Abstract
In this paper, we introduce a novel and robust body pose estimation method with single depth image, whereby it is possible to provide the skeletal configuration of the body with significant accuracy even in the condition of severe body deformations. In order for the precise identification, we propose a novel feature descriptor based on a geodesic path over the body surface by accumulating sequence of characters correspond to the path vectors along body deformations, which is referred to as GPS (Geodesic Path Sequence). We also incorporate the length of each GPS into a joint entropy-based objective function representing both class and structural information, instead of the typical objective considering only class labels in training the random forest classifier. Furthermore, we exploit a skeleton matching method based on the geodesic extrema of the body, which enhances more robustness to joints misidentification. The proposed solutions yield more spatially accurate predictions for the body parts and skeletal joints. Numerical and visual experiments with our generated data confirm the usefulness of the method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shotton, J., et al.: Real-time human pose recognition in parts from a single depth image. In: Cipolla, R., Battiato, S., Farinella, G. (eds.) Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 1297–1304. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-28661-2_5
Shotton, J., et al.: Efficient human pose estimation from single depth images. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2821–2840 (2013)
Breiman, L.: Random forests. J. Mach. Learn. 45, 5–32 (2001)
Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: Criminisi, A., Shotton, J. (eds.) Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 1022–1029. Springer, London (2009). https://doi.org/10.1007/978-1-4471-4929-3_11
Tan, D.J., Ilic, S.: Multi-forest tracker: a chameleon in tracking. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 1202–1209 (2014)
Dapogny, A., Bailly, K., Dubuisson, S.: Pairwise conditional random forests for facial expression recognition. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 3783–3791 (2015)
Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: Proceedings of International Conference on Computer Vision, pp. 415–422 (2011)
Schwarz, L., Mkhitaryan, A., Mateus, D., Navab, N.: Estimating human 3d pose from time-of-flight images based on geodesic distances and optical flow. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, Santa Barbara, CA, pp. 700–706 (2011)
Baak, A., Müller, M., Bharaj, G., Seidel, H., Theobalt, C.: A data-driven approach for real-time full body pose reconstruction from a depth camera. In: Proceedings of International Conference on Computer Vision, pp. 1092–1099 (2011)
Kontschieder, P., Kohli, P., Shotton, J., Criminisi, A.: GeoF: geodesic forests for learning coupled predictors. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 65–72 (2013)
Glocker, B., Pauly, O., Konukoglu, E., Criminisi, A.: Joint classification-regression forests for spatially structured multi-object segmentation. In: Proceedings of European Conference on Computer Vision, Florence, Italy, pp. 870–881 (2012)
Plagemann, C., Ganapathi, V., Koller, D., Thrun, S.: Real-time identification and localization of body parts from depth images. In: Proceedings of International Conference on Robotics and Automation, pp. 3108–3113 (2010)
Salvador, S., Chan, P.: FastDTW: toward accurate dynamic time warping in linear time and space. In: KDD Workshop on Mining Temporal and Sequential Data, pp. 70–80 (2004)
Kuhn, H.: The hungarian method for the assignment problem. Nav. Res. Logist. Q. 2, 83–97 (1955)
Acknowledgments
This research is supported by Ministry of Culture, Sports and Tourism (MCST) and Korea Creative Content Agency (KOCCA) in the Culture Technology (CT) Research & Development Program R2016030043.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, J., Kim, H. (2018). Robust Geodesic Skeleton Estimation from Body Single Depth. In: Blanc-Talon, J., Helbert, D., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2018. Lecture Notes in Computer Science(), vol 11182. Springer, Cham. https://doi.org/10.1007/978-3-030-01449-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-01449-0_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01448-3
Online ISBN: 978-3-030-01449-0
eBook Packages: Computer ScienceComputer Science (R0)