EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking 2D Multi-Object Detection and Tracking Algorithms in Autonomous Vehicle Driving Scenarios

Diego Gragnaniello iD, Antonio Greco iD, Alessia Saggese iD, Mario Vento iD, Antonio Vicinanza iD

Sensors · 16.04.2023 · 23 (8) · 4024

DOI: 10.3390/s23084024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.04.2023. Verfasst von Diego Gragnaniello und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, 84084 Fisciano, Italy. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-driving vehicles must be controlled by navigation algorithms that ensure safe driving for passengers, pedestrians and other vehicle drivers. One of the key factors to achieve this goal is the availability of effective multi-object detection and tracking algorithms, which allow to estimate position, orientation and speed of pedestrians and other vehicles on the road. The experimental analyses conducted so far have not thoroughly evaluated the effectiveness of these methods in road driving scenarios. To this aim, we propose in this paper a benchmark of modern multi-object detection and tracking methods applied to image sequences acquired by a camera installed on board the vehicle, namely, on the videos available in the BDD100K dataset. The proposed experimental framework allows to evaluate 22 different combinations of multi-object detection and tracking methods using metrics that highlight the positive contribution and limitations of each module of the considered algorithms. The analysis of the experimental results points out that the best method currently available is the combination of ConvNext and QDTrack, but also that the multi-object tracking methods applied on road images must be substantially improved. Thanks to our analysis, we conclude that the evaluation metrics should be extended by considering specific aspects of the autonomous driving scenarios, such as multi-class problem formulation and distance from the targets, and that the effectiveness of the methods must be evaluated by simulating the impact of the errors on driving safety.

Schlagwörter

Stichwörter der Autor:innen

BDD100Kautonomous vehicle drivingdeep learningmultiple object tracking (MOT)

Autor:innen und Institutionen

  • Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, 84084 Fisciano, Italy.

ORCID-Profile: Diego Gragnaniello, Antonio Greco, Alessia Saggese, Mario Vento, Antonio Vicinanza

Zitieren

APA

Gragnaniello, D., Greco, A., Saggese, A., Vento, M., & Vicinanza, A. (2023). Benchmarking 2D Multi-Object Detection and Tracking Algorithms in Autonomous Vehicle Driving Scenarios. Sensors, 23(8), 4024. https://doi.org/10.3390/s23084024

Vancouver

Gragnaniello D, Greco A, Saggese A, Vento M, Vicinanza A. Benchmarking 2D Multi-Object Detection and Tracking Algorithms in Autonomous Vehicle Driving Scenarios. Sensors. 2023;23(8):4024. doi:10.3390/s23084024

BibTeX
@article{Gragnaniello2023,
  author = {Gragnaniello, Diego and Greco, Antonio and Saggese, Alessia and Vento, Mario and Vicinanza, Antonio},
  title = {Benchmarking 2D Multi-Object Detection and Tracking Algorithms in Autonomous Vehicle Driving Scenarios},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {8},
  pages = {4024},
  doi = {10.3390/s23084024}
}
Kostenlos starten →