Human pose estimation; Orientation; Machine learning
Résumé :
[en] In this paper, we present a two-step methodology to improve existing human pose estimation methods from a single depth image. Instead of learning the direct mapping from the depth image to the 3D pose, we first estimate the orientation of the standing person seen by the camera and then use this information to dynamically select a pose estimation model suited for this particular orientation. We evaluated our method on a public dataset of realistic depth images with precise ground truth joints location. Our experiments show that our method decreases the error of a state-of-the-art pose estimation method by 30%, or reduces the size of the needed learning set by a factor larger than 10.
Centre de recherche :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège Telim
Disciplines :
Sciences informatiques
Auteur, co-auteur :
Azrour, Samir ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Pierard, Sébastien ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Geurts, Pierre ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
Van Droogenbroeck, Marc ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Langue du document :
Anglais
Titre :
A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically
Date de publication/diffusion :
septembre 2017
Nom de la manifestation :
Advanced Concepts for Intelligent Vision Systems (ACIVS 2017)
Organisateur de la manifestation :
Rudi Penne and Paul Scheunders
Lieu de la manifestation :
Antwerpen, Belgique
Date de la manifestation :
from 18-09-2017 to 21-09-2017
Manifestation à portée :
International
Titre de l'ouvrage principal :
Advanced Concepts for Intelligent Vision Systems
Maison d'édition :
Springer
Collection et n° de collection :
Lecture Notes in Computer Science, volume 10617
Pagination :
3-14
Peer reviewed :
Peer reviewed
Organisme subsidiant :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: IEEE International Conference Computer Vision (ICCV), Kyoto, September/October 2009, pp. 1365-1372 (2009)
Corazza, S., Gambaretto, E., Mundermann, L., Andriacchi, T.: Automatic generation of a subject-specific model for accurate markerless motion capture and biomechanical applications. IEEE Trans. Biomed. Eng. 57(4), 806-812 (2010)
Corazza, S., Mündermann, L., Gambaretto, E., Ferrigno, G., Andriacchi, T.: Markerless motion capture through visual hull, articulated ICP and subject specific model generation. Int. J. Comput. Vis. 87(1-2), 156-169 (2010)
Criminisi, A., Shotton, J. (eds.): Decision Forests for Computer Vision and Medical Image Analysis. Springer, Heidelberg (2013). https://doi.org/10.1007/978-1-4471-4929-3
Gall, J., Stoll, C., De Aguiar, E., Theobalt, C., Rosenhahn, B., Seidel, H.-P.: Motion capture using joint skeleton tracking and surface estimation. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), pp. 1746-1753 (2009)
Ganapathi, V., Plagemann, C., Koller, D., Thrun, S.: Real-time human pose tracking from range data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 738-751. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_53
Ganapathi, V., Plagemann, C., Thrun, S., Koller, D.: Real time motion capture using a single time-of-flight camera. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, pp. 755-762, June 2010
Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: IEEE International Conference Computer Vision (ICCV), Barcelona, Spain, pp. 415-422, November 2011
Jung, H., Lee, S., Heo, Y., Yun, I.: Random tree walk toward instantaneous 3D human pose estimation. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), pp. 2467-2474, June 2015
Jung, H.Y., Suh, Y., Moon, G., Lee, K.M.: A sequential approach to 3D human pose estimation: separation of localization and identification of body joints. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 747-761. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_45
Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150-162 (1994)
Piérard, S., Leroy, D., Hansen, J.-F., Van Droogenbroeck, M.: Estimation of human orientation in images captured with a range camera. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2011. LNCS, vol. 6915, pp. 519-530. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23687-7_47
Roberston, D., Shotton, J., Sharp, T.: The sherwood software library. In: Criminisi and Shotton [8], Chap. 22, pp. 333-342
Shafaei, A., Little, J.: Real-time human motion capture with multiple depth cameras. In: Conference on Computer and Robot Vision (CRV), pp. 24-31 (2016)
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, pp. 1297-1304, June 2011
Shotton, J., Girshick, R., Fitzgibbon, A., Sharp, T., Cook, M., Finocchio, M., Moore, R., Kohli, P., Criminisi, A., Kipman, A., Blake, A.: Efficient human pose estimation from single depth images. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2821-2840 (2013)
Sigal, L., Black, M.: Guest editorial: state of the art in image- and video-based human pose and motion estimation. Int. J. Comput. Vis. 87(1), 1-3 (2010)
Tompson, J., Jain, A., Lecun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advance in Neural Information Processing Systems (NIPS), pp. 1799-1807. Curran Associates Inc. (2014)
Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, pp. 1653-1660 (2014)
Wei, X., Zhang, P., Chai, J.: Accurate realtime full-body motion capture using a single depth camera. ACM Trans. Graph. 31(6), 188.1-188.12 (2012)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, pp. 1385-1392 (2011)
Ye, M., Yang, R.: Real-time simultaneous pose and shape estimation for articulated objects using a single depth camera. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR), pp. 2345-2352, June 2014
