Please use this identifier to cite or link to this item:
Title: GMC : grid based motion clustering in dynamic environment
Authors: Zhang, Handuo
Hasith, Karunasekera
Zhou, Hui
Wang, Han
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2019
Source: Zhang, H., Hasith, K., Zhou, H., & Wang, H. (2019). GMC : grid based motion clustering in dynamic environment. Proceedings of the 2019 SAI Intelligent Systems Conference (IntelliSys), 2, 1267-1280. doi:10.1007/978-3-030-29513-4_93
Project: MRP1A
Abstract: Conventional SLAM algorithms takes a strong assumption of scene motionlessness, which limits the application in real environments. This paper tries to tackle the challenging visual SLAM issue of complicated environments. We present GMC, grid-based motion clustering approach, a lightweight dynamic object filtering method that is free from high-power and expensive processors and is able to differentiate moving objects out of the surroundings. GMC encapsulates motion consistency as the statistical likelihood of detected key points within a certain region. Using this method can we provide real-time and robust correspondence algorithm that can differentiate dynamic objects with static backgrounds. Furthermore, we evaluate our system in the public TUM dataset. To compare with the state-of-the-art methods, our system can provide more accurate results by detecting dynamic objects.
ISBN: 9783030295127
DOI: 10.1007/978-3-030-29513-4_93
Rights: © 2020 Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of an article published in Proceedings of the 2019 SAI Intelligent Systems Conference (IntelliSys). The final authenticated version is available online at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Conference Papers

Files in This Item:
File Description SizeFormat 
gmc paper.pdf2.4 MBAdobe PDFView/Open

Citations 50

Updated on Feb 5, 2023

Page view(s)

Updated on Feb 3, 2023

Download(s) 50

Updated on Feb 3, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.