EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Will Johnston iD, Anthony Franz, Shannon Young iD, Rachel Oliver, Zachry Theis, Brian McReynolds iD, Michael Dexter

Sensors · 09.04.2026 · 26 (8) · 2320

DOI: 10.3390/s26082320 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2026. Verfasst von Will Johnston und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering Physics, Air Force Institute of Technology, 2950 Hobson Way, Fairborn, OH 45433, USA. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Air Force Research Laboratory Space Vehicles Directorate, Space Vehicles Directorate, Air Force Research Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

Mahalanobis distance detector distance detectorReed–Xiaoli detectoranomaly detectioncomplementary subspace detectordynamic vision sensorevent-based vision sensorfrequency analysishigh noise environmenthyperspectral analysisneuromorphic cameraprincipal component background suppression

Autor:innen und Institutionen

  • Department of Engineering Physics, Air Force Institute of Technology, 2950 Hobson Way, Fairborn, OH 45433, USA.
  • Center for Technical Intelligence Studies and Research, Air Force Institute of Technology, 2950 Hobson Way, Fairborn, OH 45433, USA.
  • Department of Aeronautics and Astronautics, Air Force Institute of Technology, 2950 Hobson Way, Fairborn, OH 45433, USA.
  • Space Vehicles Directorate, Air Force Research Laboratory, 3550 Aberdeen Ave SE, Albuquerque, NM 87117, USA.
  • Department of Physics and Meteorology, United States Air Force Academy, 2354 Fairchild Drive United States Air Force Academy, Colorado Springs, CO 80840, USA.

ORCID-Profile: Will Johnston, Shannon Young, Brian McReynolds

Förderung

  • U.S. Air Force Research Laboratory Space Vehicles Directorate
  • Space Vehicles Directorate, Air Force Research Laboratory

Zitieren

APA

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

Vancouver

Johnston W, Franz A, Young S, Oliver R, Theis Z, McReynolds B, et al. Comparison of Anomaly Detection Methods on Event-Based Vision Sensor Data in a High Noise Environment. Sensors. 2026;26(8):2320. doi:10.3390/s26082320

BibTeX
@article{Johnston2026,
  author = {Johnston, Will and Franz, Anthony and Young, Shannon and Oliver, Rachel and Theis, Zachry and McReynolds, Brian and Dexter, Michael},
  title = {Comparison of Anomaly Detection Methods on Event-Based Vision Sensor Data in a High Noise Environment},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2320},
  doi = {10.3390/s26082320}
}
Kostenlos starten →