Self-Improving SLAM in Dynamic Environments: Learning When to Mask
Adrian Bojko (CEA - Commissariat à l'Energie Atomique et aux Energies Alternatives),* Romain Dupont (DRT-LIST-DIASI-SIALV-LVML / CEA SACLAY), Mohamed Tamaazousti (CEA Saclay), Herve Le Borgne (CEA LIST)
The 33rd British Machine Vision Conference
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.Video
Citation
@inproceedings{Bojko_2022_BMVC,
author = {Adrian Bojko and Romain Dupont and Mohamed Tamaazousti and Herve Le Borgne},
title = {Self-Improving SLAM in Dynamic Environments: Learning When to Mask},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0654.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by