Abstract
This paper presents a novel technique for three-dimensional (3D) human motion capture using a set of two non-calibrated cameras. The user’s five extremities (head, hands and feet) are extracted, labeled and tracked after silhouette segmentation. As they are the minimal number of points that can be used in order to enable whole body gestural interaction, we will henceforth refer to these features as crucial points. Features are subsequently labelled using 3D triangulation and inter-image tracking. The crucial point candidates are defined as the local maxima of the geodesic distance with respect to the center of gravity of the actor region that lie on the silhouette boundary. Due to its low computational complexity, the system can run at real-time paces on standard personal computers, with an average error rate range between 4% and 9% in realistic situations, depending on the context and segmentation quality.
Similar content being viewed by others
References
Bray M, Koller-Meier E, Schraudolph N, Van Gool L (2004) Stochastic meta-descent for tracking articulated structures. In: IEEE Workshop on Articulated and Nonrigid Motion (ANM04) Washington D.C., June 2004
Correa Hernández P, Czyz J, Umeda T, Marqués F, Marichal X, Macq B (2007) Bayesian approach for morphology-based 2D human motion capture. IEEE Trans Multimed 9(4):754–765
Demirdjian D, Darrell T (2002) 3-D Articulated pose tracking for untethered diectic reference. In: ICMI 2002, Pittsburgh, October 2002
Fujiyoshi H, Lipton A (1998) Real-time human motion analysis by image skeletonization. In: IEEE Workshop on Applications of Computer Vision (WACV), Princeton, October 1998, pp 15–21
Gavrila DM (1999) The visual analysis of human movement: a survey. Comput Vis Image Underst 73(1):82–98, January
Haralick R, Shapiro L (1992) Computer and robot vision, vol. 1–2. Addison-Wesley, Reading
Haritaoglu I, Harwood D, Davis LS (2000) W4: real-time surveillance of people and their activities. IEEE Trans Pattern Anal Mach Intell 22(8):809–830, August
Johansson G (1973) Visual perception for biological motion and a model for its analysis. Percept Psychophys 14(2):201–211
Kuhn H (1955) The Hungarian method for the assignment problem. Nav Res Logist Q 2:83–97
Lanier J (2001) Virtually there. Sci Am 284:66–75, April
Marichal X, Macq B, Douxchamps D, T. Umeda and the art.live consortium (2003) ‘Real-time segmentation of video objects for mixed-reality interactive applications.’ In: VCIP 2003—SPIE Visual Communication and Image Processing Intl Conference, vol. 5150. Lugano, Switzerland, July 2003, pp 41–50
Ohya J, Utsumi A, Yamato J (2002) Analyzing video sequences of multiple humans—tracking, posture estimation and behavior recognition. The Kluwer international series in video computing, vol. 3. Kluwer, Norwell
Perrone C, Clark D, Repenning A (1996) WebQuest: substantiating education in edutainment through interactive learning games. Comput Netw ISDN Syst 28(7–11):1307
Soille P (2003) Morphological image analysis, principles and applications, 2nd edn. Springer, Berlin
Soriano M, Martinkauppi B, Huovinen S, Laaksonen M (2000) Skin detection in video under changing illumination conditions. In: Proc.of the 15th Int. Conf. on Pattern Recognition, September 2000
Umeda T, Correa Hernández P, Marqués F, Marichal X (2004) A real-time body analysis for mixed reality application. In: Proc. of the Tenth Korea–Japan Joint Workshop on Frontiers of Computer Vision, FCV-2004, Fukuoka, Japan, February 2004
Wren C, Azarbayejani A, Darrell T, Pentland A (1997) Pfinder: real-time tracking of the human body. IEEE Trans Pattern Anal Mach Intell 19(7):780–785, July
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Correa, P., Marqués, F., Marichal, X. et al. 3D posture estimation using geodesic distance maps. Multimed Tools Appl 38, 365–384 (2008). https://doi.org/10.1007/s11042-007-0191-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-007-0191-y