An Improved Robot's Localization and Mapping Method Based on ORB-SLAM

The ORB-SLAM is a real-time SLAM system based on feature points, with high accurate positioning, high robust, and the ability to operate in large-scale, small-scale, indoor and outdoor environments. However, since the whole SLAM system uses feature points and each image needs to calculate ORB characteristics once, which will consume a lot of time. Therefore, using quasi-physical sampling algorithm based on BING features combined with depth information to preprocess image. And the matching strategy of the ORB algorithm is optimized by an improved KD-Tree to improve the matching speed on the premise of invariable matching accuracy. Finally, on the basis of the above, using the KINECT to construct the 3D dense point cloud map system, improving the deficiency of ORB-SLAM which can only build sparse map. The results of experiment verified the feasibility of the algorithm, and can be robust and fast in complex indoor environments, which can be applied to the positioning and build 3D dense map.