Abstract
We address the empirical feature selection for tracker-less recognition of human actions. We rely on the appearance plus motion model over several video frames to model the human movements. We use the L2Boost algorithm, a versatile boosting algorithm which simplifies the gradient search. We study the following options in the feature computation and learning: (i) full model vs. component-wise model, (ii) sampling strategy of the histogram cells and (iii) number of previous frames to include, amongst others. We select the features’ parameters that provide the best compromise between performance and computational efficiency and apply the features in a challenging problem, the tracker-less and detection-less human activity recognition.
This work was supported by FCT (ISR/IST plurianual funding through the PIDDAC Program) and partially funded by EU Project First-MM (FP7-ICT-248258), EU Project HANDLE (FP7-ICT-231640) and by the project CMU-PT/SIA/0023/2009 under the Carnegie Mellon-Portugal Program.
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
Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: IEEE CVPR 2008, pp. 1–8 (2008)
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: IEEE ICCV 2005, vol. 2, pp. 1395–1402 (2005)
Buhlmann, P., Yu, B.: Boosting with the l2 loss: Regression and classification. Journal of the American Statistical Association 98, 324–339 (2003)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the CVPR 2005, Washington, DC, USA, pp. 886–893 (2005)
Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428–441. Springer, Heidelberg (2006)
Gerónimo, D., López, A., Sappa, A., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE PAMI 32(7), 1239–1258 (2010)
Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A Biologically Inspired System for Action Recognition. In: Proceedings ICCV, pp. 1–8 (October 2007)
Ogale, A.S., Aloimonos, Y.: A roadmap to the integration of early visual modules. International Journal of Computer Vision 72(1), 9–25 (2007)
Poppe, R.: A survey on vision-based human action recognition. Image and Vision Computing 28(6), 976–990 (2010)
Ribeiro, P.C., Moreno, P., Santos-Victor, J.: Unsupervised and online update of boosted temporal models: the UAL2boost. In: Proc. of ICMLA (December 2010)
Schindler, K., van Gool, L.: Action snippets: How many frames does human action recognition require? In: IEEE CVPR 2008, June 2008, pp. 1–8 (2008)
Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: Proc. of BMVC (September 2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moreno, P., Ribeiro, P., Santos-Victor, J. (2011). Feature Selection for Tracker-Less Human Activity Recognition. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2011. Lecture Notes in Computer Science, vol 6753. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21593-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-21593-3_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21592-6
Online ISBN: 978-3-642-21593-3
eBook Packages: Computer ScienceComputer Science (R0)