feature enhancement method based on hyperbolic tangent function and morphological filters is proposed to improve the distinction between abnormal targets and background noise and address the background noise in the spatial dimension.Mahalanobis distance is used to detect anomalies in the enhanced principal feature representation space.The proposed method is compared with nine state-of-the-art anomaly detection methods on five hyperspectral data sets.Anomaly Detection Maps(ADMs),Receiver Operating Characteristics(ROCs),Area Under Curves(AUCs),and box plots between abnormal and background pixels are used to evaluate the performance of the compared methods.AUC is a quantitative evaluation method,and the others are qualitative evaluation methods.The anomaly detection maps obtained by the proposed method eas
作者
贾森
刘宽
徐萌
朱家松
JIA Sen;LIU Kuan;XU Meng;ZHU Jiasong(Shenzhen University,College of Computer Science and Software Engineering,Shenzhen 518060,China;Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources,Shenzhen 518060,China;Guangdong-Hong Kong-Macao Joint Laboratory for Smart Cities,Shenzhen 518060,China)
出处
《遥感学报》
EI
CSCD
北大核心
2024年第1期55-68,共14页
NATIONAL REMOTE SENSING BULLETIN
基金
国家自然科学基金(编号:62271327,41971300,42271336)
广东省基础与应用基础研究基金(编号:2022A1515011290,2021A1515011413)
深圳市科技计划(编号:RCJC20221008092731042,JCYJ20220818100206015,KQTD20200909113951005)。
关键词
高光谱图像
异常检测
多路自编码器
加权空谱Gabor
双曲正切函数
特征增强
hyperspectral image
anomaly detection
multichannel autoencoders
weighted spatial-spectral Gabor
hyperbolic tangent function
feature enhancement method
