Human pose tracking in low dimensional space enhanced by limb correction

A. Moutzouris, J. Martinez-Del-Rincon, M. Lewandowski, J.-C. Nebel, D. Makris

Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

5 Citations (Scopus)


This paper proposes a two-level 3D human pose tracking method for a specific action captured by several cameras. The generation of pose estimates relies on fitting a 3D articulated model on a Visual Hull generated from the input images. First, an initial pose estimate is constrained by a low dimensional manifold learnt by Temporal Laplacian Eigenmaps. Then, an improved global pose is calculated by refining individual limb poses. The validation of our method uses a public standard dataset and demonstrates its accurate and computational efficiency.
Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Place of PublicationNEW YORK
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
ISBN (Print)978-1-4577-1303-3
Publication statusPublished - 2011
Event18th IEEE International Conference on Image Processing (ICIP) - Brussels, Belgium
Duration: 11 Sep 201114 Sep 2011


Conference18th IEEE International Conference on Image Processing (ICIP)


Dive into the research topics of 'Human pose tracking in low dimensional space enhanced by limb correction'. Together they form a unique fingerprint.

Cite this