Detecting Danger: AI-Enabled Road Crack Detection for Autonomous Vehicles

Abstract

The present article proposes the deep learning concept termed ―Faster-Region Convolutional Neural Network‖ (Faster-RCNN) technique to detect cracks on road for autonomous cars. Feature extraction, preprocessing, and classification techniques have been used in this study. Several types of image datasets, such as camera images, faster-RCNN laser images, and real-time images, have been considered. With the help of GPU (graphics processing unit), the input image is processed. Thus, the density of the road is measured and information regarding the classification of road cracks is acquired. This model aims to determine road crack precisely as compared to the existing techniques.

Keywords

• deep learning
• faster-rcnn
• gpu
• autonomous driving
• feature extraction