EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Filtering Empty Video Frames for Efficient Real-Time Object Detection

Yu Liu, Kyoung-Don Kang iD

Sensors · 10.05.2024 · 24 (10) · 3025

DOI: 10.3390/s24103025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.05.2024. Verfasst von Yu Liu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, State University of New York at Binghamton, 4400 Vestal Parkway East, Vestal, NY 13850, USA. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning models have significantly improved object detection, which is essential for visual sensing. However, their increasing complexity results in higher latency and resource consumption, making real-time object detection challenging. In order to address the challenge, we propose a new lightweight filtering method called L-filter to predict empty video frames that include no object of interest (e.g., vehicles) with high accuracy via hybrid time series analysis. L-filter drops those frames deemed empty and conducts object detection for nonempty frames only, significantly enhancing the frame processing rate and scalability of real-time object detection. Our evaluation demonstrates that L-filter improves the frame processing rate by 31–47% for a single traffic video stream compared to three standalone state-of-the-art object detection models without L-filter. Additionally, L-filter significantly enhances scalability; it can process up to six concurrent video streams in one commodity GPU, supporting over 57 fps per stream, by working alongside the fastest object detection model among the three models.

Schlagwörter

Stichwörter der Autor:innen

filteringframe processing ratelong short-term memoryreal-time object detectionscalability

Autor:innen und Institutionen

  • Department of Computer Science, State University of New York at Binghamton, 4400 Vestal Parkway East, Vestal, NY 13850, USA.

ORCID-Profile: Kyoung-Don Kang

Förderung

  • National Science Foundation

Zitieren

APA

Liu, Y., & Kang, K. D. (2024). Filtering Empty Video Frames for Efficient Real-Time Object Detection. Sensors, 24(10), 3025. https://doi.org/10.3390/s24103025

Vancouver

Liu Y, Kang KD. Filtering Empty Video Frames for Efficient Real-Time Object Detection. Sensors. 2024;24(10):3025. doi:10.3390/s24103025

BibTeX
@article{Liu2024,
  author = {Liu, Yu and Kang, Kyoung-Don},
  title = {Filtering Empty Video Frames for Efficient Real-Time Object Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {10},
  pages = {3025},
  doi = {10.3390/s24103025}
}
Kostenlos starten →