Action recognition in videos using frequency analysis of critical point trajectories

Cyrille Beaudry (1) , Renaud Péteri (1) , Laurent Mascarilla (1)

1 MIA - Mathématiques, Image et Applications - EA 3165

This paper focuses on human action recognition in video sequences. A method based on the optical flow estimation is presented, where critical points of the flow field are extracted. Multi-scale trajectories are generated from those points and are characterized in the frequency domain. Finally, a sequence is described by fusing this frequency information with motion orientation and shape information. Experiments show that this method has recognition rates among the highest in the state of the art on the KTH dataset. Contrary to recent dense sampling strategies, the proposed method only requires critical points of motion flow field, thus permitting a lower computation time and a better sequence description. Results and perspectives are then discussed.

Mots clés: Action recognition in videos; critical points; frequency analysis of motion trajectories

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Cyrille Beaudry, Renaud Péteri, Laurent Mascarilla. Action recognition in videos using frequency analysis of critical point trajectories. IEEE International Conference on Image Processing (ICIP 2014), Oct 2014, Paris, France. p. 1445-1449. ⟨hal-01004795⟩