Abstract
The development of motion capturing devices like Microsoft Kinect poses new challenges in the exploitation of human-motion data for various application fields, such as computer animation, visual surveillance, sports or physical medicine. In such applications, motion segmentation is recognized as one of the most fundamental steps. Existing methods usually segment motions at the level of logical actions, like walking or jumping, to annotate the motion segments by textual descriptions. Although the action-level segmentation is convenient for motion summarization and action retrieval, it does not suit for general action-independent motion retrieval. In this paper, we introduce a novel semantically consistent algorithm for partitioning motions into short and further non-divisible segments. The property of semantic consistency ensures that the start and end of each segment are detected at semantically equivalent phases of movement to support general motion retrieval. The proposed segmentation algorithm first extracts relative distances between particular body parts as motion features. Based on these features, segments are consequently identified by constructing and analyzing a one-dimensional energy curve representing local motion changes. Experiments conducted on real-life motions demonstrate that the algorithm outperforms other relevant approaches in terms of recall and precision with respect to a user-defined ground truth. Moreover, it identifies segments at semantically equivalent phases with the highest accuracy.
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
Preview
Unable to display preview. Download preview PDF.
References
Arikan, O., Forsyth, D.A.: Interactive Motion Generation from Examples. In: 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 483–490. ACM (2002)
Assa, J., Caspi, Y., Cohen-Or, D.: Action Synopsis: Pose Selection and Illustration. In: SIGGRAPH 2005, pp. 667–676. ACM (2005)
Barbič, J., Safonova, A., Pan, J.Y., Faloutsos, C., Hodgins, J.K., Pollard, N.S.: Segmenting Motion Capture Data into Distinct Behaviors. In: Graphics Interface Conference (GI 2004), pp. 185–194. Canadian Human-Computer Communications Society (2004)
Choensawat, W., Choi, W., Hachimura, K.: Similarity Retrieval of Motion Capture Data Based on Derivative Features. Journal of Advanced Computational Intelligence and Intelligent Informatics 16(1), 13–23 (2012)
Deza, M.M., Deza, E.: Encyclopedia of Distances, 2nd edn. Springer (2013)
Fernandez-Baena, A., Susin, A., Lligadas, X.: Biomechanical Validation of Upper-Body and Lower-Body Joint Movements of Kinect Motion Capture Data for Rehabilitation Treatments. In: 4th International Conference on Intelligent Networking and Collaborative Systems (INCoS 2012), pp. 656–661 (2012)
Fu, A.W.C., Keogh, E., Lau, L.Y., Ratanamahatana, C.A., Wong, R.C.W.: Scaling and Time Warping in Time Series Querying. The VLDB Journal 17(4), 899–921 (2008)
Gong, W., Bagdanov, A.D., Roca, F.X., Gonzàlez, J.: Automatic Key Pose Selection for 3D Human Action Recognition. In: Perales, F.J., Fisher, R.B. (eds.) AMDO 2010. LNCS, vol. 6169, pp. 290–299. Springer, Heidelberg (2010)
Josiński, H., Switoński, A., Michalczuk, A., Wojciechowski, K.: Motion Capture as Data Source for Gait-Based Human Identification. Przeglad Elektrotechniczny 88, 201–204 (2012)
Kang, J., Badi, B., Zhao, Y., Wright, D.K.: Human Motion Modeling and Simulation. In: 6th International Conference on Robotics, Control and Manufacturing Technology (ROCOM 2006), pp. 62–67. WSEAS (2006)
Keogh, E., Palpanas, T., Zordan, V.B., Gunopulos, D., Cardle, M.: Indexing large human-motion databases. In: 30th International Conference on Very Large Data Bases (VLDB 2004), pp. 780–791. VLDB Endowment (2004)
