Skip to Main content Skip to Navigation
Conference papers

Action recognition in videos using frequency analysis of critical point trajectories

Abstract : 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.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01004795
Contributor : Renaud Péteri <>
Submitted on : Wednesday, June 11, 2014 - 4:21:35 PM
Last modification on : Monday, May 4, 2020 - 5:02:04 PM
Document(s) archivé(s) le : Tuesday, April 11, 2017 - 6:41:56 AM

File

BEAUDRY_Cyrille_Action_recogni...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01004795, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

503

Files downloads

529