Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation
This addresses the problem of reliable SLAM in dynamic environments for robotics and augmented reality applications, representing a novel integration of object-level tracking with multi-instance handling.
The paper tackles robust simultaneous localization and mapping (SLAM) in highly dynamic scenes by developing a visual-inertial system that tracks, reconstructs, and relocalizes arbitrary moving objects, demonstrating its effectiveness through quantitative and qualitative testing on real-world data.
In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system. Even in extremely dynamic scenes, it can robustly optimise for the camera pose, velocity, IMU biases and build a dense 3D reconstruction object-level map of the environment. Our system can robustly track and reconstruct the geometries of arbitrary objects, their semantics and motion by incrementally fusing associated colour, depth, semantic, and foreground object probabilities into each object model thanks to its robust sensor and object tracking. In addition, when an object is lost or moved outside the camera field of view, our system can reliably recover its pose upon re-observation. We demonstrate the robustness and accuracy of our method by quantitatively and qualitatively testing it in real-world data sequences.