Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Abstract

Hyperspectral anomaly detection (HAD) is an important hyperspectral image application. HAD can find pixels with anomalous spectral signatures compared with their neighbor background without any prior information. While most of the existed researches related to statistic-based and distance-based techniques by summarizing the background samples with certain models and then finding the very few outliers by various of distance metrics, this review focuses on the HAD based on machine learning methods, which have witnessed remarkable progress in the recent years. In particular, these studies can generally be roughly grouped into the traditional machine learning and deep learning-based methods. Several representative HAD methods, including both traditional machine and deep learning-based methods, are then conducted on four real HSIs in the experiments. Finally, conclusions regarding HAD are summarized, and prospects and future development direction are discussed.

Robust Hyperspectral Anomaly Detection with Simultaneous Mixed Noise Removal via Constrained Convex Optimization

“…where Σ γ is a diagonal matrix whose diagonal elements are given by 5) Stepsize Choices for Each Background Characterization: Finally, we derive the choices of the stepsize γ B in Eq. (11) for each background characterization.…”

“…HS images have hundreds of rich spectral bands, including both visible and invisible bands, allowing us to identify the detailed information of the imaged targets. Therefore, many HS image analysis technologies, including classification, unmixing, and anomaly detection, have been studied [1]- [5].…”

Occluded object detection and exposure in cluttered environments with automated hyperspectral anomaly detection

“…Arisoy et al (2021) also utilized an autoencoder network in conjunction with a generative adversarial network (GAN) to identify anomalous pixels from their reconstruction error. Xu et al (2022) offers a comprehensive review of machine learning based approaches with added emphasis on deep methods. It is important to note that deep learning approaches are often difficult to introspect, creating adversity in troubleshooting and guaranteeing consistent behavior.…”

Prior-based collaborative representation with global adaptive weight for hyperspectral anomaly detection

“…On this basis, HSI interpretation techniques have been widely applied in many fields, such as classification, [2][3][4][5] change detection, [6][7][8][9] and object detection. [10][11][12] As an important subbranch of hyperspectral target location, hyperspectral anomaly detection (HAD) aims to distinguish objects of interest by capturing subtle spectral differences of ground objects without any prior information or supervision. 13,14 HAD has been widely applied in mineral exploration, 15 agriculture, 16 and other fields to monitor.…”

“…Compared with visible and multispectral imagery, hyperspectral images (HSIs) contain hundreds of continuous spectral bands that provide spectral-spatial information. On this basis, HSI interpretation techniques have been widely applied in many fields, such as classification, 2 – 5 change detection, 6 – 9 and object detection 10 – 12 As an important subbranch of hyperspectral target location, hyperspectral anomaly detection (HAD) aims to distinguish objects of interest by capturing subtle spectral differences of ground objects without any prior information or supervision 13 , 14 .…”