Lan, R., Sun, H.: Automated Human Motion Segmentation via Motion Regularities. The Visual Computer, 1–19 (2013)
Lan, R., Sun, H., Zhu, M.: Text-Like Motion Representation for Human Motion Retrieval. In: Yang, J., Fang, F., Sun, C. (eds.) IScIDE 2012. LNCS, vol. 7751, pp. 72–81. Springer, Heidelberg (2013)
Li, C., Kulkarni, P.R., Prabhakaran, B.: Segmentation and recognition of motion capture data stream by classification. Multimedia Tools and Applications 35(1), 55–70 (2007)
Lin, Y., McCool, M.D.: Nonuniform Segment-Based Compression of Motion Capture Data. In: Bebis, G., et al. (eds.) ISVC 2007, Part I. LNCS, vol. 4841, pp. 56–65. Springer, Heidelberg (2007)
Liu, F., Zhuang, Y., Wu, F., Pan, Y.: 3D Motion Retrieval with Motion Index Tree. Computer Vision and Image Understanding 92(2-3), 265–284 (2003)
Lv, F., Nevatia, R.: Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 359–372. Springer, Heidelberg (2006)
Müller, M., Baak, A., Seidel, H.: Efficient and Robust Annotation of Motion Capture Data. In: ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2009), pp. 17–26 (2009)
Müller, M., Demuth, B., Rosenhahn, B.: An Evolutionary Approach for Learning Motion Class Patterns. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 365–374. Springer, Heidelberg (2008)
Müller, M., Röder, T., Clausen, M., Eberhardt, B., Krüger, B., Weber, A.: Documentation Mocap Database HDM05. Tech. Rep. CG-2007-2, Universität Bonn (2007)
Müller, M., Baak, A., Seidel, H.P.: Efficient and Robust Annotation of Motion Capture Data. In: ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2009), p. 10. ACM Press (2009)
Park, J.P., Lee, K.H., Lee, J.: Finding Syntactic Structures from Human Motion Data. Computer Graphics Forum 30(8), 2183–2193 (2011)
Ren, C., Lei, X., Zhang, G.: Motion Data Retrieval from Very Large Motion Databases. In: International Conference on Virtual Reality and Visualization (ICVRV 2011), pp. 70–77 (2011)
Sedmidubsky, J., Valcik, J., Balazia, M., Zezula, P.: Gait Recognition Based on Normalized Walk Cycles. In: Bebis, G., et al. (eds.) ISVC 2012, Part II. LNCS, vol. 7432, pp. 11–20. Springer, Heidelberg (2012)
Sedmidubsky, J., Valcik, J., Zezula, P.: A Key-Pose Similarity Algorithm for Motion Data Retrieval. In: Blanc-Talon, J., Kasinski, A., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2013. LNCS, vol. 8192, pp. 669–681. Springer, Heidelberg (2013)
Wang, P., Lau, R.W., Zhang, M., Wang, J., Song, H., Pan, Z.: A Real-time Database Architecture for Motion Capture Data. In: 19th International Conference on Multimedia (MM 2011), pp. 1337–1340. ACM (2011)
Wu, S., Wang, Z., Xia, S.: Indexing and Retrieval of Human Motion Data by a Hierarchical Tree. In: 16th Symposium on Virtual Reality Software and Technology (VRST 2009), pp. 207–214. ACM Press (2009)
Xiao, J., Zhuang, Y., Yang, T., Wu, F.: An Efficient Keyframe Extraction from Motion Capture Data. In: Nishita, T., Peng, Q., Seidel, H.-P. (eds.) CGI 2006. LNCS, vol. 4035, pp. 494–501. Springer, Heidelberg (2006)
Zhou, F., De la Torre Frade, F., Hodgins, J.K.: Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(3), 582–596 (2013)
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
Balazia, M., Sedmidubsky, J., Zezula, P. (2014). Semantically Consistent Human Motion Segmentation. In: Decker, H., Lhotská, L., Link, S., Spies, M., Wagner, R.R. (eds) Database and Expert Systems Applications. DEXA 2014. Lecture Notes in Computer Science, vol 8644. Springer, Cham. https://doi.org/10.1007/978-3-319-10073-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-10073-9_36
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10072-2
Online ISBN: 978-3-319-10073-9
eBook Packages: Computer ScienceComputer Science (R0)