Abstract
This paper proposes a new approach to model human arm pose configuration from still images based on learned features and arm part structure constraints. The subjects in still images have no assumption with regards to clothing style, action category and background, so our model has to accommodate these uncertainties. Proposed approach uses an energy model that incorporates the dependence relationships among arm joints and arm parts, where the potentials represent their occurrence probabilities. Positive and negative instances are computed from input image, using multi-scale image patches to capture the details of arm joints and arm parts. A joint convolutional neural network is then developed for feature extraction. Local rigidity of arm part is used to constrain occurrence of arm joints and arm parts, and these constraints can be efficiently incorporated in dynamic programming for human arm pose inference. Our experimental results show better performance than alternative approaches using hand-crafted features for various still images.
Similar content being viewed by others
References
Wang, L., Yung, N.: Bayesian 3d model based human detection in crowded scenes using efficient optimization. In: 2011 IEEE Workshop on Applications of Computer Vision (WACV), pp. 557–563. IEEE (2011)
Zuffi, S., Romero, J., Schmid, C., Black, M.J.: Estimating human pose with flowing puppets. In: IEEE International Conference on Computer Vision (ICCV), pp. 3312–3319. IEEE (2013)
Li, C., Yung, N.: Action categorization based on arm pose modeling. In: Proceedings of the 9th International Conference on Computer Vision Theory and Applications, vol. 2, pp. 39–47 (2014)
Li, C., Yung, N.: Categorization of human actions with high dynamics in upper extremities based on arm pose modeling. Mach. Vis. Appl. 26(5), 619–632 (2015)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1385–1392. IEEE (2011)
Sapp, B., Taskar, B.: Modec: multimodal decomposable models for human pose estimation. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3674–3681. IEEE (2013)
Palastanga, N., Field, D., Soames, R.: Anatomy and Human Movement: Structure and Function, vol. 20056. Elsevier Health Sciences, Amsterdam (2006)
Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3476–3483. IEEE (2013)
Conaire, C., O’Connor, N., Smeaton, A.: Detector adaptation by maximising agreement between independent data sources. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–6. IEEE (2007)
Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognit. 29(1), 51–59 (1996)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, vol. 1, pp. 886–893. IEEE (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. J. Comput. Vis. 43(1), 7–27 (2001)
Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing features: efficient boosting procedures for multiclass object detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 762–769. IEEE (2004)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: The Handbook Of Brain Theory and Neural Networks, vol. 3361(10) (1995)
Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653–1660 (2014)
Chen, X., Yuille, A.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Neural Information Processing Systems, pp. 1736–1744 (2014)
Jain, A., Tompson, J., LeCun, Y., Bregler, C.: Modeep: a deep learning framework using motion features for human pose estimation. In: Computer Vision-ACCV, pp. 302–315 (2014)
Pfister, T., Simonyan, K., Charles, J., Zisserman, A.: Deep convolutional neural networks for efficient pose estimation in gesture videos. In: Computer Vision-ACCV, pp. 538–552 (2014)
Ramakrishna, V., Munoz, D., Hebert, M., Bagnell, J.A., Sheikh, Y.: Pose machines: articulated pose estimation via inference machines. In: Computer Vision-ECCV, pp. 33–47. Springer, Berlin (2014)
Park, D., Ramanan, D.: N-best maximal decoders for part models. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2627–2634. IEEE (2011)
LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. In: Predicting structured data. MIT press (2006)
Felzenszwalb, P.F., Zabih, R.: Dynamic programming and graph algorithms in computer vision. IEEE Trans. Pattern Anal. Mach. Intell. 33(4), 721–740 (2011)
Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3d human pose annotations. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1365–1372. IEEE (2009)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Sermanet, P., LeCun, Y.: Traffic sign recognition with multi-scale convolutional networks. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2809–2813. IEEE (2011)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735–1742. IEEE (2006)
Liu, C.: Probabilistic siamese network for learning representations. Master’s thesis, University of Toronto (2013)
Delalleau, O., Bengio, Y.: Parallel Stochastic Gradient Descent. CIAR Summer School, Toronto (2007)
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy), vol. 4, p. 3. Austin, TX (2010)
Goodfellow, I.J., Warde-Farley, D., Lamblin, P., Dumoulin, V., Mirza, M., Pascanu, R., Bergstra, J., Bastien, F., Bengio, Y.: Pylearn2: a machine learning research library (2013). arXiv preprint arXiv:1308.4214
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Acknowledgments
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla k40c GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, C., Yung, N.H.C., Sun, X. et al. Human arm pose modeling with learned features using joint convolutional neural network. Machine Vision and Applications 28, 1–14 (2017). https://doi.org/10.1007/s00138-016-0796-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-016-0796-0