Abstract
Modern systems for real-time hand tracking rely on a combination of discriminative and generative approaches to robustly recover hand poses. Generative approaches require the specification of a geometric model. In this paper, we propose a the use of sphere-meshes as a novel geometric representation for real-time generative hand tracking. How tightly this model fits a specific user heavily affects tracking precision. We derive an optimization to non-rigidly deform a template model to fit the user data in a number of poses. This optimization jointly captures the user's static and dynamic hand geometry, thus facilitating high-precision registration. At the same time, the limited number of primitives in the tracking template allows us to retain excellent computational performance. We confirm this by embedding our models in an open source real-time registration algorithm to obtain a tracker steadily running at 60Hz. We demonstrate the effectiveness of our solution by qualitatively and quantitatively evaluating tracking precision on a variety of complex motions. We show that the improved tracking accuracy at high frame-rate enables stable tracking of extended and complex motion sequences without the need for per-frame re-initialization. To enable further research in the area of high-precision hand tracking, we publicly release source code and evaluation datasets.
Supplemental Material
Available for Download
Supplemental file.
- Albrecht, I., Haber, J., and Seidel, H.-P. 2003. Construction and animation of anatomically based human hand models. In Proc. of the Symposium on Computer Animation (SCA). Google ScholarDigital Library
- Ballan, L., Taneja, A., Gall, J., Van Gool, L., and Pollefeys, M. 2012. Motion capture of hands in action using discriminative salient points. In Proc. of the European Conf. on Computer Vision (ECCV). Google ScholarDigital Library
- Bloomenthal, J., and Shoemake, K. 1991. Convolution surfaces. In Computer Graphics (Proc. SIGGRAPH). Google ScholarDigital Library
- Bloomenthal, J., Bajaj, C., Blinn, J., Cani, M.-P., Rockwood, A., Wyvill, B., and Wyvill, G. 1997. Introduction to Implicit Surfaces. Morgan Kaufmann. Google ScholarDigital Library
- Botsch, M., Kobbelt, L., Pauly, M., Alliez, P., and Lévy, B. 2010. Polygon Mesh Processing. A. K. Peters.Google Scholar
- Bouaziz, S., Wang, Y., and Pauly, M. 2013. Online modeling for realtime facial animation. ACM Transactions on Graphics (Proc. of SIGGRAPH). Google ScholarDigital Library
- Buss, S. R. 2004. Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods. IEEE Journal of Robotics and Automation.Google Scholar
- de La Gorce, M., Fleet, D. J., and Paragios, N. 2011. Model-based 3D hand pose estimation from monocular video. Pattern Analysis and Machine Intelligence (PAMI). Google ScholarDigital Library
- Dipietro, L., Sabatini, A. M., and Dario, P. 2008. A survey of glove-based systems and their applications. IEEE Transactions on Systems, Man, and Cybernetics. Google ScholarDigital Library
- Erol, A., Bebis, G., Nicolescu, M., Boyle, R. D., and Twombly, X. 2007. Vision Based Hand Pose Estimation: A Review. Computer Vision Image Understanding. Google ScholarDigital Library
- Fleishman, S., Kliger, M., Lerner, A., and Kutliroff, G. 2015. Icpik: Inverse kinematics based articulated-icp. In Proc. of the IEEE CVPR Workshops (HANDS).Google Scholar
- Innmann, M., Zollhöfer, M., Niessner, M., Theobalt, C., and Stamminger, M. 2016. Volumedeform: Real-time volumetric non-rigid reconstruction. In Proc. of the European Conf. on Computer Vision (ECCV).Google Scholar
- Keskin, C., Kiraç, F., Kara, Y. E., and Akarun, L. 2012. Hand pose estimation and hand shape classification using multilayered randomized decision forests. In Proc. of the European Conf. on Computer Vision (ECCV). Google ScholarDigital Library
- Khamis, S., Taylor, J., Shotton, J., Keskin, C., Izadi, S., and Fitzgibbon, A. 2015. Learning an efficient model of hand shape variation from depth images. Proc. of Comp. Vision and Pattern Recog. (CVPR).Google Scholar
