RGBDTAM: A Cost-Effective and Accurate RGB-D Tracking and Mapping System
This work addresses the need for cost-effective and accurate indoor robotics navigation, though it appears incremental as it builds upon existing direct RGB-D SLAM methods with specific improvements.
The authors tackled the problem of simultaneous localization and mapping (SLAM) using RGB-D cameras by proposing a direct RGB-D SLAM algorithm that achieves state-of-the-art accuracy and robustness at low cost, with experiments on the RGB-D TUM dataset showing better accuracy and robustness in CPU real-time compared to GPU-based systems.
Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics. In this paper we propose a direct RGB-D SLAM algorithm with state-of-the-art accuracy and robustness at a los cost. Our experiments in the RGB-D TUM dataset [34] effectively show a better accuracy and robustness in CPU real time than direct RGB-D SLAM systems that make use of the GPU. The key ingredients of our approach are mainly two. Firstly, the combination of a semi-dense photometric and dense geometric error for the pose tracking (see Figure 1), which we demonstrate to be the most accurate alternative. And secondly, a model of the multi-view constraints and their errors in the mapping and tracking threads, which adds extra information over other approaches. We release the open-source implementation of our approach 1 . The reader is referred to a video with our results 2 for a more illustrative visualization of its performance.