Implementation of inverse perspective mapping algorithm for the development of an automatic lane tracking system
Anuar Mikdad Muad, Aini Hussain, Salina Abdul Samad, Mohd Marzuki Mustaffa, Burhanuddin Yeop Majlis · 2004
Vision based automatic lane tracking system requires information such as lane markings, road curvature and leading vehicle be detected before capturing the next image frame. Placing a camera on the vehicle dashboard and capturing the forward view results in a perspective view of the road image. The perspective view of the captured image somehow distorts the actual shape of the road, which involves the width, height, and depth. Respectively, these parameters represent the x, y and z components. As such, the image needs to go through a pre-processing stage to remedy the distortion using a transformation technique known as an inverse perspective mapping (IPM). This paper outlines the procedures involved.