Comparison of Anomaly Detection Methods on Event-Based Vision Sensor Data in a High Noise Environment

Authors

• Will Johnston, Air Force Institute of Technology
• Anthony L. Franz, Center for Technical Intelligence Studies and Research, Air Force Institute of TechnologyFollow
• Shannon R. Young, Center for Technical Intelligence Studies and Research, Air Force Institute of TechnologyFollow
• Rachel Oliver, Air Force Institute of Technology
• Zachary Theis, Space Vehicles Directorate, Air Force Research Laboratory
• Brian McReynolds, United States Air Force Academy
• Michael L. Dexter, Center for Technical Intelligence Studies and Research, Air Force Institute of TechnologyFollow

Document Type

Article

Publication Date

4-9-2026

Abstract

Event-based vision sensors (EVSs) provide unique frequency analysis opportunities due to their event data output and high temporal resolution. Anomaly detection methods used in hyperspectral analysis can be used on the event frequency spectra to detect targets. However, the introduction of a strong, flickering interfering source can reduce the EVS sensitivity and obscure targets of interest. Previous work presented a method showing that targets could still be detected through an overwhelming source using frequency analysis, background suppression, and statistical filtering. This paper extends that research and compares the ability of five different eigenanalysis anomaly detection methods (principal component background suppression (PCBS) with peak threshold detection, Mahalanobis distance (MD) detector, complementary subspace detector (CSD), Reed–Xiaoli (RX) detector, and subspace Reed–Xiaoli (SSRX) detector) to detect targets in a high noise environment. The PCBS, MD, and CSD detectors performed well and were able to detect the targets through the overwhelming source. The PCBS detector had the best performance at low false-alarm rates (a > 400% detection probability increase at a false-alarm probability of 10⁻⁵). While the MD and CSD detectors had the best detection at higher false-alarm probabilities (approximately 7 × 10⁻²), the MD detector had a sub-second execution time. Depending on the application, the PCBS or MD detector are the best choice out of these five methods to detect targets in this type of high noise environment.

Comments

© 2026 by the authors.   Licensee MDPI, Basel, Switzerland.

  This article is published by MDPI, licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Sourced from the published version of record cited below. 

DOI

10.3390/s26082320

Source Publication

Sensors (eISSN 1424-8220)

Recommended Citation

Johnston, W., Franz, A., Young, S., Oliver, R., Theis, Z., McReynolds, B., & Dexter, M. (2026). Comparison of anomaly detection methods on event-based vision sensor data in a high noise environment. Sensors, 26(8), 2320. https://doi.org/10.3390/s26082320