Multi-dimensional human action recognition model based on image set and group sparisty

Abstract

Human action recognition is a hot research topic in computer vision, which has been applied into surveillance system and human machine interface. However, since the high variability of appearance, shapes and potential occlusions, single-view human action recognition task is challenging, thus, in this paper, we proposed multi-dimensional human action recognition model based on image set and group sparsity. Specifically, we first extract dense trajectory feature for each camera, and then construct the shared codebook by k-means for all cameras, after that, Bag-of-Word (BoW) weight scheme is employed to code dense trajectory feature by the shared codebook for each camera respectively, and then multi-dimensional human action recognition model based on image set and group sparsity is trained where multi-view samples are considered as query set, and it is whole reconstructed by gallery set, at the same time, spare coefficients are requested to group sparsity. Large scale experimental results on three public multi-view action3D datasets – Northwestern UCLA, IXMAX and CVS-MV-RGBD-Single, show that multi-dimensional data is very helpful for action recognition, and the proposed scheme based on image set can further improve the performance, what is more, when group sparsity is added, its performance is comparable to the state-of-the-art methods.