Back to Search Start Over

Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation

Authors :
Wang, Pichao
Li, Wanqing
Ogunbona, Philip
Gao, Zhimin
Zhang, Hanling
Publication Year :
2014

Abstract

Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition. Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints. Secondly, limbs are combined into parts and the limb's states are mapped into part states. Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames. These parts are referred to as Frequent Local Parts or FLPs. The FLPs allow us to build powerful bag-of-FLP-based action representation. This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1409.4014
Document Type :
Working Paper