Abstract
We present a discriminative deformable part model for the recovery of qualitative pose, inferring coarse pose labels (e.g., left, front-right, back), a task which we expect to be more robust to common confounding factors that hinder the inference of exact 2D or 3D joint locations. Our approach automatically selects parts that are predictive of qualitative pose and trains their appearance and deformation costs to best discriminate between qualitative poses. Unlike previous approaches, our parts are both selected and trained to improve qualitative pose discrimination and are shared by all the qualitative pose models. This leads to both increased accuracy and higher efficiency, since fewer parts models are evaluated for each image. In comparisons with two state-of-the-art approaches on a public dataset, our model shows superior performance.
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
Hofmann, M., Gavrila, D.M.: Multi-view 3D human pose estimation combining single-frame recovery, temporal integration and model adaptation. In: CVPR (2009)
Wei, X.K., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: ICCV (2009)
Guan, P., Weiss, A., Balan, A.O., Black, M.J.: Estimating human shape and pose from a single image. In: ICCV (2009)
Andriluka, M., Roth, S., Schiele, B.: Monocular 3D pose estimation and tracking by detection. In: CVPR (2010)
Daubney, B., Xie, X.: Tracking 3D human pose with large root node uncertainty. In: CVPR (2011)
Gall, J., Yao, A., Van Gool, L.: 2D Action Recognition Serves 3D Human Pose Estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 425–438. Springer, Heidelberg (2010)
Lonescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. In: ICCV (2011)
Chen, C., Heili, A., Odobez, J.: Combined estimation of location and body pose in surveillance video. In: AVSS (2011)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) (2010)
Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting People Using Mutually Consistent Poselet Activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 168–181. Springer, Heidelberg (2010)
Maji, S., Bourdev, L., Malik, J.: Action recognition from a distributed representation of pose and appearance. In: CVPR (2011)
Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. IEEE Transactions on Computer 22 (1973)
Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. International Journal of Computer Vision (IJCV), 55–79 (2005)
Singh, V.K., Nevatia, R.: Action recognition in cluttered dynamic scenes using pose-specific part models. In: ICCV (2011)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR (2011)
Sapp, B., Jordan, C., Tasker, B.: Adaptive pose priors for pictorial structures. In: CVPR (2010)
Singh, V.K., Nevatia, R., Huang, C.: Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 314–327. Springer, Heidelberg (2010)
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)
Eichner, M., Ferrari, V.: We Are Family: Joint Pose Estimation of Multiple Persons. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 228–242. Springer, Heidelberg (2010)
Gu, C., Ren, X.: Discriminative Mixture-of-Templates for Viewpoint Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 408–421. Springer, Heidelberg (2010)
Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3D human pose annotations. In: ICCV (2009)
Maire, M., Yu, S.X., Perona, P.: Object detection and segmentation from joint embedding of parts and pixels. In: ICCV (2011)
Yang, W., Wang, Y., Mori, G.: Recognizing human actions from still images with latent poses. In: CVPR (2010)
Farrell, R., Oza, O., Zhang, N., Morariu, V.I., Darrell, T., Davis, L.S.: Subordinate categorization using volumetric primitives and pose-normalized appearance. In: ICCV (2011)
Bourdev, L., Maji, S., Malik, J.: Describing people: Poselet-based approach to attribute classification. In: ICCV (2011)
Wang, Y., Tran, D., Liao, Z.: Learning hierarchical poselets for human parsing. In: CVPR (2011)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, H., Morariu, V.I., Davis, L.S. (2013). Qualitative Pose Estimation by Discriminative Deformable Part Models. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7725. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37444-9_57
Download citation
DOI: https://doi.org/10.1007/978-3-642-37444-9_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37443-2
Online ISBN: 978-3-642-37444-9
eBook Packages: Computer ScienceComputer Science (R0)