EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model

Mishuk Majumder, Chester Wilmot

Journal of Imaging · 27.06.2023 · 9 (7) · 131

DOI: 10.3390/jimaging9070131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 27.06.2023. Verfasst von Mishuk Majumder und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil & Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USA. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Louisiana Department of Transportation and Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Different techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In terms of accuracy and flexible interval counting, the adequacy of existing research on employing the model for vehicle counting from video footage is unlikely sufficient. The present study endeavors to develop computer algorithms for automated traffic counting from pre-recorded videos using the YOLO model with flexible interval counting. The study involves the development of algorithms aimed at detecting, tracking, and counting vehicles from pre-recorded videos. The YOLO model was applied in TensorFlow API with the assistance of OpenCV. The developed algorithms implement the YOLO model for counting vehicles in two-way directions in an efficient way. The accuracy of the automated counting was evaluated compared to the manual counts, and was found to be about 90 percent. The accuracy comparison also shows that the error of automated counting consistently occurs due to undercounting from unsuitable videos. In addition, a benefit–cost (B/C) analysis shows that implementing the automated counting method returns 1.76 times the investment.

Schlagwörter

Stichwörter der Autor:innen

OpenCVTensorFlowYou Only Look Once (YOLO)accuracy of automated traffic countingautomated vehicle countingbenefit–cost (B/C) analysisobject detectionpre-recorded video

Autor:innen und Institutionen

  • Department of Civil & Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.

Förderung

  • Louisiana Department of Transportation and Development

Zitieren

APA

Majumder, M., & Wilmot, C. (2023). Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model. Journal of Imaging, 9(7), 131. https://doi.org/10.3390/jimaging9070131

Vancouver

Majumder M, Wilmot C. Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model. Journal of Imaging. 2023;9(7):131. doi:10.3390/jimaging9070131

BibTeX
@article{Majumder2023,
  author = {Majumder, Mishuk and Wilmot, Chester},
  title = {Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model},
  journal = {Journal of Imaging},
  year = {2023},
  volume = {9},
  number = {7},
  pages = {131},
  doi = {10.3390/jimaging9070131}
}
Kostenlos starten →