Vision systems have acquired growing importance in mobile robotics during the last years due to their low cost and the rich information that cameras provide in comparison with traditional robotic sensors, like laser scanners or sonars. Vision-based systems are employed in a wide range of robotic applications such as object recognition, obstacle avoidance, navigation, topological global localization and, more recently, in simultaneous localization and mapping (SLAM), which has become a prominent research area in mobile robotics since the early 1990s.

Monocular SLAM is an appealing way of solving the localization and mapping problem in mobile robotics because cameras are inexpensive, compact, easy to calibrate and consume low power. During the last years monocular SLAM has advanced notably with the use of parallel processing and efficient algorithms for data association and map optimization. It has made possible that current state-of-the-art approaches can operate accurately in some large scale scenarios, facilitating its application in a wide range of areas such as augmented reality, scene reconstruction and, particularly, mobile robotics.

We have presented a compact plane-based representation of the scene that we name PbMap (Plane-based Map). This map can be built online using a 6DoF moving RGB-D sensor. It consists of a set of 3D planar patches described by simple geometric and radiometric features (normal vector, centroid, area, dominant color, etc.). This world representation can be used to recognize scenes and to detect loop closures while building the map.

Medium- and high-resolution satellite images provided by latest missions such as QuickBird, Ikonos, OrbView or former ones such as IRS have opened a new range of applications in the remote sensing field because of the possibility of extracting detailed information from the images. These applications include some that are becoming common in the last years, such as natural disaster monitoring (i.e. flooding, earthquake, etc.) or urban change detection, and others that will be a real possibility in the next years, such as urban scene reconstruction, cartography update, urban inventory, etc.