This work presents a novel RGB-D-inertial dynamic SLAM method that can enable accurate localisation when the majority of the camera view is occluded by multiple dynamic objects over a long period of time. Most dynamic SLAM approaches either remove dynamic objects as outliers when they account for a minor proportion of the visual input, or detect dynamic objects using semantic segmentation before camera tracking. Therefore, dynamic objects that cause large occlusions are difficult to detect without prior information. The remaining visual information from the static background is also not enough to support localisation when large occlusion lasts for a long period. To overcome these problems, our framework presents a robust visual-inertial bundle adjustment that simultaneously tracks camera, estimates cluster-wise dense segmentation of dynamic objects and maintains a static sparse map by combining dense and sparse features. The experiment results demonstrate that our method achieves promising localisation and object segmentation performance compared to other state-of-the-art methods in the scenario of long-term large occlusion.

翻译：本文提出一种新颖的RGB-D-惯性动态SLAM方法，能够在相机视野长期被多个动态物体大部分遮挡时实现精确定位。现有大多数动态SLAM方法或是在动态物体仅占视觉输入较小比例时将其作为异常值剔除，或是在相机跟踪前利用语义分割检测动态物体。因此，在缺乏先验信息的情况下，造成大范围遮挡的动态物体难以被检测；同时，当大遮挡长期持续时，静态背景中残留的视觉信息也不足以支撑定位。为解决这些问题，本框架提出一种鲁棒的视觉-惯性光束平差法，该方法同时跟踪相机、估计动态物体的聚类级稠密分割，并通过融合稠密与稀疏特征维护静态稀疏地图。实验结果表明，与其他先进方法相比，本方法在长期大遮挡场景下实现了优越的定位与物体分割性能。