Title: Human interactive behaviour recognition method based on multi-feature fusion

Authors: Qing Ye; Rui Li; Hang Yang; Xinran Guo

Addresses: School of Information Science and Technology, North China University of Technology, Beijing 100144, China ' School of Information Science and Technology, North China University of Technology, Beijing 100144, China ' School of Information Science and Technology, North China University of Technology, Beijing 100144, China ' School of Information Science and Technology, North China University of Technology, Beijing 100144, China

Abstract: Recently, the selection of the overall and individual characteristics in interactive actions and the high-dimensional complexity of features are still important factors affecting the recognition accuracy. In this paper, we propose a human interactive behaviour recognition method based on multi-feature fusion, which includes two parts, feature extraction and behaviour recognition. Firstly, we use histogram feature descriptors to form a three-dimensional gradient histogram of local space-time feature (3D-HOG) and histogram of global optical flow feature (HOF). Then the bag-of-words model is used to reduce the dimensions and the classification matrix is obtained through multilayer perceptron (MLP) classifiers. In the second part, we use recurrent neural network (RNN) to get connections in time. Considering the information of interactive behaviour will be different at different stages, an improved Gauss neural network are proposed for interactive behaviour recognition. The experimental results show that the algorithm can effectively improve the accuracy in the UT-Interaction dataset.

Keywords: multi-feature fusion; bag-of-words model; multilayer perceptron classifiers; MLP; an improved gauss neural network; interactive behaviour recognition; recurrent neural network; RNN.

DOI: 10.1504/IJCSE.2022.123113

International Journal of Computational Science and Engineering, 2022 Vol.25 No.3, pp.262 - 271

Received: 09 Jan 2021
Accepted: 05 Jun 2021

Published online: 30 May 2022 *

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