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

Seongyong Koo, Dongheui Lee, Dong Soo Kwon

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

5 Zitate (Scopus)

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.

OriginalspracheEnglisch
Titel2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Seiten1114-1121
Seitenumfang8
DOIs
PublikationsstatusVeröffentlicht - 2013
Extern publiziertJa
Veranstaltung2013 IEEE International Conference on Robotics and Automation, ICRA 2013 - Karlsruhe, Deutschland
Dauer: 6 Mai 201310 Mai 2013

Publikationsreihe

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

Konferenz

Konferenz2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Land/GebietDeutschland
OrtKarlsruhe
Zeitraum6/05/1310/05/13

Fingerprint

Untersuchen Sie die Forschungsthemen von „GMM-based 3D object representation and robust tracking in unconstructed dynamic environments“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren