Title: OHON4D: optimised histogram of 4D normals for human behaviour recognition in depth sequences

Authors: Mourad Bouzegza; Ammar Belatreche; Ahmed Bouridane; Mohamed Elarbi-Boudihir

Addresses: Department of Computer and Information Sciences, Northumbria University, Newcastle, UK; College of Computer and Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia ' Department of Computer and Information Sciences, Northumbria University, Newcastle, UK ' Department of Computer and Information Sciences, Northumbria University, Newcastle, UK; Center for Data Analytics and Cybersecurity, University of Sharjah, Sharjah, United Arab Emirates ' EEDIS Laboratoire, École Supérieure d'Informatique, Sidi Bel Abbes, Algeria

Abstract: Understanding human behaviour in video streams is one of the most active areas in computer vision research. Its purpose is to automatically detect, track and describe human activities in a sequence of image frames. The challenges that researchers have to face are numerous and complex so that building a faithful feature vector that describes and identifies the human behaviour remains a crucial aspect. This paper presents a geometry-based descriptor whose features are extracted from data acquired by depth sensors. It uses a heuristic approach to optimise the histogram of oriented 4D normals (HON4D) descriptor proposed by O. Oreifej and Z. Liu. The latter used a histogram to describe the depth sequence by extracting the normal orientation of the surface distribution in the 4D space of time, depth, and spatial coordinates. The proposed approach in this paper, called optimised histogram of 4D normals (OHON4D), enhances the HON4D method by considering only four projectors to represent a 4D normal instead of 120. We obtained a similar accuracy while saving approximately half of the computational time.

Keywords: computer vision; optimised histrogram; 4D normals; human behaviour recognition; HAR; video streams; geometry based descriptor; Kinect depth sensors.

DOI: 10.1504/IJIEI.2024.140166

International Journal of Intelligent Engineering Informatics, 2024 Vol.12 No.3, pp.328 - 352

Received: 04 Dec 2023
Accepted: 29 Dec 2023
Published online: 26 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article