Vision-Based Deep Learning Algorithm for Detecting Potholes

Research output: Journal contributionsConference article in journalResearchpeer-review

Standard

Vision-Based Deep Learning Algorithm for Detecting Potholes. / Gajjar, Kanushka; Niekerk, T. Van; Wilm, Thomas et al.
In: Journal of Physics: Conference Series, Vol. 2162, 012019, 25.01.2022.

Research output: Journal contributionsConference article in journalResearchpeer-review

Harvard

APA

Vancouver

Gajjar K, Niekerk TV, Wilm T, Mercorelli P. Vision-Based Deep Learning Algorithm for Detecting Potholes. Journal of Physics: Conference Series. 2022 Jan 25;2162:012019. doi: 10.1088/1742-6596/2162/1/012019

Bibtex

@article{d82b640921de4768bbf6625d19feab9a,
title = "Vision-Based Deep Learning Algorithm for Detecting Potholes",
abstract = "Potholes on roads pose a major threat to motorists. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836 s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes. ",
keywords = "Engineering",
author = "Kanushka Gajjar and Niekerk, {T. Van} and Thomas Wilm and Paolo Mercorelli",
year = "2022",
month = jan,
day = "25",
doi = "10.1088/1742-6596/2162/1/012019",
language = "English",
volume = "2162",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",
publisher = "IOP Publishing Ltd",
note = "International Conference on Applied Physics, Simulation and Computing - APSAC 2021 ; Conference date: 03-09-2021 Through 05-09-2021",

}

RIS

TY - JOUR

T1 - Vision-Based Deep Learning Algorithm for Detecting Potholes

AU - Gajjar, Kanushka

AU - Niekerk, T. Van

AU - Wilm, Thomas

AU - Mercorelli, Paolo

N1 - Conference code: 5

PY - 2022/1/25

Y1 - 2022/1/25

N2 - Potholes on roads pose a major threat to motorists. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836 s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

AB - Potholes on roads pose a major threat to motorists. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836 s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85124945075&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/2162/1/012019

DO - 10.1088/1742-6596/2162/1/012019

M3 - Conference article in journal

AN - SCOPUS:85124945075

VL - 2162

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

M1 - 012019

T2 - International Conference on Applied Physics, Simulation and Computing - APSAC 2021

Y2 - 3 September 2021 through 5 September 2021

ER -

Documents

DOI

Recently viewed

Publications

  1. Die Energieversorgung in Deutschland und die Rolle der Steinkohle
  2. Boltanski/Chiapello: Ein feministischer Geist im neuen Kapitalismus?
  3. Springback compensation by superposition of stress in air bending
  4. Gegenöffentlichkeit(en) und partizipativer Journalismus im Internet
  5. The case of a proposed 21.5 MWe biomass gasifier in Winkleigh, Devon
  6. Die Bedeutung von Anspruchsgruppen bei Nachfolgeexistenzgründungen
  7. Von Trollen, Zauberern, der MACHT und anderen wundersamen Abenteuern
  8. Forest-specific diversity of vascular plants, bryophytes, and lichens
  9. Der Einsatz von Projektmanagement im Rahmen der Kooperationspraxis
  10. Lagrangian structures and transport in turbulent magnetized plasmas
  11. Was wir noch zu sagen hätten - Briefe an unsere Leserinnen und Leser
  12. Auswirkungen der Arbeitsbeziehung auf das Personalmanagement in KMU
  13. America's army and the military recruitment and management of 'talent'
  14. Exports and Firm Characteristics in German Manufacturing Industries
  15. Thesen zur Förderung nachhaltigen Konsums in Bildungseinrichtungen
  16. Motivations of Global Careers Among Expatriates in German Companies
  17. Quasi-in-situ observation of microstructure at the friction interface
  18. Recent Capital Market Regulatory Developments in Germany and the EU
  19. Marina F. Bykova, Kenneth R. Westphal (Hrsg.) The Palgrave Hegel Handbook
  20. Konstitutionalisierung und Normativität der europäischen Grundrechte
  21. Networking als zentrale Schlüsselqualifikation für Gründungsvorhaben
  22. Zum bildenden Potenzial experimenteller und künstlerischer Kurzfilme
  23. Entwicklung von Instrumenten zur Vermeidung von Lebensmittelabfällen
  24. Fortführung der EU-Agrarpolitk unter dem Paradigma der Nachhaltigkeit
  25. Kaufrecht und Werkvertragsrecht – ein systematischer Vergleich (Teil 1)
  26. Depression-specific Costs and their Factors based on SHI Routine data
  27. Photooxidation as Advanced Oxidation Treatment of Hospital Effluents
  28. Young people called "unaccompanied minors" and European welfare states
  29. Linking biodiversity and ecosystem service science to societal actors