Human activity recognition in the semantic simplex of elementary actions

Beaudry Cyrille, Péteri Renaud and Mascarilla Laurent

Abstract

This paper presents an original approach for recognizing human activities in video sequences. A human activity is seen as a temporal sequence of elementary action probabilities. Actions are first generically learned using a robust action recognition method based on optical flow estimation and a cross-dataset training process. Activities are then projected as trajectories on the semantic simplex in order to be characterized and discriminated. A new trajectory attribute based on the total curvature Fourier descriptor is introduced. This attribute takes into account the induced geometry of the simplex manifold. Experiments on labelled datasets of human activities prove the efficiency of the proposed method for discriminating complex actions.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 645K)
PDF iconPaper (PDF, 3M)
ZIP iconSupplemental Materials (ZIP, 15M)

DOI

10.5244/C.29.118
https://dx.doi.org/10.5244/C.29.118

Citation

Beaudry Cyrille, Péteri Renaud and Mascarilla Laurent. Human activity recognition in the semantic simplex of elementary actions. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 118.1-118.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_118,
	title={Human activity recognition in the semantic simplex of elementary actions},
	author={Beaudry Cyrille and Péteri Renaud and Mascarilla Laurent},
	year={2015},
	month={September},
	pages={118.1-118.12},
	articleno={118},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.118},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.118}
}