Human Action Recognition in Video Sequences Using Deep Belief Networks

被引:18
作者
Abdellaoui, Mehrez [1 ,2 ]
Douik, Ali [1 ]
机构
[1] Univ Sousse, Natl Engn Sch Sousse, Networked Object Control & Commun Syst Lab, Sousse 4054, Tunisia
[2] Univ Kairouan, Higher Inst Appl Sci & Technol Kairouan, Kairouan 3100, Tunisia
关键词
human action recognition; deep belief network; restricted Boltzmann machine; deep learning;
D O I
10.18280/ts.370105
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
For the last several decades, Human Activity Recognition (HAR) has been an intriguing topic in the domain of artificial intelligence research, since it has applications in many areas, such as image and signal processing. Generally, every recognition system can be either an end-to-end system or including two phases: feature extraction and classification. In order to create an optimal HAR system that offers a better quality of classification prediction, in this paper we propose a new approach within two-phase recognition system paradigm. Probabilistic generative models, known as Deep Belief Networks (DBNs), are introduced. These DBNs comprise a series of Restricted Boltzmann Machines (RBMs) and are responsible for data reconstruction, feature construction and classification. We tested our approach on the KTH and UIUC human action datasets. The results obtained are very promising, with the recognition accuracy outperforming the recent state-of-the-art.
引用
收藏
页码:37 / 44
页数:8
相关论文
共 50 条
[21]   Human Action Recognition in Video [J].
Singh, Dushyant Kumar .
ADVANCED INFORMATICS FOR COMPUTING RESEARCH, ICAICR 2018, PT I, 2019, 955 :54-66
[22]   Human Action Recognition Using Fusion of Modern Deep Convolutional and Recurrent Neural Networks [J].
Tkachenko, Dmytro .
2018 IEEE FIRST INTERNATIONAL CONFERENCE ON SYSTEM ANALYSIS & INTELLIGENT COMPUTING (SAIC), 2018, :181-185
[23]   Deep ensembled voting framework for human activity recognition and validation on video sequences [J].
Neha Gupta ;
Suneet K. Gupta ;
Vanita Jain ;
Narpinder Singh ;
Jasjit S. Suri .
Evolving Systems, 2025, 16 (2)
[24]   Deep Metric Learning for Human Action Recognition with SlowFast Networks [J].
Shi, Shanmeng ;
Jung, Cheolkon .
2021 INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2021,
[25]   Human action recognition using deep rule-based classifier [J].
Allah Bux Sargano ;
Xiaowei Gu ;
Plamen Angelov ;
Zulfiqar Habib .
Multimedia Tools and Applications, 2020, 79 :30653-30667
[26]   Human action recognition using deep rule-based classifier [J].
Sargano, Allah Bux ;
Gu, Xiaowei ;
Angelov, Plamen ;
Habib, Zulfiqar .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (41-42) :30653-30667
[27]   An Efficient Video Inpainting Approach Using Deep Belief Network [J].
Srinivasan, M. Nuthal ;
Chinnadurai, M. .
COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2022, 43 (02) :515-529
[28]   Human Action Recognition Using Deep Learning Methods [J].
Yu, Zeqi ;
Yan, Wei Qi .
2020 35TH INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ), 2020,
[29]   A new framework for deep learning video based Human Action Recognition on the edge [J].
Cob-Parro, Antonio Carlos ;
Losada-Gutierrez, Cristina ;
Marron-Romera, Marta ;
Gardel-Vicente, Alfredo ;
Bravo-Munoz, Ignacio .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 238
[30]   Deep Belief Networks and Deep Learning [J].
Hua, Yuming ;
Guo, Junhai ;
Zhao, Hua .
PROCEEDINGS OF 2015 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND INTERNET OF THINGS, 2015, :1-4