Sliding window based landmark extraction for indoor 2D SLAM using forward-looking monocular camera

Abstract

In this study, we propose a method to extract landmarks for pose-graph SLAM using only the forward-looking monocular camera mounted in a small mobile robot. By using the sliding window approach, the region of interest is determined to triangulate the landmarks. The landmark extraction process uses multiple sets of bearing information for triangulation. As the landmark is extracted, choose the landmark which is near the navigation plane to project into the 2D landmark node. To test its accuracy, the laser rangefinder is used as a ground truth. Also the various sliding window sizes are tried for a landmark to investigate the effect of the window size on the accuracy. Using this approach as landmark extraction for the SLAM algorithm, we expect to implement monocular based metric SLAM with the graph based back-end optimization.