A novel gradient based method for RGB-D human action recognition

2018 3rd International Conference on Insulating Materials, Material Application and Electrical Engineering

材料科学;无线电电子学;电工学

Tang, Haohao^1 ; Zhang, Hanling^1

College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China^1

关键词: Action recognition;    Benchmark datasets;    Gradient-based method;    Human-action recognition;    Intra-class variation;    Shape information;    Spatio temporal;    Structural information;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/452/4/042108/pdf
DOI  :  10.1088/1757-899X/452/4/042108

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Most action recognition approaches proposed over the years that were designed for RGB sequences cannot utilize the rich 3D-structural information to reduce large intra-class variations. This paper addresses the issue of handling sole depth structural information for accurate human action recognition. It presents and evaluates the saliency based P-DmHOG features for human action representation. Saliency based P-DmHOG features are depth features inspired by the well-known HOG descriptor. Good results namely 96.78%, 97.78% and 93.13% are achieved on three public benchmark datasets: MSR Actions 3D, MSR Action Pairs 3D, and MSR Daily Activity 3D, which show the efficiency of proposed method to spatio-temporal and shape information.