Abstract
In this paper, a novel, robust, and simple method for automatically estimating the hand pose is proposed and validated. The method uses a multi-camera optoelectronic system and a model-based stochastic algorithm. The approach is marker-based and relies on an Unscented Kalman Filter. A hand kinematic model is introduced for constraining relative marker’s positions and improving the algorithm robustness with respect to outliers and possible occlusions. The algorithm outputs are 3D coordinate measures of markers and hand joint angle values. To validate the proposed algorithm, a comparison with ground truths for angular and 3D coordinate measures is carried out. The comparative analysis shows the advantages of using the model-based stochastic algorithm with respect to standard processing software of optoelectronic cameras in terms of implementation simplicity, time consumption, and user effort. The accuracy is remarkable, with a difference of maximum 0.035r a d and 4m m with respect to angular and 3D Cartesian coordinates ground truths, respectively.
Similar content being viewed by others
Notes
Otherwise it should be hopefully possible to extract the subset of strictly dominant rows from the matrix and work with them.
References
Provenzale A, Cordella F, Zollo L, Davalli A, Sacchetti R, Guglielmelli E (2014) A grasp synthesis algorithm based on postural synergies for an anthropomorphic arm-hand robotic system. Proc IEEE RAS EMBS Int Conf Biomed Robot Biomechatron
Foxlin E (2007) Motion tracking requirements and technologies Handbook of virtual environments: design, implementation, and applications, Lawrence Erlbaum Associates, vol 35, pp 1989–2002
Bianchi M, Salaris P, Bicchi A (2013) Synergy-based hand pose sensing: optimal glove design. Int J Robot Res 32:396–406. doi:10.1177/0278364912474079
Oikonomidis I (2012) Tracking the articulated motion of two strongly interacting hands. Proc CVPR IEEE, Argyros AA
Sridhar S, Mueller F, Oulasvirta A, Theobalt C (2015) Fast and robust hand tracking using detection-guided optimization Conference on computer vision and pattern recognition, pp 3213–3221
Wheatland N, Wang Y, Song H, Neff M, Zordan V, Jorg S (2015) State of the art in hand and finger modeling and animation. Eurographics
Cerveri P, De Momi E, Lopomo N, Baud-Bovy G, Barros RML, Ferrigno G (2007) Finger kinematic modeling and real-time hand motion estimation. Ann Biomed Eng 35:11. doi:10.1007/s10439-007-9364-0
Meyer J, Kuderer M, Muller J, Burgard W (2014) Online marker labeling for fully automatic skeleton tracking in optical motion capture. IEEE Int Conf Robot Autom
Zordan VB, Van Der Horst NC (2003) Mapping optical motion capture data to skeletal motion using a physical model ACM SIGGRAPH/Eurographics symposium on computer animation
Maycock J, Rohlig T, Schroder M, Botsch M, Ritter H (2015) Fully automatic optical motion tracking using an inverse kinematics approach IEEE-RAS international conference on humanoid robots
Aristidou A, Lasenby J (2013) Real-time marker prediction and cor estimation in optical motion capture. Vis Comput 29:7–26. doi:10.1007/s00371-011-0671-y
Kandepu R, Foss B, Imsland L (2008) Applying the unscented Kalman filter for nonlinear state estimation. J Process Control 18:753–768. doi:10.1016/j.jprocont.2007.11.004
Liu H, Wu K, Meusel P, Seitz N, Hirzinger G, Jin MH, Liu YW, Fan SW, Lan T, Chen ZP (2008) Multisensory five-finger dexterous hand: the DLR/HIT Hand II. IEEE Int C Int Robot
Bullock IM, Borras J, Dollar AM (2012) Assessing assumption in kinematic hand models: a review. Proc IEEE RAS EMBS Int Conf Biomed Robot Biomechatron
Cobos S, Ferre M, Uran S, Ortego J, Pena C (2008) Efficient human hand kinematics for manipulation tasks. IEEE Int C Int Robot
Chang LY, Pollard NS (2008) Method for determining kinematic parameters of the in vivo thumb carpometacarpal joint. IEEE Trans Biomed Eng 55:1897–1907. doi:10.1109/TBME.2008.919854
