Abstract
Currently, many vision-based motion capture systems require passive markers attached to key locations on the human body. However, such systems are intrusive with limited application. The algorithm that we use for human motion capture in this paper is based on Markov random field (MRF) and dynamic graph cuts. It takes full account of the impact of 3D reconstruction error and integrates human motion capture and 3D reconstruction into MRF-MAP framework. For more accurate and robust performance, we extend our algorithm by incorporating color constraints into the pose estimation process. The advantages of incorporating color constraints are demonstrated by experimental results on several video sequences.
Similar content being viewed by others
References
Caillette F, Howard T. Real-time markerless human body tracking with multi-view 3-D voxel reconstruction. In: BMVC, volume II, 2004. 596–606
Kehl R, Bray M, Van Gool L. Full body tracking from multiple views using stochastic sampling. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005
Cheung G K M, Baker S, Kanade T. Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture. In: ACM SIGGRAPH, 2003. 77–84
Chu C W, Jenkins O C, Mataric M J. Markerless kinematic model and motion capture from volume sequences. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2003. 475–482
Mundermann L, Corazza S, Andriacchi T. Accurately measuring human movement using articulated ICP with soft-joint constraints and a repository of articulated models. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2007
Wan C K, Yuan B Z, Miao Z J. Markerless human body motion capture using Markov random field and dynamic graph cuts. Visual Comput, 2008, 24: 373–380
Seitz S M, Dyer CR. Photorealistic scene reconstruction by voxel coloring. Int J Comput Vision, 1999, 35(2): 151–173
Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE J Robot Automat, 1987, 3(4): 323–344
Sun Y D, Li B, Yuan B Z, et al. Better foreground segmentation for static cameras via new energy form and dynamic graph-cut. In: International Conference on Pattern Recognition, 2006
Potomesil M. Generating octree models of 3d objects from their silhouettes in a sequence of images. Comput Vision, Graph Image Process, 1987, 40: 1–10
Szeliski R. Rapid octree construction from image sequences. CVGIP: Image Understanding, 1993, 58(1): 23–32
Sundaresan A, Chellappa R. Markerless motion capture using multiple cameras. In: CVIIE, 2005. 15–26
Mikic I, Trivedi M, Hunter E, et al. Human body model acquisition and tracking using voxel data. Int J Comput Vision, 2003, 53(3): 199–223
Moeslund T B, Granum E. A survey of computer vision-based human motion capture. Comput Vision Image Understand, 2001, 231–268
Kolmogorov V, Zabih R. What energy functions can be minimized via graph cuts? IEEE Trans Patt Anal Mach Intell, 2004, 26(2): 147–159
Boykov Y, Jolly M. Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: IEEE International Conference on Computer Vision (ICCV 2001). 2001, 1: 105–112
Kohli P, Torr P. Efficiently solving dynamic Markov random fields using graph cuts. In: IEEE International Conference on Computer Vision ICCV, 2005
Press W, Flannery B, Teukolsky, et al. Numerical Recipes in C. Cambridge: Cambridge University Press, 1998
Author information
Authors and Affiliations
Corresponding authors
Additional information
Supported by the National Basic Research Program of China (Grant No. 2006CB303105)
Rights and permissions
About this article
Cite this article
Li, J., Wan, C., Zhang, D. et al. Markerless human motion capture by Markov random field and dynamic graph cuts with color constraints. Sci. China Ser. F-Inf. Sci. 52, 252–259 (2009). https://doi.org/10.1007/s11432-009-0040-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-009-0040-x