EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos

Yves Berviller iD, Masoomeh Shireen Ansarnia, Etienne Tisserand iD, Patrick Schweitzer, Alain Tremeau

Sensors · 27.02.2023 · 23 (5) · 2637

DOI: 10.3390/s23052637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.02.2023. Verfasst von Yves Berviller und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institut Jean Lamour, Université de Lorraine, UMR7198, F-54052 Nancy, France. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we present a deep learning processing flow aimed at Advanced Driving Assistance Systems (ADASs) for urban road users. We use a fine analysis of the optical setup of a fisheye camera and present a detailed procedure to obtain Global Navigation Satellite System (GNSS) coordinates along with the speed of the moving objects. The camera to world transform incorporates the lens distortion function. YOLOv4, re-trained with ortho-photographic fisheye images, provides road user detection. All the information extracted from the image by our system represents a small payload and can easily be broadcast to the road users. The results show that our system is able to properly classify and localize the detected objects in real time, even in low-light-illumination conditions. For an effective observation area of 20 m × 50 m, the error of the localization is in the order of one meter. Although an estimation of the velocities of the detected objects is carried out by offline processing with the FlowNet2 algorithm, the accuracy is quite good, with an error below one meter per second for urban speed range (0 to 15 m/s). Moreover, the almost ortho-photographic configuration of the imaging system ensures that the anonymity of all street users is guaranteed.

Schlagwörter

Stichwörter der Autor:innen

ADASI2Vcamera to world transformdeep learningreal time

Autor:innen und Institutionen

  • Institut Jean Lamour, Université de Lorraine, UMR7198, F-54052 Nancy, France.
  • Independent Researcher, F-57155 Marly, France.

ORCID-Profile: Yves Berviller, Etienne Tisserand

Zitieren

APA

Berviller, Y., Ansarnia, M. S., Tisserand, E., Schweitzer, P., & Tremeau, A. (2023). Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos. Sensors, 23(5), 2637. https://doi.org/10.3390/s23052637

Vancouver

Berviller Y, Ansarnia MS, Tisserand E, Schweitzer P, Tremeau A. Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos. Sensors. 2023;23(5):2637. doi:10.3390/s23052637

BibTeX
@article{Berviller2023,
  author = {Berviller, Yves and Ansarnia, Masoomeh Shireen and Tisserand, Etienne and Schweitzer, Patrick and Tremeau, Alain},
  title = {Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2637},
  doi = {10.3390/s23052637}
}
Kostenlos starten →