GMM-based 3D object representation and robust tracking in unconstructed dynamic environments

Seongyong Koo, Dongheui Lee, Dong Soo Kwon

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

5 Scopus citations

Abstract

Operating in unstructured dynamic human environments, it is desirable for a robot to identify dynamic objects and robustly track them without prior knowledge. This paper proposes a novel model-free approach for probabilistic representation and tracking of moving objects from 3D point set data based on Gaussian Mixture Model (GMM). GMM is inherently flexible such that represents any shape of objects as 3D probability distribution of the true positions. In order to achieve the robustness of the model, the proposed tracking method consists of GMM-based 3D registration, Gaussian Sum Filtering, and GMM simplification processes. The tracking performance of the proposed method was evaluated in the moving two human hands with one object, and it performed over 87% tracking accuracy together with processing 5 frames per second.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Pages1114-1121
Number of pages8
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 IEEE International Conference on Robotics and Automation, ICRA 2013 - Karlsruhe, Germany
Duration: 6 May 201310 May 2013

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Country/TerritoryGermany
CityKarlsruhe
Period6/05/1310/05/13

Fingerprint

Dive into the research topics of 'GMM-based 3D object representation and robust tracking in unconstructed dynamic environments'. Together they form a unique fingerprint.

Cite this