Abstract
Urban pavement disease recognition is for the most part, a mission performed manually. Recently, video analysis task has been one of the most important applications in various fields. Aims to renovate on the automated vision-based disease recognition and to experiment new methods of road disease detection, this paper analyzes the images took from a city and performed image data visualization of road issues. From image features extracted from histogram of oriented gradient, we perform principal components analysis to reduce the dimensionality of features. Results are presented by visualizing datapoints using t-distributed stochastic neighbor embedding. The experiment shows that the image data visualization using t-SNE is suitable for the growing field of urban road disease recognition.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call