基于孪生特征融合的弱监督学习高光谱异常探测
Hyperspectral Anomaly Detection Using a Siamese Spatial Feature with Weakly Supervised Learning
周晓忠 1刘军廷 1周海涛1
作者信息
- 1. 宁波冶金勘察设计研究股份有限公司,浙江 宁波 315194
- 折叠
摘要
高光谱异常检测以无监督方式分析光谱数据中的背景与异常目标.然而,高光谱背景的复杂分布以及训练样本中异常目标的存在,给模型的泛化性和应用能力带来挑战.基于此,提出一种样本自学习与孪生特征融合的检测网络(S2FDNet).首先,基于测度K-means的异常背景类别搜索算法,以弱监督方式学习背景与异常粗略标签.然后,以孪生光谱与空间特征提取框架,设计了全局-局部光谱特征提取模块与多尺度空间特征提取模块,提升对背景与异常特征的高维判别能力.模型以弱监督训练模式更新异常与背景样本集与模型参数,测试阶段直接利用预测概率检测异常.采用两个高光谱数据验证S2FDNet算法性能,结果表明,所提算法可有效检测异常目标,提升了背景与异常的可分性.
Abstract
Hyperspectral anomaly detection processes background and anomalous targets in spectral data using an unsupervised approach.However,the complex nature of hyperspectral background distributions and the presence of anomalous targets in the training samples challenge the model's generalization and application capabilities.To address this issue,we propose the S2FDNet detection network that integrates sample self-learning with dual feature fusion.First,an anomaly background category search algorithm based on measure K-means was employed to classify the background and anomaly rough labels under weak supervision.A dual spectral and spatial feature extraction framework,including a global-local spectral feature extraction module and a multiscale spatial feature extraction module,was then employed to enhance the discriminative capacity for background and anomalous features across high-dimensional spaces.The model underwent updates to abnormal and background sample sets and model parameters during the weakly supervised training mode,and anomalies were directly detected using predicted probabilities during testing.Evaluations with two hyperspectral datasets confirm that S2FDNet algorithm effectively identifies anomalous targets and improves the distinction between background and anomalies.
关键词
高光谱异常检测/弱监督学习/孪生网络/空谱特征提取Key words
hyperspectral anomaly detection/weakly supervised learning/Siamese network/spatial spectral feature extraction引用本文复制引用
出版年
2024
NETL
NSTL
万方数据