Abstract
Human parsing is a challenging task because it is difficult to obtain accurate results of each part of human body. Precious Boltzmann Machine based methods reach good results on segmentation but are poor expression on human parts. In this paper, an approach is presented that exploits Shape Boltzmann Machine networks to improve the accuracy of human body parsing. The proposed Curve Correction method refines the final segmentation results. Experimental results show that the proposed method achieves good performance in body parsing, measured by Average Pixel Accuracy (aPA) against state-of-the-art methods on Penn-Fudan Pedestrians dataset and Pedestrian Parsing Surveillance Scenes dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fowlkes, C.C., Bo, Y.: Shape-based pedestrian parsing. In: IEEE Conference on Computer Vision and Pattern Recognition (2011)
Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: IEEE International Conference on Computer Vision (2009)
Lin, L., Yang, W., Luo, P.: Clothing co-parsing by joint image segmentation and labeling. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Luis, K., Ortiz, E., Berg, T.L., Yamaguchi, K., Hadi, M.: Parsing clothing in fashion photographs. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
Rauschert, I., Collins, R.T.: A generative model for simultaneous estimation of human body shape and pixel-level segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 704–717. Springer, Heidelberg (2012)
Williams, C., Ali Eslami, S.M.: A generative model for parts-based object segmentation. In: Advances in Neural Information Processing Systems, pp. 272–281 (2012)
Williams, C.K.I., Winn, J., Eslami, S.M.A., Heess, N.: The shape boltzmann machine: a strong model of object shape. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
Wang, X., Tang, X., Luo, P., Tian, Y.: Switchable deep network for pedestrian detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Salakhutdinov, R., Fidler, S., Zhu, Y., Urtasun, R.: Segdeepm: exploiting segmentation and context in deep neural networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)
Girshick, R., Malik, J., Hariharan, B., Arbelez, P.: Hypercolumns for object segmentation and fine-grained localization, eprint (2014). arXiv:1411.5752
Darrell, T., Malik, J., Girshick, R., Donahue, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Wang, L.-M., Shi, J., Song, G., Shen, I.-F.: Object detection combining recognition and segmentation. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part I. LNCS, vol. 4843, pp. 189–199. Springer, Heidelberg (2007)
Tang, X., Wang, X.: Pedestrian parsing via deep decompositional network. In: IEEE International Conference on Computer Vision (2013)
Simon, M., Yang, J., Safar, Y.: Max-margin boltzmann machines for object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Fowlkes, C., Malik, J., Arbelez, P., Maire, M.: Contour detection and hierarchical image segmentation. In: IEEE Transaction on Software Engineering (2011)
Puzicha, J., Belongie, S., Malik, J.: Shape matching and object recognition using shape contexts. In: IEEE International Conference on Computer Science and Information Technology (2002)
Liu, S., Guo, X., Lin, L., Cao, X., Zhang, H.: Sym-fish: a symmetry-aware flip invariant sketch histogram shape descriptor. In: IEEE International Conference on Computer Vision (2013)
Nowozin, S., Kim, S., Yoo, C.D., Kohli, P.: Image segmentation using higher-order correlation clustering. IEEE Trans. Pattern Anal. Mach. Intell. 36(9), 1761–1774 (2014)
Balan, A.O., Sigal, L., Black, M.J.: Humaneva: synchronized video and motion capture dataset for evaluation of articulated human motion. In: IEEE International Conference on Computer Vision (2006)
Acknowledgements
This work is supported by the National High Technology Development Plan (863 Plan) under Grant No. 2011AA01A205, the National Significant Science and Technology Projects of China under Grant No. 2013ZX01039001-002-003, the NSFC project under Grant No. U1433112 and No. 61170253. We also thank the support from the academic program of Tencent Inc.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, Q., Yuan, C., Huang, F., Wang, C. (2015). Human Parsing via Shape Boltzmann Machine Networks. In: Ho, YS., Sang, J., Ro, Y., Kim, J., Wu, F. (eds) Advances in Multimedia Information Processing -- PCM 2015. PCM 2015. Lecture Notes in Computer Science(), vol 9314. Springer, Cham. https://doi.org/10.1007/978-3-319-24075-6_63
Download citation
DOI: https://doi.org/10.1007/978-3-319-24075-6_63
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24074-9
Online ISBN: 978-3-319-24075-6
eBook Packages: Computer ScienceComputer Science (R0)