Faster R-CNN Structure for Computer Vision-based Road Pavement Distress Detection

Smart cities can be controlled in all aspects and it is desired to have a structure that planned controllable feedback. Asphalt generally used as pavement material on roads provide transportation of vehicles such cars buses the highway. deformed due weather conditions, heavy vehicle passage. In smart city structure, similar deformations should reported relevant unit. this article, was tried determine deteriorations asphalt by selecting data set obtained from region with image processing methods deep learning technique. With action camera placed an automobile, total 4315 images various distortions without any deterioration were dataset. The dataset classified using pixel-based Faster Region-based Convolutional Neural Network. Accuracy, precision sensitivity values make performance result classification meaningful. proposed method, average accuracy rate 93.2%. these results, approach automatically detect structures has been developed.