Monocular Vision-Based SLAM in Indoor Environment Using Corner, Lamp, and Door Features From Upward-Looking Camera

We examine monocular vision-based simultaneous localization and mapping (SLAM) of a mobile robot using an upward-looking camera. Although a monocular camera looking up toward the ceiling can provide a low-cost solution to indoor SLAM, this approach is often unable to achieve dependable navigation due to a lack of reliable visual features on the ceiling. We propose a novel approach to monocular SLAM using corner, lamp, and door features simultaneously to achieve stable navigation in various environments. We use the corner features and the circular-shaped brightest parts of the ceiling image for detection of lamp features. Furthermore, vertical and horizontal lines are combined to robustly detect line-based door features to reduce the problem that line features can be easily misidentified due to nearby edges. The use of these three types of features as landmarks increases our ability to observe the features in various environments and maintains the stability of the SLAM process. A series of experiments in indoor environments showed that the proposed scheme resulted in dependable navigation.