Abstract
Automatic pose and shape initialization is the first step to conquer the problem of human tracking, acquiring prior knowledge about the tracking subject. It is crucial for accomplishing a successful tracking. In this paper, we present a simple and effective framework to automatically calibrate the human pose and shape by integrating a data driven shape parameterization into the skeletal animation pipeline and optimizing the template body model against multiview silhouette images to acquire the tracking subject shape and pose information. A PCA based approach is proposed to summarize the space of human body variations in height, weight, muscle tone, gender, body shape. Multiview analysis by synthesis optimization in the hierarchial order is employed to realize pose and shape calibration. Finally, experiments on HumanEvaII and Human3.6m dataset demonstrate our approach is very effective and robust to real world situations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Vertex weights are often assigned by graphics software or artists.
- 2.
The skeleton root offset between the true posture and the template model.
- 3.
The shape dimension difference ratio is defined by the subject body height divided by the template body height.
References
Allen, B., Curless, B., Popović, Z.: The space of human body shapes: reconstruction and parameterization from range scans. In: SIGGRAPH 2003: ACM SIGGRAPH 2003 Papers, pp. 587–594. ACM Press, New York (2003). https://doi.org/10.1145/1201775.882311. http://grail.cs.washington.edu/projects/digital-human/pub/allen03space.pdf
Allen, B., Curless, B., Popović, Z., Hertzmann, A.: Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis. In: SCA 2006: Proceedings of the 2006 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 147–156. Eurographics Association, Aire-la-Ville (2006). http://portal.acm.org/citation.cfm?id=1218084
Anguelov, D., et al.: SCAPE: shape completion and animation of people. ACM Trans. Graph. 24(3), 408–416 (2005)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: Rockwood, A. (ed.) SIGGRAPH 1999, Computer Graphics Proceedings, pp. 187–194. Addison Wesley Longman, Los Angeles (1999). http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.27.8314
Blender: Blender is the free open source 3d content creation suite (2020). http://www.Blender.org
Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. In: Dutr’e, P., Stamminger, M. (eds.) Computer Graphics Forum (Proceedings of the Eurographics 2008), Munich, Germany, vol. 2, March 2009
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325–1339 (2014). https://doi.org/10.1109/TPAMI.2013.248, 3D
Lewis, J.P., Cordner, M., Fong, N.: Pose space deformation: a unified approach to shape interpolation and skeleton-driven deformation. In: SIGGRAPH, pp. 165–172 (2000)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 34(6), 248:1–248:16 (2015)
Magnenat-Thalmann, N., Laperrière, R., Thalmann, D.: Joint-dependent local deformations for hand animation and object grasping. In: Proceedings on Graphics Interface 1988, pp. 26–33. Canadian Information Processing Society (1988)
Magnenat-Thalmann, N., Seo, H.: Data-driven approaches to digital human modeling. In: 3DPVT, pp. 380–387 (2004)
MakeHuman: Open source tool for making 3d characters (2020). http://www.makehuman.org
Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598–613. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_36
Powell, M.J.D.: A hybrid method for nonlinear equations. Numerical Methods for Nonlinear Algebraic Equations (1970). https://ci.nii.ac.jp/naid/10006528967/en/
Sigal, L., Balan, A., Black, M.: HUMANEVA: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87, 4 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, Y., Song, G., Zhang, H. (2021). Automatic Pose and Shape Initialization via Multiview Silhouette Images. In: Mahmud, M., Kaiser, M.S., Vassanelli, S., Dai, Q., Zhong, N. (eds) Brain Informatics. BI 2021. Lecture Notes in Computer Science(), vol 12960. Springer, Cham. https://doi.org/10.1007/978-3-030-86993-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-86993-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86992-2
Online ISBN: 978-3-030-86993-9
eBook Packages: Computer ScienceComputer Science (R0)