DOT: Dynamic Object Tracking for Visual SLAM

TL;DR

DOT enhances visual SLAM by accurately tracking and masking dynamic objects using instance segmentation and multi-view geometry, significantly improving robustness and accuracy in dynamic environments.

Contribution

Introduces DOT, a novel method combining segmentation and multi-view geometry for dynamic object tracking in SLAM systems, improving performance in dynamic scenes.

Findings

Improves ORB-SLAM 2 robustness in dynamic environments

Significantly increases SLAM accuracy in highly dynamic scenes

Effective dynamic object masking reduces errors

Abstract

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.