Abstract
In this study, a new method allowing recognizing and segmenting everyday life actions is proposed. Only one camera is utilized without calibration. Viewpoint invariance is obtained by several acquisitions of the same action. To enhance robustness, each sequence is characterized globally: a detection of moving areas is first computed on each image. All these binary points form a volume in the three-dimensional (3D) space (x,y,t). This volume is characterized by its geometric 3D moments. Action recognition is then carried out by computing the Mahalanobis distance between the vector of features of the action to be recognized and those of the reference database. Results, which validate the suggested approach, are presented on a base of 1662 sequences performed by several persons and categorized in eight actions. An extension of the method for the segmentation of sequences with several actions is also proposed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE transactions on pattern analysis and machine intelligence 23(3) (2001)
Chomat, O., Crowley, J.L.: Probabilistic recognition of activity using local appearance. Computer Vision and Pattern Recognition, Colorado, USA (1999)
Gavrila, D.M.: The visual analysis of human movement: a survey. Computer Vision and Image Understanding 73 (1), 82–98 (1999)
Hongeng, S., Bremond, F., Nevatia, R.: Bayesian framework for video surveillance application. In: International Conference on Computer Vision, Barcelona, Spain (2000)
Hu, M.K.: Visual pattern recognition by moment invariants. IRE Trans. on Information Theory IT-8, 179–187 (1962)
Martin, J., Crowley, J.L.: An appearance based approach to gesture recognition. In: International Conference on Image Analysis and Processing, Florence, Italia (1997)
Masoud, O., Papanikolopoulos, N.: Recognizing human activities. In: Conf. On advanced video and signal based surveillance (2003)
Porikli, F., Tuzel, O.: Human body tracking by adaptive background models and meanshift analysis. In: IEEE International Workshop on Performance Evaluation of Tracking and Surveillanc (March 2003)
Prevost, L., Oudot, L., Moises, A., Michel-Sendis, C., Milgram, M.: Hybrid generative/ discriminative classifier for unconstrained character recognition. Pattern Recognition Letters (2005) (to appear)
Rabiner, L.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–285 (1989)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. Computer Vision and Pattern Recognition 2, 246–252 (1999)
Sun, X., Chen, C., Manjunath, B.S.: Probabilistic motion parameter models for human activity recognition. In: International Conference on Pattern Recognition, pp. 443–446 (2002)
Wang, J.J., Singh, S.: Video Analysis of Human Dynamics - a survey. Real-time Imaging Journal 9 (5), 320–345 (2003)
Zelnik-Manor, L., Irani, M.: Event based analysis of video. Computer Vision and Pattern Recognition, 123–130 (2001)
Yamato, J., Ohya, J., Ishii, K.: Recognizing Human Action in Time-Sequential Images using Hidden Markov Models. In: Computer Vision and Pattern Recognition, pp. 379–385. IL, Los Alamitos June 15-18 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mokhber, A., Achard, C., Qu, X., Milgram, M. (2005). Action Recognition with Global Features. In: Sebe, N., Lew, M., Huang, T.S. (eds) Computer Vision in Human-Computer Interaction. HCI 2005. Lecture Notes in Computer Science, vol 3766. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11573425_11
Download citation
DOI: https://doi.org/10.1007/11573425_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29620-1
Online ISBN: 978-3-540-32129-3
eBook Packages: Computer ScienceComputer Science (R0)