Obstacle detection for a vehicle using optical flow

A novel approach to obstacle detection using optical flow without recovering range information has been developed. This method can be used for ground vehicles to navigate through man-made roadways or natural outdoor terrain or for air vehicles to land on known or unknown terrain. A linear relationship, plotted as a line and called a reference flow line, has been found. This reference flow line can be used to detect discrete obstacles above or below the reference terrain. Slopes of surface regions are also computed. The approach is simple, fast, and robust because: (1) the only required information is one component of the optical flow, (2) each image line can be processed in parallel, and (3) the error sources involved are reduced to a minimum. An initial experiment using noisy synthetic data is also included to demonstrate the applicability and robustness of the method. >