Incremental object learning and robust tracking of multiple objects from RGB-D point set data

Seongyong Koo, Dongheui Lee, Dong Soo Kwon

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

In this paper, we propose a novel model-free approach for tracking multiple objects from RGB-D point set data. This study aims to achieve the robust tracking of arbitrary objects against dynamic interaction cases in real-time. In order to represent an object without prior knowledge, the probability density of each object is represented by Gaussian mixture models (GMM) with a tempo-spatial topological graph (TSTG). A flexible object model is incrementally updated in the pro-posed tracking framework, where each RGB-D point is identified to be involved in each object at each time step. Furthermore, the proposed method allows the creation of robust temporal associations among multiple updated objects during split, complete occlusion, partial occlusion, and multiple contacts dynamic interaction cases. The performance of the method was examined in terms of the tracking accuracy and computational efficiency by various experiments, achieving over 97% accuracy with five frames per second computation time. The limitations of the method were also empirically investigated in terms of the size of the points and the movement speed of objects.

Original languageEnglish
Pages (from-to)108-121
Number of pages14
JournalJournal of Visual Communication and Image Representation
Volume25
Issue number1
DOIs
StatePublished - Jan 2014
Externally publishedYes

Keywords

  • 3-d point set registration
  • Gaussian mixture models
  • Incremental learning
  • Multiple objects tracking
  • RGB-D point set data
  • Robot vision
  • Tempo-spatial data association
  • Visual tracking

Fingerprint

Dive into the research topics of 'Incremental object learning and robust tracking of multiple objects from RGB-D point set data'. Together they form a unique fingerprint.

Cite this