Building 3D Map Based on Monte Carlo Localization and Feature Extraction

Zhun Fan, Ying Chen, Chong Li*

*Corresponding author for this work

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

Abstract

In this project, we mainly explore and construct the 3D indoor map. The goal of this paper is to merge the data from the laser and kinect sensor with Monte Carlo Location(MCL) in 2D map. We use the laser range sensor to construct the 2D map and get the robot's pose transformation matrix. Then, we obtain the color and depth image by using the kinect sensor and build 3D point cloud map by using the feature extraction method, getting the kinect's pose transformation matrix. After that, we get the optimal pose transformation by using the Kalman Filter to calibrate the robot's pose transformation matrix and the kinect's pose transformation matrix. Finally, the optimal pose transformation matrix is employed to accomplish the local 3D map and construct the global 3D indoor map. To show the superiority of our method, we make some experiments and compare with some other algorithms. Experimental results show that our method has a better superiority.

Original languageEnglish
Title of host publication10th IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages99-104
Number of pages6
ISBN (Electronic)9781728190099
DOIs
Publication statusPublished - 10 Oct 2020
Externally publishedYes
Event10th IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2020 - Xi'an, China
Duration: 10 Oct 202013 Oct 2020

Publication series

Name10th IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2020

Conference

Conference10th IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2020
Country/TerritoryChina
CityXi'an
Period10/10/2013/10/20

Fingerprint

Dive into the research topics of 'Building 3D Map Based on Monte Carlo Localization and Feature Extraction'. Together they form a unique fingerprint.

Cite this