Spatio-Temporal RANSAC for Robust Estimation of Ground Plane in Video Range Images for Automotive Applications

This paper considers the problem of ground plane estimation in range image data obtained from Time-of-Flight camera. We extend the 3D spatial RANSAC for ground plane estimation to 4D spatio-temporal RANSAC by incorporating a time axis. Ground plane models are derived from spatio-temporal random data points, thereby robustifying the algorithm against short term temporal effects such as passing cars, pedestrians, etc. The computationally fast and robust estimation of ground plane leads to reliable identification of obstacles and pedestrians using statistically derived spatial thresholds. Experimental results with real video data from range sensor mounted on a vehicle moving in a car park are presented.