Object-aware semantic mapping of indoor scenes using octomap

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

In order to enable robots to provide high-level services in complex indoor environments, it is necessary to improve the robots' ability to cognize the environments. Most of the existing research is focused on indoor 3D reconstruction and semantic segmentation without the organization and maintenance of object recognition results. In this paper, we present an approach to build a 3D semantic map that includes both voxel-based geometrical demonstrations and object-aware entities with the combination of Simultaneous Localization and Mapping (SLAM) and Mask Region-based Convolutional Network (Mask R-CNN). An extended seeded region growing algorithm is designed for 3D segmentation refinement, and an octree-based framework octomap is used to present 3D map in replacement of point cloud map. We present experiments in a simulated home environment and the experimental results verify the accuracy and efficiency of our method.

Original languageEnglish
Title of host publicationProceedings of the 38th Chinese Control Conference, CCC 2019
EditorsMinyue Fu, Jian Sun
PublisherIEEE Computer Society
Pages8671-8676
Number of pages6
ISBN (Electronic)9789881563972
DOIs
StatePublished - Jul 2019
Externally publishedYes
Event38th Chinese Control Conference, CCC 2019 - Guangzhou, China
Duration: 27 Jul 201930 Jul 2019

Publication series

NameChinese Control Conference, CCC
Volume2019-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference38th Chinese Control Conference, CCC 2019
Country/TerritoryChina
CityGuangzhou
Period27/07/1930/07/19

Keywords

  • Mask Region-based Convolutional Network
  • Object-aware
  • Octomap
  • Segmentation Refinement
  • Semantic Mapping

Fingerprint

Dive into the research topics of 'Object-aware semantic mapping of indoor scenes using octomap'. Together they form a unique fingerprint.

Cite this