A novel gradient based method for RGB-D human action recognition. Issue 4 (December 2018)

• Record Type: Journal Article
• Authors: Tang, Haohao; Zhang, Hanling
• Is Part Of: IOP conference series. Volume 452:Issue 4(2018)
• Publication Date: 2018-12
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/452/4/042108
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: 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.