Road Detection Using Lane Detection Algorithms with Noise and Edge Detection Techniques

Road fault detection is an essential part of modern vehicle systems. Particularly in real-time vehicular ad hoc networks (VANETs), this study addresses the limitations of existing fault detection algorithms. This often presents lower performance in noisy and adverse environments such as fog, powder, shadows, potholes, oil slicks and tire skid marks. To overcome these challenges, We have implemented and evaluated advanced edge detection techniques. These techniques, which include Laplacian, Sobel, and Canny edge detection, are used on previously processed road photos. It focuses on minimizing the effect of noise on the detection process and isolating regions of interest (ROI). Comparative analysis draws attention to each technique's advantages and disadvantages. In noisy environments, Canny's edge detection performs better in terms of accuracy and resilience. The foundation for enhancing error detection systems is provided by these results. As a result, autonomous driving technology is more dependable and safer.