Cordella F, Zollo L, Salerno A, Accoto D, Guglielmelli E, Siciliano B (2014) Human hand motion analysis and synthesis of optimal power grasps for a robotic hand. Int J Adv Rob Syst 11:1–13. doi:10.5772/57554
Siciliano B, Sciavicco L, Villani L, Oriolo G (2009) Robotics — modelling, planning and control. Springer, London. ISBN 978-1-84628-641-4
Wan EA, Van der Merwe R (2000) The unscented Kalman filter for nonlinear estimation Symposium on adaptive systems for signal processing, communications, and control
Cordella F, Di Corato F, Zollo L, Siciliano B (2013) New trends in image analysis and processing ICIAP 2013, Lecture Notes in Computer Science. In: Petrosino A, Maddalena L, Pala P (eds) A robust hand pose estimation algorithm for hand rehabilitation. Springer Verlag, Berlin, pp 1–10
Sarkka S, Vehtari A, Lampinen J (2004) Raoblackwellized Monte Carlo data association for multiple target tracking Proceedings of the 7th international conference on information fusion, vol 1, pp 583–590
Di Corato F (2013) A unified framework for constrained visual-inertial navigation with guaranteed convergence. PhD Dissertation, University of Pisa
Liang H, Yuan J, Thalmann D, Zhang Z (2013) Model-based hand pose estimation via spatial-temporal hand parsing and 3D fingertip localization. Vis Comput 29:837–848
Kortier HG, Sluiter VI, Roetenberg D, Veltink PH (2014) Assessment of hand kinematic using inertial and magnetic sensors. J Neuroeng Rehabil 11:70. doi:10.1186/1743-0003-11-70
Cordella F, Taffoni F, Raiano L, Carpino G, Pantoni M, Zollo L, Schena E, Guglielmelli E, Formica D (2016) Design and development of a sensorized cylindrical object for grasping assessment. Conf Proc IEEE Eng Med Biol Soc
Romeo RA, Cordella F, Zollo L, Formica D, Saccomandi P, Schena E, Carpino G, Davalli A, Sacchetti R, Guglielmelli E (2015) Development and preliminary testing of an instrumented object for force analysis during grasping. Conf Proc IEEE Eng Med Biol Soc
Acknowledgments
This work was supported partly by the Italian Institute for Labour Accidents (INAIL) with PPR 2 project (CUP: E58C13000990001) and partly by the European Project H2020/AIDE: Multimodal and Natural computer interaction Adaptive Multimodal Interfaces to Assist Disabled People in Daily Activities (CUP J42I15000030006).
Author information
Authors and Affiliations
Corresponding author
Additional information
Work done while Francesco Di Corato was at the Research Center “E. Plaggio” Pisa, Italy
Appendix
Appendix
The Denavit-Hartenberg (DH) parameters for the index finger and for the thumb are shown in Tables 1 and 2, respectively. The other long fingers have the same DH parameters of the index. DH parameters are evaluated in such a way as to obtain a generic algorithm valid for different hand sizes. Therefore, the algorithm envisages an initial calibration phase, where the 3D Cartesian coordinates of the markers center are detected manually in the first image acquired by the camera and the link lengths are measured, by means of the 3-dimensional information provided by the vision system.
In the Tables 1 and 2, L index and L thumb represent the link lengths of the index finger and of the thumb, respectively.
Once the DH parameters have been computed, the rotation matrices can be extracted. Given the symbolic form of a generic rotation matrix
the corresponding Euler angles in configuration ZYX, under the assumption that r 13≠0 and r 23≠0, are
where a t a n2(x,y) is the arctangent of two arguments, the choice of the positive sign for the term \(\sqrt {r_{13}^{2} + r_{23}^{2}}\) limits the range of the feasible values of 𝜃 to (0,π). If 𝜃 is chosen in the range (−π, 0), Eq. 20 becames
Rights and permissions
About this article
Cite this article
Cordella, F., Corato, F.D., Siciliano, B. et al. A stochastic algorithm for automatic hand pose and motion estimation. Med Biol Eng Comput 55, 2197–2208 (2017). https://doi.org/10.1007/s11517-017-1654-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-017-1654-6