Vision-Based Deep Learning Algorithm for Detecting Potholes

Research output: Journal contributionsConference article in journalResearchpeer-review

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.

Original languageEnglish
Article number012019
JournalJournal of Physics: Conference Series
Volume2162
Number of pages11
ISSN1742-6588
DOIs
Publication statusPublished - 25.01.2022
EventInternational Conference on Applied Physics, Simulation and Computing - APSAC 2021 - Salerno, Italy
Duration: 03.09.202105.09.2021
Conference number: 5

Documents

DOI

Recently viewed

Publications

  1. Learning with animations and simulations in a computer-based learning environment about torques
  2. Entropy-guided feature generation for structured learning of Portuguese dependency parsing
  3. Using Natural Language Processing Techniques to Tackle the Construct Identity Problem in Information Systems Research
  4. The Use of Genetic Algorithm for PID Controller Auto-Tuning in ARM CORTEX M4 Platform
  5. Evolutionary generation of dispatching rule sets for complex dynamic scheduling problems
  6. Modelling tasks—The relation between linguistic skills, intra-mathematical skills, and context-related prior knowledge
  7. Algebraic combinatorics in mathematical chemistry. Methods and algorithms. I. Permutation groups and coherent (cellular) algebras.
  8. Ant colony optimization algorithm and artificial immune system applied to a robot route
  9. Development of a Didactic Graphical Simulation Interface on MATLAB for Systems Control
  10. Proceedings of the SeMantic Answer Type and Relation Prediction Task at ISWC 2021 Semantic Web Challenge (SMART2021)
  11. Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
  12. Modelling the Complexity of Measurement Estimation Situations - A Theoretical Framework for the Estimation of Lengths
  13. Building a process layer for business applications using the blackboard pattern
  14. Emergency detection based on probabilistic modeling in AAL environments
  15. Control of a Sun Tracking Robot Based on Adaptive Sliding Mode Control with Kalman Filtering and Model Predictive Control
  16. A Multilevel CFA-MTMM Model for Nested Structurally Different Methods
  17. Introducing a multivariate model for predicting driving performance
  18. Identification of structure-biodegradability relationships for ionic liquids - clustering of a dataset based on structural similarity
  19. Age-related differences in processing visual device and task characteristics when using technical devices
  20. Implicit statistical learning and working memory predict EFL development and written task outcomes in adolescents
  21. Using the flatness of DC-Drives to emulate a generator for a decoupled MPC using a geometric approach for motion control in Robotino
  22. A discrete-time fractional order PI controller for a three phase synchronous motor using an optimal loop shaping approach
  23. Globally asymptotic output feedback tracking of robot manipulators with actuator constraints
  24. Construct Objectification and De-Objectification in Organization Theory
  25. A model predictive control in Robotino and its implementation using ROS system
  26. Long-term memory predictors of adult language learning at the interface between syntactic form and meaning
  27. Comparing the performance of computational estimation methods for physicochemical properties of dimethylsiloxanes and selected siloxanols
  28. Human–learning–machines: introduction to a special section on how cybernetics and constructivism inspired new forms of learning
  29. A change of values is in the air