EUVIMEDEUVIMED entdecken
Crossref

Video-Based Vehicle Speed Measurement Using Recurrent All-Pairs Field Transforms for Optical Flow

Huizhi Xu, Dongsheng Hao, Shuang Chen

IEEE Sensors Journal · 15.07.2024 · 24 (14) · 22945-22957

DOI: 10.1109/jsen.2024.3406592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.07.2024. Verfasst von Huizhi Xu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the intricate urban road scenarios, the algorithm for vehicle speed measurement based on image sensors encounters challenges of low precision. Often, a confluence of video and radar solutions is employed, impeding large-scale applications in the engineering domain. By amalgamating deep learning algorithms and camera imaging principle, a speed measurement algorithm was crafted that integrates scene and object features. Initially, the YOLOv5s object detection model was employed and refined the model’s backbone and loss function to elevate the precision of vehicle detection. Subsequently, in conjunction with the recurrent all-pairs field transforms (RAFT) algorithm and camera imaging principle, the geometric relationship between road scenes and images was established, deriving vehicle speed based on the coordinates of vehicle’s feature points. Furthermore, a vehicle dataset was curated to train and assess the improved YOLOv5s model. Finally, employing an experimental vehicle traversed the designated video detection section at five constant speeds, to validate the efficacy of the speed measurement algorithm. The experimental results illustrate that, in comparison to the original model on the self-established dataset, the improved YOLOv5s demonstrates the enhancements of 1.7% and 1.4% in mAP@0.5 and mAP@0.5:0.95, respectively. The mean absolute error and the root-mean-square error for all speed measurement values are 1.95 and 2.38 km/h, respectively. In summary, this algorithm is applicable to vehicle speed measurement tasks in complex traffic environments, showcasing better precision.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xu, H., Hao, D., & Chen, S. (2024). Video-Based Vehicle Speed Measurement Using Recurrent All-Pairs Field Transforms for Optical Flow. IEEE Sensors Journal, 24(14), 22945-22957. https://doi.org/10.1109/jsen.2024.3406592

Vancouver

Xu H, Hao D, Chen S. Video-Based Vehicle Speed Measurement Using Recurrent All-Pairs Field Transforms for Optical Flow. IEEE Sensors Journal. 2024;24(14):22945-22957. doi:10.1109/jsen.2024.3406592

BibTeX
@article{Xu2024,
  author = {Xu, Huizhi and Hao, Dongsheng and Chen, Shuang},
  title = {Video-Based Vehicle Speed Measurement Using Recurrent All-Pairs Field Transforms for Optical Flow},
  journal = {IEEE Sensors Journal},
  year = {2024},
  volume = {24},
  number = {14},
  pages = {22945--22957},
  doi = {10.1109/jsen.2024.3406592}
}
Kostenlos starten →