- Krupka, E., Vinnikov, A., Klein, B., Bar Hillel, A., Freedman, D., and Stachniak, S. 2014. Discriminative ferns ensemble for hand pose recognition. In Proc. of Comp. Vision and Pattern Recog. (CVPR). Google ScholarDigital Library
- Loper, M. M., and Black, M. J. 2014. OpenDR: An approximate differentiable renderer. In Proc. of the European Conf. on Computer Vision (ECCV).Google Scholar
- Makris, A., and Argyros, A. A. 2015. Model-based 3d hand tracking with on-line shape adaptation. In Proc. of British Machine Vision Conference (BMVC).Google Scholar
- Melax, S., Keselman, L., and Orsten, S. 2013. Dynamics based 3d skeletal hand tracking. In Proc. of Graphics Interface. Google ScholarDigital Library
- Newcombe, R. A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohli, P., Shotton, J., Hodges, S., and Fitzgibbon, A. 2011. Kinectfusion: Real-time dense surface mapping and tracking. In IEEE International Symposium on Mixed and Augmented Reality (ISMAR). Google ScholarDigital Library
- Newcombe, R. A., Fox, D., and Seitz, S. M. 2015. Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time. Proc. of Comp. Vision and Pattern Recog. (CVPR).Google Scholar
- Oberweger, M., Wohlhart, P., and Lepetit, V. 2015. Training a Feedback Loop for Hand Pose Estimation. In Proc. of the Intern. Conf. on Computer Vision (ICCV). Google ScholarDigital Library
- Oikonomidis, I., Kyriazis, N., and Argyros, A. A. 2011. Efficient model-based 3D tracking of hand articulation using kinect. In Proc. of British Machine Vision Conference (BMVC).Google Scholar
- Olson, M., and Zhang, H. 2006. Silhouette extraction in hough space. Computer Graphics Forum (Proc. of EuroGraphics).Google Scholar
- Plankers, R., and Fua, P. 2003. Articulated soft objects for multi-view shape and motion capture. Pattern Analysis and Machine Intelligence (PAMI). Google ScholarDigital Library
- Qian, C., Sun, X., Wei, Y., Tang, X., and Sun, J. 2014. Realtime and robust hand tracking from depth. In Proc. of Comp. Vision and Pattern Recog. (CVPR). Google ScholarDigital Library
- Rehg, J. M., and Kanade, T. 1994. Visual tracking of high dof articulated structures: An application to human hand tracking. In Proc. of the European Conf. on Computer Vision (ECCV). Google ScholarDigital Library
- Rhee, T., Neumann, U., and Lewis, J. P. 2006. Human hand modeling from surface anatomy. In Proc. ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D). Google ScholarDigital Library
- Schroder, M., Maycock, J., Ritter, H., and Botsch, M. 2014. Real-time hand tracking using synergistic inverse kinematics. In Proc. of the Intern. Conf. on Robotics and Automation (ICRA).Google Scholar
- Sharp, T., Keskin, C., Robertson, D., Taylor, J., Shotton, J., Leichter, D. K. C. R. I., Wei, A. V. Y., Krupka, D. F. P. K. E., Fitzgibbon, A., and Izadi, S. 2015. Accurate, robust, and flexible real-time hand tracking. In Proc. of ACM Special Interest Group on Computer-Human Interaction (CHI). Google ScholarDigital Library
- Sridhar, S., Oulasvirta, A., and Theobalt, C. 2013. Interactive markerless articulated hand motion tracking using RGB and depth data. In Proc. of the Intern. Conf. on Computer Vision (ICCV). Google ScholarDigital Library
- Sridhar, S., Rhodin, H., Seidel, H.-P., Oulasvirta, A., and Theobalt, C. 2014. Real-time hand tracking using a sum of anisotropic gaussians model. In Proc. International Conference on 3D Vision (3DV). Google ScholarDigital Library
- Sridhar, S., Mueller, F., Oulasvirta, A., and Theobalt, C. 2015. Fast and robust hand tracking using detection-guided optimization. In Proc. of Comp. Vision and Pattern Recog. (CVPR).Google Scholar
- Sun, X., Wei, Y., Liang, S., Tang, X., and Sun, J. 2015. Cascaded hand pose regression. In Proc. of Comp. Vision and Pattern Recog. (CVPR).Google Scholar
- Tagliasacchi, A., and Li, H. 2016. Modern techniques and applications for real-time non-rigid registration. Proc. SIGGRAPH Asia (Technical Courses).Google Scholar
- Tagliasacchi, A., Schroeder, M., Tkach, A., Bouaziz, S., Botsch, M., and Pauly, M. 2015. Robust articulated-icp for real-time hand tracking. Computer Graphics Forum (Proc. Symposium on Geometry Processing, SGP).Google Scholar
