arXiv Analytics

Sign in

arXiv:1903.10782 [cs.RO]AbstractReferencesReviewsResources

High-quality Instance-aware Semantic 3D Map Using RGB-D Camera

Dinh-Cuong Hoang, Todor Stoyanov, Achim J. Lilienthal

Published 2019-03-26Version 1

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning based instance segmentation and classification into a state of the art RGB-D SLAM system. We leverage the pipeline of ElasticFusion \cite{whelan2016elasticfusion} as a backbone, and propose modifications of the registration cost function to make full use of the instance class labels in the process. The proposed objective function features tunable weights for the depth, appearance, and semantic information channels, which can be learned from data. The resulting system is capable of producing accurate semantic maps of room-sized environments, as well as reconstructing highly detailed object-level models. The developed method has been verified through experimental validation on the TUM RGB-D SLAM benchmark and the YCB video dataset. Our results confirmed that the proposed system performs favorably in terms of trajectory estimation, surface reconstruction, and segmentation quality in comparison to other state-of-the-art systems.

Comments: Manuscript submitted to 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Received March 1, 2019
Categories: cs.RO
Related articles: Most relevant | Search more
arXiv:1810.03303 [cs.RO] (Published 2018-10-08)
Accurate Pouring with an Autonomous Robot Using an RGB-D Camera
arXiv:2209.08258 [cs.RO] (Published 2022-09-17)
A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera
arXiv:2303.00132 [cs.RO] (Published 2023-02-28, updated 2023-07-05)
Low computational-cost detection and tracking of dynamic obstacles for mobile robots with RGB-D cameras