A Transfer Learning-Based System of Pothole Detection in Roads through Deep Convolutional Neural Networks
2022 International Conference on Decision Aid Sciences and Applications (DASA)
(2022), pp. 1469-1473
Jhon Michael C. Manalo
a
,
Alvin Sarraga Alon
b
,
Yolanda D. Austria
c
,
Nino E. Merencilla
d
,
Maribel A. Misola
d
,
Ricky C. Sandil
d
a Computer Engineering Program, Batangas State University, Batangas City, Philippines
b Digital Transformation Center, STEER Hub, Batangas State University, Batangas City, Philippines
c Department of Computer Engineering, Adamson University, Manila, Philippines
d Department of Computer Engineering, FEU Institute of Technology, Manila, Philippines
Abstract: Pothole detection is critical in defining optimal road management solutions and maintenance. The researcher used deep learning and yolov3 to create a pothole detection system in this study. A deep learning algorithm called YOLOv3 is used to develop a model that can successfully identify potholes. The detection model had an average precision of 95.43%, and identified potholes had accuracies ranging from 33% to 69%, which is to be anticipated given the numerous various forms and sizes of potholes.