EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BS Dataset: A Tailor-Made Urban Road Pothole Dataset for Real-Time Detection and Safety-Oriented Monitoring

Roberto Benedetti iD, Valerio Bortolotto

Sensors · 20.08.2026 · 26 (16) · 5267

DOI: 10.3390/s26165267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.08.2026. Verfasst von Roberto Benedetti und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer, Control, and Management Engineering, Sapienza University of Rome, 00185 Roma, Italy. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bridgestone Europe NV/SA—Italian Branch Technical Center Europe.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road surface hazards remain a persistent concern for vehicle safety, passenger comfort, and the operational continuity of transport infrastructure. Among these hazards, potholes are particularly significant because they can cause tire damage, suspension wear, wheel misalignment, and sudden vehicle instability. In addition to direct mechanical damage, potholes may reduce driving comfort, increase maintenance costs, and degrade traffic efficiency in urban environments where roads are heavily used and rapidly deteriorate. For these reasons, the timely detection of potholes is an important requirement for road safety and infrastructure management. This work presents a tailor-made dataset for road pothole detection in urban environments, referred to as the Bridgestone Dataset (BS Dataset). The dataset was designed to support object detection from vehicle-mounted imagery collected from a test vehicle under realistic road conditions, thereby aligning the training data more closely with the target deployment scenario. The resulting dataset is intended to support real-time monitoring systems for road hazard detection and maintenance planning. The dataset was also designed as a multimodal resource. In addition to pothole bounding-box annotations, it provides accelerometer and GPS signals to characterize the vehicle dynamics during operation which might help identifying hazard severity and the potential risk to the vehicle. To collect the dataset, the authors developed a smartphone application, which supports the acquisition of both images and vehicle telemetry by leveraging the device’s internal sensors.

Schlagwörter

Stichwörter der Autor:innen

computer visiondeep learningmultimodal datasetpothole detectionroad monitoring

Autor:innen und Institutionen

  • Department of Computer, Control, and Management Engineering, Sapienza University of Rome, 00185 Roma, Italy.
  • Bridgestone Europe NV/SA-Italian Branch Technical Center Europe, Via del Fosso del Salceto 13/15, 00128 Rome, Italy.

ORCID-Profile: Roberto Benedetti

Förderung

  • Bridgestone Europe NV/SA—Italian Branch Technical Center Europe

Zitieren

APA

Benedetti, R., & Bortolotto, V. (2026). BS Dataset: A Tailor-Made Urban Road Pothole Dataset for Real-Time Detection and Safety-Oriented Monitoring. Sensors, 26(16), 5267. https://doi.org/10.3390/s26165267

Vancouver

Benedetti R, Bortolotto V. BS Dataset: A Tailor-Made Urban Road Pothole Dataset for Real-Time Detection and Safety-Oriented Monitoring. Sensors. 2026;26(16):5267. doi:10.3390/s26165267

BibTeX
@article{Benedetti2026,
  author = {Benedetti, Roberto and Bortolotto, Valerio},
  title = {BS Dataset: A Tailor-Made Urban Road Pothole Dataset for Real-Time Detection and Safety-Oriented Monitoring},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5267},
  doi = {10.3390/s26165267}
}
Kostenlos starten →