Towards Real-time Semantic RGB-D SLAM in Dynamic Environments
This addresses the challenge of robust camera tracking in dynamic settings for robotics and AR/VR applications, representing an incremental improvement over existing methods.
The paper tackles the problem of visual SLAM failing in dynamic environments by proposing a real-time semantic RGB-D SLAM system that detects both known and unknown moving objects, achieving high localization accuracy on low-power embedded platforms.
Most of the existing visual SLAM methods heavily rely on a static world assumption and easily fail in dynamic environments. Some recent works eliminate the influence of dynamic objects by introducing deep learning-based semantic information to SLAM systems. However such methods suffer from high computational cost and cannot handle unknown objects. In this paper, we propose a real-time semantic RGB-D SLAM system for dynamic environments that is capable of detecting both known and unknown moving objects. To reduce the computational cost, we only perform semantic segmentation on keyframes to remove known dynamic objects, and maintain a static map for robust camera tracking. Furthermore, we propose an efficient geometry module to detect unknown moving objects by clustering the depth image into a few regions and identifying the dynamic regions via their reprojection errors. The proposed method is evaluated on public datasets and real-world conditions. To the best of our knowledge, it is one of the first semantic RGB-D SLAM systems that run in real-time on a low-power embedded platform and provide high localization accuracy in dynamic environments.