3D GLOH features for human action recognition

Abdulmunem, Ashwan ORCID: https://orcid.org/0000-0002-1903-9269, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766 2017. 3D GLOH features for human action recognition. Presented at: International Conference on Pattern Recognition, Cancun, Mexico, 4-8 December 2016. 2016 23rd International Conference on Pattern Recognition (ICPR). Piscataway, New Jersey: IEEE, pp. 805-810. 10.1109/ICPR.2016.7899734

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

Abstract

Human action recognition from videos has wide applicability and receives significant interests. In this work, to better identify spatio-temporal characteristics, we propose a novel 3D extension of Gradient Location and Orientation Histograms, which provides discriminative local features representing not only the gradient orientation, but also their relative locations. We further propose a human action recognition system based on the Bag of Visual Words model, by combining the new 3D GLOH local features with Histograms of Oriented Optical Flow (HOOF) global features. Along with the idea from our recent work to extract features only in salient regions, our overall system outperforms existing feature descriptors for human action recognition for challenging real-world video datasets.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Publisher:	IEEE
ISBN:	978-1-5090-4847-2
Date of First Compliant Deposit:	10 August 2016
Date of Acceptance:	13 July 2016
Last Modified:	01 Nov 2022 11:04
URI:	https://orca.cardiff.ac.uk/id/eprint/93737

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item