DOT: Dynamic Object Tracking for Visual SLAM
This addresses robustness issues for SLAM systems in dynamic environments, though it is incremental as it builds on existing SLAM frameworks.
The paper tackles the problem of visual SLAM in dynamic environments by introducing DOT, a front-end that combines instance segmentation and multi-view geometry to track and mask dynamic objects, improving ORB-SLAM 2's accuracy and robustness in such scenes.
In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments. DOT combines instance segmentation and multi-view geometry to generate masks for dynamic objects in order to allow SLAM systems based on rigid scene models to avoid such image areas in their optimizations. To determine which objects are actually moving, DOT segments first instances of potentially dynamic objects and then, with the estimated camera motion, tracks such objects by minimizing the photometric reprojection error. This short-term tracking improves the accuracy of the segmentation with respect to other approaches. In the end, only actually dynamic masks are generated. We have evaluated DOT with ORB-SLAM 2 in three public datasets. Our results show that our approach improves significantly the accuracy and robustness of ORB-SLAM 2, especially in highly dynamic scenes.