Gradient-Flow Tensor Divergence Feature for Human Action Recognition

Ngoc Nam BUI
Jin Young KIM
Hyoung-Gook KIM

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E99-A    No.1    pp.437-440
Publication Date: 2016/01/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E99.A.437
Type of Manuscript: LETTER
Category: Vision
human action recognition,  tensor operator,  GMM supervector,  non-linear GMM KL,  dense trajectory,  

Full Text: PDF(708.9KB)>>
Buy this Article

Current research trends in computer vision have tended towards achieving the goal of recognizing human action, due to the potential utility of such recognition in various applications. Among many potential approaches, an approach involving Gaussian Mixture Model (GMM) supervectors with a Support Vector Machine (SVM) and a nonlinear GMM KL kernel has been proven to yield improved performance for recognizing human activities. In this study, based on tensor analysis, we develop and exploit an extended class of action features that we refer to as gradient-flow tensor divergence. The proposed method has shown a best recognition rate of 96.3% for a KTH dataset, and reduced processing time.