Video Image-based Intelligent Architecture for Human Motion Capture

 

Lei Jun (1), Dieter Hogrefe (1), Tan jianrong (2)

(1) Telematics Group, Georg-August-Universitaet-Goettingen, 37083 Goettingen, Germany

http://www.tmg.informatik.uni-goettingen.de

(2) Graphics Institute Zhejiang University

310009 China

Abstract:

The study of human motion is a fascinating subject in computer vision and has been developed quite a few years. Traditional methods to realize human motion capture mainly use equipments of machinery, electromagnetic, acoustics, optics, graphics and so on. Whereas these are some defects existed in these methods e.g. expensive equipments, the place limited by sensors and localization of sport range, and it has no consistent standards because of different purposes and requirements. Most importantly, they always need a person to execute the long and sterile work for surveillance. Sometimes only by manual operation cannot accord with desires that data should be collected without redundant or unhelpful information. In view of video characters which bring about changes and new opportunities in the human motion capturing technology, this paper presents an actual architecture to automatically capture human motion by comparing video images and extracting surveillant area. Then we provide an effective method for storage. Furthermore, the functionalities of architecture are realized in GOLF sport education example.

 

Keywords: motion capture, video image, surveillant area, storage, video stream

 

Die Studie über die menschliche Bewegung ist ein faszinierendes Subjekt in der Computer-Vision, und sie entwickelte sich im Laufe von vielen Jahren. Nach der traditionellen Methode werden Maschinenanlagen, elektromagnetische Ausstattungen, Akustik, Optik, Grafik usw. benutzt, um die menschliche Bewegung zu erfassen. In dieser Methode gibt es aber manche Mängel, z.B. hohe Kosten, die Beschränkung vom Sensor und die Lokalisierung im Sportsbereich, und wegen der verschiedenen Vorsätze und Bedingungen hat es keine beständigen Maßtäbe. Am wichtigsten ist, dass eine Person die langweilige und sterile Arbeit für Beobachtung machen muss. Manchmal kann dieses manuell bediente Engagement mit dem Wunsch nach erfassenden Daten ohne überflüssige oder nutzlose Informationen nicht übereinstimmen. Die Charaktereigenschaft des Videos stellt neue Chancen und Änderungen für die menschliche Bewegungserfassung dar. Der vorliegende Atikel zeigt uns eine wirkliche Architektur der Bewegungserfassung des Menschen, die die Vergleiche des Video-Images und die Ausdrücken des Beobachtungsbereichs benutzt. Dann ist eine effektive Methode für Datenspeicherung. Außerdem verwertet die Architektur in GOLF-Sportsbildung gut als ein Beispiel.

 

 

	Jun Lei received the B.S degree in Mathematic Institute from Teacher-training college of Hangzhou, China, in 2001. She received M.S degree in Computer Graphics Institute from Zhejiang University, China in 2004 and is currently working towards the Ph.D. degree with Institute for Informatics, Goettingen University, Germany. She entered Computer Graphics co. in Hangzhou, working as technical manager from Mar.2002 to Oct.2002 and Attended UTStarcom co. Ltd P&T department, working as technical researcher from Nov.2002 to Feb.2003. She worked as technical researcher in “Ding Li Mobile Communicate Company” from Oct.2003 to Dec.2003 in Zhuhai, China. Her research interests include design and analysis multimedia systems, digital image processing and now focus on multimedia distribution over wireless and wired broadband Internet access networks and Multiple Protocol Label Switching (MPLS) backbones and survivability, protection algorithm of optical WDM mesh networks.
	Dieter Hogrefe graduated from Philips Exeter Academy, USA in 1976. He studied Computer Science and Mathematics at the Germany with a Diploma and University of Hannover, Germany with a Diploma degree and received his Ph.D in Computer Science in 1985. His research activities are directed towards Computer Networks and Software Engineering. He has published numerous papers and two books on analysis, simulation and testing of formally specified communication systems. From 1983 to 1986 he was with the Siemens research centre in Munich and worked in the area of analysis of telecommunication systems. He was responsible for the protocol simulation and analysis of the CCS No. 7. He had professorships at the University of Hamburg, Bern, Luebeck and since 2002 he is FULL PROFESSOR (C4) for Telematics at the University of Goettingen. Prof. Hogrefe represents the IITB (Frauhofer Institute for Information and Data Processing) in the European Telecommunication Standards Institute, ETSI, where is chairman of the Technical Committee Methods for Testing and Speci?cation.
	Jiangrong Tan received his Ph.D. degree in Mathematics Institute from Zhejiang University, China in 1992. Now he is the PROFESSOR and doctoral supervisor of Zhejiang University, China. His research interests include CAD, CIMS, virtual reality and scientific visualization, etc. He has published several papers and three books on CAD and CIMS. He is currently also the VICE DIRECTOR of “state key lab of CAD&CG, Zhejiang University”. Prof. Tan received “the State Foundation for Excellent Young Scholars” in 1994 and “National Foundation on Graphics Science for Excellent Young Scholars” in 1995. He is also confirmed as “The leader of key study of Zhejiang Province” in 1997 and received “Top Grade Award in Excellent Teacher of BAOGANG”in 2003. He has also received the “State second award of science and technology“ in 2004.