Robust Landmark Detection and Localization; A Multisensor Approach

This paper describes a landmark position measurement system using an integrated laser-camera sensor. Laser range finder can be used to detect landmarks that are direction invariant in the laser data such as protruding edges in walls, edges of tables, chairs. When such features are unavailable the processes that depend on landmarks such as navigation and simultaneous localization and mapping (SLAM) algorithms will not be able to perform at the best accuracy. However, in many instances larger number of landmarks can be detected using computer vision. In the proposed method camera is used to detect landmarks while the location of the landmark is measured by the laser range finder using laser-camera calibration information. Thus, the proposed method exploits the beneficial aspects of each sensor to overcome the disadvantages of the other sensor. Experimental results with important statistics are provided and an application in SLAM is presented.