Stair detection and tracking from egocentric stereo vision

Abstract

In this work we present a real-time approach to capture the properties of staircases from a free moving, head mounted stereo-camera. A variety of systems can profit from such ability, examples range from robots in multi-floor exploration scenarios to wearable assistance systems for the visually impaired. We introduce a light-weight method to measure the individual steps and use this information to update a minimal stair model while approaching and traversing the stair. Results are evaluated on an in- and outdoor scenario and show competitive accuracy to state of the art approaches working on precise lidar-sensors.