Abstract
We propose a novel model-based approach to activity recognition using high-level primitives that are derived from a human body model estimated from sensor data. Using short but fixed positions of the hands and turning points of hand movements, a continuous data stream is segmented in short segments of interest. Within these segments, joint boosting enables the automatic discovery of important and distinctive features ranging from motion over posture to location. To demonstrate the feasibility of our approach we present the user-dependent and across-user results of a study with 8 participants. The specific scenario that we study is composed of 20 activities in quality inspection of a car production process.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Deng, J., Tsui, H.: An HMM-based approach for gesture segmentation and recognition. In: 15th Int. Conf. on Pattern Recognition, vol. 2, pp. 679–682 (2000)
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. The Annals of Statistics 38(2), 337–374 (2000)
Kallio, S., Kela, J., Korpipää, P., Mäntyjärvi, J.: User independent gesture interaction for small handheld devices. IJPRAI 20(4) (2006)
Lester, J., Choudhury, T., Kern, N., Borriello, G., Hannaford, B.: A Hybrid Discriminative/Generative Approach for Modeling Human Activities. In: Proc. of the International Joint Conference on Artificial Intelligence (IJCAI) (2005)
Mäntylä, V.-M., Mäntyjärvi, J., Seppänen, T., Tuulari, E.: Hand gesture recognition of a mobile device user. In: IEEE International Conference on Multimedia and Expo. (2000)
Ogris, G., Stiefmeier, T., Lukowicz, P., Tröster, G.: Using a complex Multi-modal On-body Sensor System for Activity Spotting. In: 12th IEEE International Symposium on Wearable Computers, Pittsburgh, USA (2008)
Ogris, G., Kreil, M., Lukowicz, P.: Using FSR based muscle activity monitoring to recognize manipulative arm gestures. In: Int. Symp. on Wear. Comp. (October 2007)
Stiefmeier, T., Roggen, D., Tröster, G.: Gestures are strings: efficient online gesture spotting and classification using string matching. In: Proceedings of the ICST 2nd international conference on Body area networks (2007)
Stiefmeier, T., Roggen, D., Ogris, G., Lukowicz, P., Tröster, G.: Wearable activity tracking in car manufacturing. IEEE Pervasive Computing 7(2), 42–50 (2008)
Stiefmeier, T., Ogris, G., Junker, H., Lukowicz, P., Tröster, G.: Combining motion sensors and ultrasonic hands tracking for continuous activity recognition in a maintenance scenario. In: Int. Symp. on Wear. Comp. (October 2006)
Torralba, A., Murphy, K.P.: Sharing Visual Features for Multiclass and Multiview Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. 29(5) (2007)
Ubisense, http://www.ubisense.de/content/14.html
Viola, P.A., Jones, M.J.: Robust real-time face detection. Int. Journal on Comp. Vision 57(2), 137–154 (2004)
Ward, J.A., Lukowicz, P., Tröster, G., Starner, T.: Activity recognition of assembly tasks using body-worn microphones and accelerometers. IEEE Trans. Pattern Analysis and Machine Intell. 28(10), 1553–1567 (2006)
XSens Motion Technologies, http://xsens.com/
XSens Moven, http://www.moven.com/en/home_moven.php
Zinnen, A., Schiele, B.: A new Approach to Enable Gesture Recognition in Continuous Data Streams. In: 12th IEEE International Symposium on Wearable Computers, September 28 - October 1 (2008)
Zinnen, A., Laerhoven, K., Schiele, B.: Toward Recognition of Short and Non-repetitive Activities from Wearable Sensors. In: Schiele, B., Dey, A.K., Gellersen, H., de Ruyter, B., Tscheligi, M., Wichert, R., Aarts, E., Buchmann, A. (eds.) AmI 2007. LNCS, vol. 4794, pp. 142–158. Springer, Heidelberg (2007)
Pylvänäinen, T.: Accelerometer based gesture recognition using continuous HMMS. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3522, pp. 639–646. Springer, Heidelberg (2005)
Ryoo, M.S., Aggarwal, J.K.: Recognition of Composite Human Activities through Context-Free Grammar Based Representation. In: Computer Vision and Pattern Recognition, vol. 2, pp. 1709–1718 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zinnen, A., Wojek, C., Schiele, B. (2009). Multi Activity Recognition Based on Bodymodel-Derived Primitives. In: Choudhury, T., Quigley, A., Strang, T., Suginuma, K. (eds) Location and Context Awareness. LoCA 2009. Lecture Notes in Computer Science, vol 5561. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01721-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-01721-6_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01720-9
Online ISBN: 978-3-642-01721-6
eBook Packages: Computer ScienceComputer Science (R0)