Multi-sensor-based online positive learning for drivable region detection

Abstract

A new method for detecting drivable regions in an unrehearsed and unstructured outdoor environment using multi-sensor information is presented. To achieve this goal, two key methods are developed: (i) robust and effective feature definition using colour and geometry and (ii) online learning algorithm using positive samples for detecting drivable regions. With real data sets, the effect of sensor modality is evaluated and is compared the performance of the algorithm to a cluster-based approach.