Stereo-based Free Space Computation in Complex Traffic Scenarios

This paper presents a method for the computation of free space in complex traffic scenarios. Dynamic depth information is estimated by integrating stereo disparity images over time. Disparity and disparity speed are computed pixel-wise with Kalman filters. The stereo information is used to compute stochastic occupancy grids. Dynamic programming on a polar-like occupancy grid yields the free space. An analysis of the calculated free space allows the detection of the available free corridor in front of the ’ego-vehicle’. The method runs at a frame rate of 20 Hz in our demonstrator vehicle.