Local polynomial space–time descriptors for action classification

Olivier Kihl (1) , David Picard (1) , Philippe-Henri Gosselin (2, 1)

1 MIDI - Multimedia Indexation and Data Integration
2 TEXMEX - Multimedia content-based indexing

In this paper we propose to tackle human actions indexing by introducing a new local motion de-scriptor based on a model of the optical flow. We pro-pose to apply a coding step to vector field before the modeling. We use two modeling, a spatial model and a temporal model. The spatial model is computed by pro-jection of optical flow onto bivariate orthogonal poly-nomials. Then, the time evolution of spatial coefficients is modeled with a one dimension polynomial basis. To perform the action classification, we extend recent still image signatures using local descriptors to our proposal and combine them with linear SVM classifiers. The ex-periments are carried out on the well known UCF11 dataset and on the more challenging Hollywood2 ac-tion classification dataset and show promising results.

Domains: Signal and Image Processing

Olivier Kihl, David Picard, Philippe-Henri Gosselin. Local polynomial space–time descriptors for action classification. Machine Vision and Applications, 2014, pp.1-11. ⟨10.1007/s00138-014-0652-z⟩. ⟨hal-01097536⟩