ERX: A Fast Real-Time Anomaly Detection Algorithm for Hyperspectral Line Scanning

Detecting unexpected objects (anomalies) in real time has great potential for monitoring, managing, and protecting the environment. Hyperspectral line-scan cameras are a low-cost solution that enhances confidence in anomaly detection over red-green-blue (RGB) and multispectral imagery. However, exis...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on geoscience and remote sensing Ročník 63; s. 1 - 17
Hlavní autori: Garske, Samuel, Evans, Bradley, Artlett, Christopher, Wong, K. C.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Adaptability
Adaptive algorithms
Algorithms
Anomalies
Anomaly detection
Australia
Cameras
Computers
Covariance matrices
Datasets
Distortion
Drones
Edge computing
Environmental protection
Field tests
hyperspectral
Hyperspectral imaging
line scanning
Real time
Real-time systems
Reviews
Robustness
Satellites
Scanning
Small satellites
unsupervised learning
ISSN:0196-2892, 1558-0644
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Detecting unexpected objects (anomalies) in real time has great potential for monitoring, managing, and protecting the environment. Hyperspectral line-scan cameras are a low-cost solution that enhances confidence in anomaly detection over red-green-blue (RGB) and multispectral imagery. However, existing line-scan algorithms are too slow when using small computers (e.g., those onboard a drone or small satellite), do not adapt to changing scenery, or lack robustness against geometric distortions. This article introduces the exponentially moving Reed-Xiaoli (ERX) algorithm to address these issues, and compares it with four existing Reed-Xiaoli (RX)-based anomaly detection methods for hyperspectral line scanning. Three large and more complex datasets are also introduced to better assess the practical challenges when using line-scan cameras (two hyperspectral and one multispectral). ERX is evaluated using a Jetson Xavier NX edge computing module (six-core CPU, 8-GB RAM, and 20-W power draw), achieving the best combination of speed and detection performance. ERX was nine times faster than the next-best algorithm on the dataset with the highest number of bands (108 bands), with an average speed of 561 lines per second on the Jetson. It achieved a 29.3% area under each receiver operating characteristic (ROC) curve (AUC) improvement over the next-best algorithm on the most challenging dataset, while showing greater adaptability through consistently high AUC scores regardless of the camera's starting location. ERX performed robustly across all datasets, achieving an AUC of 0.941 on a drone-collected hyperspectral line scan dataset without geometric corrections (a 16.9% improvement over existing algorithms). This work enables the future research on the detection of anomalous objects in real time, adaptive and automatic threshold selection, and real-time field tests. The datasets and the Python code are openly available at: https://github.com/WiseGamgee/HyperAD , promoting accessibility and future work.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2025.3532225