Vision-Based Deep Learning Algorithm for Detecting Potholes

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

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.

OriginalspracheEnglisch
Aufsatznummer012019
ZeitschriftJournal of Physics: Conference Series
Jahrgang2162
Anzahl der Seiten11
ISSN1742-6588
DOIs
PublikationsstatusErschienen - 25.01.2022
VeranstaltungInternational Conference on Applied Physics, Simulation and Computing - APSAC 2021 - Salerno, Italien
Dauer: 03.09.202105.09.2021
Konferenznummer: 5

Dokumente

DOI

Zuletzt angesehen

Publikationen

  1. Lyapunov stability analysis to set up a PI controller for a mass flow system in case of a non-saturating input
  2. Analyzing math teacher students' sensitivity for aspects of the complexity of problem oriented mathematics instruction
  3. Automated Invoice Processing: Machine Learning-Based Information Extraction for Long Tail Suppliers
  4. Identification of conductive fiber parameters with transcutaneous electrical nerve stimulation signal using RLS algorithm
  5. Continuous and Discrete Concepts for Detecting Transport Barriers in the Planar Circular Restricted Three Body Problem
  6. Can measurement errors explain variance in the relationship between muscle- and tendon stiffness and range of motion?—a blinded reliability and objectivity study
  7. Using EEG movement tagging to isolate brain responses coupled to biological movements
  8. Exploring the Unknown
  9. A luenberger observer for a quasi-static disturbance estimation in linear time invariant systems
  10. Dynamic capabilities and routinization
  11. Comparing Web-Based and Blended Training for Coping With Challenges of Flexible Work Designs
  12. Test of advanced hyperfine structure theory by precision radio-frequency and laser spectroscopy in molybdenum
  13. Sharing in Christ's rule
  14. Effect of erbium modification on the microstructure, mechanical and corrosion characteristics of binary Mg-Al alloys
  15. Approximate tree kernels
  16. Collaborative design prototyping in transdisciplinary research
  17. End-to-End Active Speaker Detection
  18. Reconfiguring Desecuritization
  19. Individual differences and cognitive load theory
  20. Assessing authenticity in modelling test items: deriving a theoretical model
  21. Properties of some overlapping self-similar and some self-affine measures
  22. General Patterns and Conclusions
  23. Explaining the (Non-) Adoption of Advanced Data Analytics in Auditing

Presse / Medien

  1. Orchester ohne Dirigent