Skip to main navigation Skip to search Skip to main content

A concise tutorial on human motion tracking and recognition with Microsoft Kinect

  • Cleveland State University

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

This paper provides a concise tutorial on the Microsoft Kinect technology and the state of art research on human motion tracking and recognition with Microsoft Kinect. A pre-requisite for human motion recognition is feature extraction. There are two types of feature extraction methods: skeleton joint based, and depth/color image based. Given a set of feature vectors, a motion could be recognized using machine learning, direct comparison, or rule-based methods. We also outline future research directions on the Kinect technology.
Original languageEnglish
Article number93101
JournalScience China Information Sciences
Volume59
Issue number9
DOIs
StatePublished - Sep 1 2016

Keywords

  • Microsoft Kinect
  • depth camera
  • human motion tracking and recognition
  • machine learning

Cite this