Colour Vision Based Drivable Road Area Estimation

Abstract

Autonomous navigation of robot for on-road driving has gained importance in automobile research area. Image based path tracking has obtained growing attention for future driving assistance for it's inexpensive and effective.  Image from a monocular camera, directing in front side is used for tracking the drivable road area. Use of colour based drivable road area estimation technique is common in such problems. Different colour parameters have been considered for image segmentation till the date. This paper considers the use of intensity and hue for better segmentation results. The segmented results prove to be more efficient in real-time road scenario.