EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Spiking Neural Networks in Imaging: A Review and Case Study

Michael Voudaskas, Jack Iain MacLean iD, Neale A W Dutton iD, Brian D Stewart, Istvan Gyongy

Sensors · 04.11.2025 · 25 (21) · 6747

DOI: 10.3390/s25216747 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 04.11.2025. Verfasst von Michael Voudaskas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Integrated Micro and Nano Systems, The University of Edinburgh, Edinburgh EH9 3BF, UK. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 112 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: STMicroelectronics, Scottish Research Partnership in Engineering, UKRI EPSRC Centre for Doctoral Training in Applied Photonics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This review examines the state of spiking neural networks (SNNs) for imaging, combining a structured literature survey, a comparative meta-analysis of reported datasets, training strategies, hardware platforms, and applications and a case study on LMU-based depth estimation in direct Time-of-Flight (dToF) imaging. While SNNs demonstrate promise for energy-efficient, event-driven computation, current progress is constrained by reliance on small or custom datasets, ANN-SNN conversion inefficiencies, simulation-based hardware evaluation, and a narrow focus on classification tasks. The analysis highlights scaling trade-offs between accuracy and efficiency, persistent latency bottlenecks, and limited sensor–hardware integration. These findings were synthesised into key challenges and future directions, emphasising benchmarks, hardware-aware training, ecosystem development, and broader application domains.

Schlagwörter

Stichwörter der Autor:innen

Legendre memory unitimagingneural networkneuromorphic engineeringreviewspiking neural networktime of flight

Autor:innen und Institutionen

  • Institute for Integrated Micro and Nano Systems, The University of Edinburgh, Edinburgh EH9 3BF, UK.
  • STMicroelectronics Imaging Division, Edinburgh EH3 5DA, UK.

ORCID-Profile: Jack Iain MacLean, Neale A W Dutton

Förderung

  • STMicroelectronics
  • Scottish Research Partnership in Engineering
  • UKRI EPSRC Centre for Doctoral Training in Applied Photonics

Zitieren

APA

Voudaskas, M., MacLean, J. I., Dutton, N. A. W., Stewart, B. D., & Gyongy, I. (2025). Spiking Neural Networks in Imaging: A Review and Case Study. Sensors, 25(21), 6747. https://doi.org/10.3390/s25216747

Vancouver

Voudaskas M, MacLean JI, Dutton NAW, Stewart BD, Gyongy I. Spiking Neural Networks in Imaging: A Review and Case Study. Sensors. 2025;25(21):6747. doi:10.3390/s25216747

BibTeX
@article{Voudaskas2025,
  author = {Voudaskas, Michael and MacLean, Jack Iain and Dutton, Neale A W and Stewart, Brian D and Gyongy, Istvan},
  title = {Spiking Neural Networks in Imaging: A Review and Case Study},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6747},
  doi = {10.3390/s25216747}
}
Kostenlos starten →