Road prediction for intelligent vehicles using video

This paper presents the use of a video camera for predicting vehicle trajectory. It analyses the data available from the video camera, the features which can be used for trajectory prediction and how these relate to the real world. A recursive least squares based estimator is designed which is robust with respect to horizon problems and deals with distance varying measurement noise. The results illustrate the estimation and comprises simulated data, to illustrate robustness, and video data to show typical road features