Monocular Obstacle Detection for Real-World Environments

In this paper, we present a feature based approach for monocular scene reconstruction based on extended Kalman filters (EKF). Our method processes a sequence of images taken by a single camera mounted in front of a mobile robot. Using different techniques we are able to produce a precise reconstruction that is free from outliers and therefore can be used for reliable obstacle detection and avoidance. In real-world field-tests we show that the presented approach is able to detect obstacles that can not be seen by other sensors, such as laser-range-finders. Furthermore, we show that visual obstacle detection combined with a laser range finder can increase the detection rate of obstacles considerably allowing the autonomous use of mobile robots in complex public and home environments.