Abstract
In this work, we address the problem of human pose estimation in still images by proposing a holistic model for learning the appearance of the human body from image patches. These patches, which are randomly chosen, are used for extracting features and training a regression forest. During training, a mapping between image features and human poses, defined by joint offsets, is learned; while during prediction, the body joints are estimated with an efficient mode-seeking algorithm. In comparison to other holistic approaches, we can recover body poses from occlusion or noisy data. We demonstrate the power of our method in two publicly available datasets and propose a third one. Finally, we achieve state-of-the-art results in comparison to other approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Moeslund, T.B., Hilton, A., Krüger, V., Sigal, L.: Visual Analysis of Humans. Springer (2011)
Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: IEEE CVPR, pp. 588–595 (2013)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: IEEE CVPR, pp. 1385–1392 (2011)
Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: People detection and articulated pose estimation. In: IEEE CVPR, pp. 1014–1021 (2009)
Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61(1), 55–79 (2005)
Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Transactions on Computers 22(1), 67–92 (1973)
Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S.: 3d pictorial structures for multiple human pose estimation. In: IEEE CVPR (2014)
Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: IEEE CVPR, pp. 1465–1472 (2011)
Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. TPAMI 28(1), 44–58 (2006)
Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Rogez, G., Rihan, J., Ramalingam, S., Orrite, C., Torr, P.H.: Randomized trees for human pose detection. In: IEEE CVPR, pp. 1–8 (2008)
Urtasun, R., Darrell, T.: Sparse probabilistic regression for activity-independent human pose inference. In: IEEE CVPR, pp. 1–8 (2008)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: IEEE ICCV, pp. 415–422 (2011)
Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., Moore, R.: Real-time human pose recognition in parts from single depth images. Communications of the ACM 56(1), 116–124 (2013)
Andriluka, M., Roth, S., Schiele, B.: Discriminative appearance models for pictorial structures. IJCV 99(3), 259–280 (2012)
Eichner, M., Ferrari, V.: Better appearance models for pictorial structures (2009)
Sapp, B., Toshev, A., Taskar, B.: Cascaded models for articulated pose estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 406–420. Springer, Heidelberg (2010)
Kazemi, V., Burenius, M., Azizpour, H., Sullivan, J.: Multi-view body part recognition with random forests. In: BMVC (2013)
Dantone, M., Gall, J., Leistner, C., Van Gool, L.: Human pose estimation using body parts dependent joint regressors. In: IEEE CVPR, pp. 3041–3048 (2013)
Zuffi, S., Freifeld, O., Black, M.J.: From pictorial structures to deformable structures. In: IEEE CVPR, pp. 3546–3553 (2012)
Bergtholdt, M., Kappes, J., Schmidt, S., Schnörr, C.: A study of parts-based object class detection using complete graphs. IJCV 87(1-2), 93–117 (2010)
Sun, M., Savarese, S.: Articulated part-based model for joint object detection and pose estimation. In: IEEE ICCV, pp. 723–730 (2011)
Gavrila, D.M.: A bayesian, exemplar-based approach to hierarchical shape matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(8), 1408–1421 (2007)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: IEEE ICCV, pp. 750–757 (2003)
Ionescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. In: IEEE ICCV, pp. 2220–2227 (2011)
Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: IEEE ICCV, pp. 1365–1372 (2009)
Wang, Y., Tran, D., Liao, Z.: Learning hierarchical poselets for human parsing. In: IEEE CVPR, pp. 1705–1712 (2011)
Criminisi, A., Shotton, J.: Decision forests for computer vision and medical image analysis. Springer (2013)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE CVPR, vol. 1, pp. 886–893 (2005)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9), 1627–1645 (2010)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. TPAMI 24(5), 603–619 (2002)
Pishchulin, L., Jain, A., Andriluka, M., Thormahlen, T., Schiele, B.: Articulated people detection and pose estimation: Reshaping the future. In: IEEE CVPR, pp. 3178–3185 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Belagiannis, V., Amann, C., Navab, N., Ilic, S. (2014). Holistic Human Pose Estimation with Regression Forests. In: Perales, F.J., Santos-Victor, J. (eds) Articulated Motion and Deformable Objects. AMDO 2014. Lecture Notes in Computer Science, vol 8563. Springer, Cham. https://doi.org/10.1007/978-3-319-08849-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-08849-5_3
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08848-8
Online ISBN: 978-3-319-08849-5
eBook Packages: Computer ScienceComputer Science (R0)