InCrowd-VI provides a realistic visual-inertial benchmark with 58 head-worn sequences in crowded indoor spaces, where state-of-the-art SLAM systems frequently fail to meet accuracy and real-time requirements.
Self-Improving SLAM in Dynamic Environments: Learning When to Mask
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Visual SLAM - Simultaneous Localization and Mapping - in dynamic environments typically relies on identifying and masking image features on moving objects to prevent them from negatively affecting performance. Current approaches are suboptimal: they either fail to mask objects when needed or, on the contrary, mask objects needlessly. Thus, we propose a novel SLAM that learns when masking objects improves its performance in dynamic scenarios. Given a method to segment objects and a SLAM, we give the latter the ability of Temporal Masking, i.e., to infer when certain classes of objects should be masked to maximize any given SLAM metric. We do not make any priors on motion: our method learns to mask moving objects by itself. To prevent high annotations costs, we created an automatic annotation method for self-supervised training. We constructed a new dataset, named ConsInv, which includes challenging real-world dynamic sequences respectively indoors and outdoors. Our method reaches the state of the art on the TUM RGB-D dataset and outperforms it on KITTI and ConsInv datasets.
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation
InCrowd-VI provides a realistic visual-inertial benchmark with 58 head-worn sequences in crowded indoor spaces, where state-of-the-art SLAM systems frequently fail to meet accuracy and real-time requirements.