Project Summary

Road detection is an important task in computer vision, and image processing with the aim to identify and segment road areas from images and videos to get drivable regions for autonomous vehicles with edge detection playing a role in the process. Edge detction is a wdiely used tyechnique in many cases, such as object recognition  and tracking, medical imaging, industrial machine vision, image segmentation and enhancement, and satellite image analysis, to name a few. There are several edge detection methods, such as Roberts, Laplacian, and Prewitt. In this research, two edge detctors are analyzed and compared: the Sobel and Canny detectors. The algorithms of the two edge detectors are applied to images and videos of roads, and each edge detector's performance will be compared and evaluated using Pixel Accuracy (PA) and Pratt Quality Factor (PQF).