- Tagliasacchi, A., Delame, T., Spagnuolo, M., Amenta, N., and Telea, A. 2016. 3d skeletons: A state-of-the-art report. Computer Graphics Forum (Proc. of EuroGraphics).Google Scholar
- Tan, D. J., Cashman, T., Taylor, J., Fitzgibbon, A., Tarlow, D., Khamis, S., Izadi, S., and Shotton, J. 2016. Fits like a glove: Rapid and reliable hand shape personalization. In Proc. of Comp. Vision and Pattern Recog. (CVPR).Google Scholar
- Tang, D., Yu, T.-H., and Kim, T.-K. 2013. Real-time articulated hand pose estimation using semi-supervised transductive regression forests. In Proc. of the Intern. Conf. on Computer Vision (ICCV). Google ScholarDigital Library
- Taylor, J., Stebbing, R., Ramakrishna, V., Keskin, C., Shotton, J., Izadi, S., Hertzmann, A., and Fitzgibbon, A. 2014. User-specific hand modeling from monocular depth sequences. In Proc. of Comp. Vision and Pattern Recog. (CVPR). Google ScholarDigital Library
- Taylor, J., Bordeaux, L., Cashman, T., Corish, B., Keskin, C., Soto, E., Sweeney, D., Valentin, J., Luff, B., Topalian, A., Wood, E., Khamis, S., Kohli, P., Sharp, T., Izadi, S., Banks, R., Fitzgibbon, A., and Shotton, J. 2016. Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. ACM Transactions on Graphics (Proc. of SIGGRAPH). Google ScholarDigital Library
- Tejani, A., Tang, D., Kouskouridas, R., and Kim, T.-K. 2014. Latent-class hough forests for 3d object detection and pose estimation. In Proc. of the European Conf. on Computer Vision (ECCV).Google Scholar
- Thiery, J.-M., Guy, E., and Boubekeur, T. 2013. Spheremeshes: Shape approximation using spherical quadric error metrics. ACM Transactions on Graphics (Proc. of SIGGRAPH). Google ScholarDigital Library
- Thiery, J.-M., Guy, E., Boubekeur, T., and Eisemann, E. 2016. Animated mesh approximation with sphere-meshes. ACM Transactions on Graphics (TOG). Google ScholarDigital Library
- Tompson, J., Stein, M., Lecun, Y., and Perlin, K. 2014. Real-time continuous pose recovery of human hands using convolutional networks. ACM Transactions on Graphics (TOG). Google ScholarDigital Library
- Vaillant, R., Barthe, L., Guennebaud, G., Cani, M.-P., Rohmer, D., Wyvill, B., Gourmel, O., and Paulin, M. 2013. Implicit skinning: Real-time skin deformation with contact modeling. ACM Transactions on Graphics (Proc. of SIGGRAPH). Google ScholarDigital Library
- Vaillant, R., Guennebaud, G., Barthe, L., Wyvill, B., and Cani, M.-P. 2014. Robust iso-surface tracking for interactive character skinning. ACM Transactions on Graphics (TOG). Google ScholarDigital Library
- Wang, R. Y., and Popovic, J. 2009. Real time hand tracking with a colored glove. ACM Transactions on Graphics (Proc. of SIGGRAPH). Google ScholarDigital Library
- Welch, G., and Foxlin, E. 2002. Motion tracking: No silver bullet, but a respectable arsenal. IEEE Comput. Graph. Appl.. Google ScholarDigital Library
Index Terms
- Sphere-meshes for real-time hand modeling and tracking
Recommendations
Accurate, Robust, and Flexible Real-time Hand Tracking
CHI '15: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing SystemsWe present a new real-time hand tracking system based on a single depth camera. The system can accurately reconstruct complex hand poses across a variety of subjects. It also allows for robust tracking, rapidly recovering from any temporary failures. ...
Real-Time Robust Hand Tracking Based on Camshift and Motion Velocity
ICDH '14: Proceedings of the 2014 5th International Conference on Digital HomeAlthough a lot of works have been done in the domain of hand tracking, it is still a challenge to robustly tracking hand motion. Traditional Cam shift algorithm which can efficiently tracking object in a simple scene is sensitive to the changing of ...
Hand tracking in bimanual movements
A general hand-tracking algorithm is presented for tracking hands in bimanual movements. The problem is approached from a neuroscience point of view. Using a dynamic model and some motor control phenomena, the movement of the hands during a bimanual ...
Comments