DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM

TL;DR

DynaSLAM II is a visual SLAM system that integrates multi-object tracking with static scene mapping, improving scene understanding and camera tracking in dynamic environments using semantic segmentation and joint optimization.

Contribution

It introduces a tightly-coupled approach to simultaneously track dynamic objects and perform SLAM, enhancing scene understanding in non-rigid environments.

Findings

Tracking dynamic objects improves camera localization accuracy.

Joint optimization of static and dynamic elements enhances scene reconstruction.

Object bounding boxes are effectively estimated within a fixed temporal window.

Abstract

The assumption of scene rigidity is common in visual SLAM algorithms. However, it limits their applicability in populated real-world environments. Furthermore, most scenarios including autonomous driving, multi-robot collaboration and augmented/virtual reality, require explicit motion information of the surroundings to help with decision making and scene understanding. We present in this paper DynaSLAM II, a visual SLAM system for stereo and RGB-D configurations that tightly integrates the multi-object tracking capability. DynaSLAM II makes use of instance semantic segmentation and of ORB features to track dynamic objects. The structure of the static scene and of the dynamic objects is optimized jointly with the trajectories of both the camera and the moving agents within a novel bundle adjustment proposal. The 3D bounding boxes of the objects are also estimated and loosely optimized within a fixed temporal window. We demonstrate that tracking dynamic objects does not only provide rich clues for scene understanding but is also beneficial for camera tracking. The project code will be released upon acceptance.