Real-Time Two Hands Tracking System

  • Liu, Nianjun (School of Information Technology and Electrical Engineering The University of Queensland) ;
  • Lovell, Brian C. (School of Information Technology and Electrical Engineering The University of Queensland)
  • Published : 2002.07.01

Abstract

The paper introduces a novel system of two hands real-time tracking based on the unrestricted hand skin segmentation by multi color systems. After corer-based segmentation and pre-processing operation, a label set of regions is created to locate the two hands automatically. By the normalization, template matching is used to find out the left or right hand. An improved fast self-adaptive tracking algorithm is applied and Canny filter is used for hand detection.

Keywords