Self-Improving SLAM in Dynamic Environments: Learning When to Mask
October 15, 2022 Β· Declared Dead Β· π British Machine Vision Conference
Repo contents: README.md, consinv_dataset.png
Authors
Adrian Bojko, Romain Dupont, Mohamed Tamaazousti, HervΓ© Le Borgne
arXiv ID
2210.08350
Category
cs.CV: Computer Vision
Cross-listed
cs.AI
Citations
4
Venue
British Machine Vision Conference
Repository
https://github.com/adrianbojko/consinv-dataset
β 5
Last Checked
1 month ago
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Computer Vision
π
π
Old Age
π
π
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
R.I.P.
π»
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
π
π
Old Age
SSD: Single Shot MultiBox Detector
π
π
Old Age
Squeeze-and-Excitation Networks
R.I.P.
π»
Ghosted
Rethinking the Inception Architecture for Computer Vision
Died the same way β 𦴠Skeleton Repo
R.I.P.
π¦΄
Skeleton Repo
EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
R.I.P.
π¦΄
Skeleton Repo
Deep Learning for 3D Point Clouds: A Survey
R.I.P.
π¦΄
Skeleton Repo
Adversarial Examples: Attacks and Defenses for Deep Learning
R.I.P.
π¦΄
Skeleton Repo