Indoor localization with occlusion removal

A novel 3D image-based indoor localization system integrated with an obstacle removal component is proposed. In contrast with existing state-of-the-art localization techniques focusing on static outdoor or indoor environments, the adverse effects generated by moving obstacles, which are very common in busy indoor spaces, is considered in our work. In particular, this problem is converted into a separation of moving foreground and static background. We use a low-rank and sparse matrix decomposition approach to solve this problem efficiently. Our system has been tested on data sets established to emphasize the dynamic situations caused by deforming obstructions appearing in front of a static background scene that may contain useful features for localization. We demonstrate that the localization effectiveness is increased significantly after removing the dynamic occluding objects. The performance of our system is evaluated based on quantitative experimental results.