EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OPTIMIZING PEDESTRIAN TRACKING FOR ROBUST PERCEPTION WITH YOLOv8 AND DEEPSORT

Ghania Zidani, Djalal DJARAH, Abdslam BENMAKHLOUF, Laid KHETTACHE

Applied Computer Science · 30.03.2024 · 20 (1) · 72-84

DOI: 10.35784/acs-2024-05 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Computer Science, online erschienen am 30.03.2024. Verfasst von Ghania Zidani und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-object tracking is a crucial aspect of perception in the area of computer vision, widely used in autonomous driving, behavior recognition, and other areas. The complex and dynamic nature of environments, the ever-changing visual features of people, and the frequent appearance of occlusion interactions all impose limitations on the efficacy of existing pedestrian tracking algorithms. This results in suboptimal tracking precision and stability. As a solution, this article proposes an integrated detector-tracker framework for pedestrian tracking. The framework includes a pedestrian object detector that utilizes the YOLOv8 network, which is regarded as the latest state-of-the-art detector, that has been established. This detector provides an ideal detection base to address limitations. Through the combination of YOLOv8 and the DeepSort tracking algorithm, we have improved the ability to track pedestrians in dynamic scenarios. After conducting experiments on publicly available datasets such as MOT17 and MOT20, a clear improvement in accuracy and consistency was demonstrated, with MOTA scores of 63.82 and 58.95, and HOTA scores of 43.15 and 41.36, respectively. Our research highlights the significance of optimizing object detection to unleash the potential of tracking for critical applications like autonomous driving.

Zitieren

APA

Zidani, G., DJARAH, D., BENMAKHLOUF, A., & KHETTACHE, L. (2024). OPTIMIZING PEDESTRIAN TRACKING FOR ROBUST PERCEPTION WITH YOLOv8 AND DEEPSORT. Applied Computer Science, 20(1), 72-84. https://doi.org/10.35784/acs-2024-05

Vancouver

Zidani G, DJARAH D, BENMAKHLOUF A, KHETTACHE L. OPTIMIZING PEDESTRIAN TRACKING FOR ROBUST PERCEPTION WITH YOLOv8 AND DEEPSORT. Applied Computer Science. 2024;20(1):72-84. doi:10.35784/acs-2024-05

BibTeX
@article{Zidani2024,
  author = {Zidani, Ghania and DJARAH, Djalal and BENMAKHLOUF, Abdslam and KHETTACHE, Laid},
  title = {OPTIMIZING PEDESTRIAN TRACKING FOR ROBUST PERCEPTION WITH YOLOv8 AND DEEPSORT},
  journal = {Applied Computer Science},
  year = {2024},
  volume = {20},
  number = {1},
  pages = {72--84},
  doi = {10.35784/acs-2024-05}
}
Kostenlos starten →