Recognizing Human Actions by Using Spatio-temporal Motion Descriptors - Advanced Concepts for Intelligent Vision Systems - page 373

available dataset, but additionally we created a dataset of persons standing up,
which contained several types of practical problems (e.g. motion in background
or partial occlusion). According to our experiments the simple frame-difference
based descriptor achieved recognition rates comparable to the optical flow-based
approach, with significantly lower computational complexity. In the future we
are planning to increase the size of our current dataset and also the number
of different action types. Moreover, we will also evaluate how the different pa-
rameter settings (e.g. quantization or cel l and block size) affect the recognition
performance.
Acknowledgement
This work was partially supported by the Hungarian Scientific Research Fund
under grant number 76159.
References
1. Gavrila, D.M.: The visual analysis of human movement: a survey. Computer Vision
and Image Understanding 73(1), 82-98 (1999)
2. Song, Y., Goncalves, L., Perona, P.: Unsupervised learning of human motion. IEEE
Trans. on Pattern Analysis and Machine Intelligence 25(7), 814-827 (2003)
3. Rao, C., Shah, M.: View-invariance in action recognition. In: Proc. of the IEEE
Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 316-322 (2001)
4. Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse
spatio-temporal features. In: Proc. of the 14th Int. Conf. on Computer Communi-
cations and Networks, pp. 65-72 (2005)
5. Laptev, I.: On space-time interest points. Int. J. of Computer Vision 64(2-3), 107-
123 (2005)
6. Ballan, L., Bertini, M., Del Bimbo, A., Seidenari, L., Serra, G.: Recognizing human
actions by fusing spatio-temporal appearance and motion descriptors. In: Proc. of
the IEEE Int. Conf. on Image Processing (2009)
7. Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local SVM
approach. In: Proc. of the 17th Int. Conf. on Pattern Recognition, pp. 32-36 (2004)
8. Vapnik, V.N.: Statistical Learning Theory. Wiley Interscience, Hoboken (1998)
9. Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-
gradients. In: Proc. of the British Machine Vision Conference, pp. 995-1004 (2008)
10. Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human
actions from movies. In: Proc. of the IEEE Conf. on Computer Vision and Pattern
Recognition, pp. 1-8 (2008)
11. Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In:
Proc. of the 9th IEEE Int. Conf. on Computer Vision, pp. 726-733 (2003)
12. Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of
flow and appearance. In: Proc. of the European Conf. on Computer Vision, pp.
7-13 (2006)
13. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In:
Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 886-
893 (2005)