MAP ZDF segmentation and tracking using active stereo vision: Hand tracking case study

Andrew Dankers*, Nick Barnes, Alex Zelinsky

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

A maximum a posterior probability zero disparity filter (MAP ZDF) ensures coordinated stereo fixation upon an arbitrarily moving, rotating, re-configuring hand, performing marker-less pixel-wise segmentation of the hand. Active stereo fixation permits real-time foveal hand tracking and segmentation over a large visual workspace, allowing investigation of unrestricted natural human gesturing. Hand segmentation is shown to be robust to lighting conditions, defocus, hand colour variation, foreground and background clutter including non-tracked hands, and partial or gross occlusions including those due to non-tracked hands. The system operates at approximately 27 fps on a 3 GHz single processor PC.

Original languageEnglish
Pages (from-to)74-86
Number of pages13
JournalComputer Vision and Image Understanding
Volume108
Issue number1-2
DOIs
Publication statusPublished - Oct 2007
Externally publishedYes

Fingerprint

Dive into the research topics of 'MAP ZDF segmentation and tracking using active stereo vision: Hand tracking case study'. Together they form a unique fingerprint.

Cite this