Human Action Recognition in Video Sequences Using Deep Belief Networks

被引:20
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
[41]   Deep Learning and Kurtosis-Controlled, Entropy-Based Framework for Human Gait Recognition Using Video Sequences [J].
Sharif, Muhammad Imran ;
Khan, Muhammad Attique ;
Alqahtani, Abdullah ;
Nazir, Muhammad ;
Alsubai, Shtwai ;
Binbusayyis, Adel ;
Damasevicius, Robertas .
ELECTRONICS, 2022, 11 (03)
[42]   Deep network for human action recognition using Weber motion [J].
Chaudhary, Sachin ;
Murala, Subrahmanyam .
NEUROCOMPUTING, 2019, 367 :207-216
[43]   Human Action Recognition using Transfer Learning with Deep Representations [J].
Sargano, Allah Bux ;
Wang, Xiaofeng ;
Angelov, Plamen ;
Habib, Zulfiqar .
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2017, :463-469
[44]   Multi-Source Heterogeneous Iris Recognition Using Stacked Convolutional Deep Belief Networks-Deep Belief Network Model [J].
Huo, Guang ;
Zhang, Qi ;
Zhang, Yangrui ;
Liu, Yuanning ;
Guo, Huan ;
Li, Wenyu .
PATTERN RECOGNITION AND IMAGE ANALYSIS, 2021, 31 (01) :81-90
[45]   Human action recognition using a hybrid deep learning heuristic [J].
Dash, Samarendra Chandan Bindu ;
Mishra, Soumya Ranjan ;
Raju, K. Srujan ;
Prasad, L. V. Narasimha .
SOFT COMPUTING, 2021, 25 (20) :13079-13092
[46]   A combined multiple action recognition and summarization for surveillance video sequences [J].
Elharrouss, Omar ;
Almaadeed, Noor ;
Al-Maadeed, Somaya ;
Bouridane, Ahmed ;
Beghdadi, Azeddine .
APPLIED INTELLIGENCE, 2021, 51 (02) :690-712
[47]   A combined multiple action recognition and summarization for surveillance video sequences [J].
Omar Elharrouss ;
Noor Almaadeed ;
Somaya Al-Maadeed ;
Ahmed Bouridane ;
Azeddine Beghdadi .
Applied Intelligence, 2021, 51 :690-712
[48]   Video augmentation technique for human action recognition using genetic algorithm [J].
Nida, Nudrat ;
Yousaf, Muhammad Haroon ;
Irtaza, Aun ;
Velastin, Sergio A. .
ETRI JOURNAL, 2022, 44 (02) :327-338
[49]   Deep Learning Algorithms for Human Fighting Action Recognition [J].
Ali, Mohammed Abduljabbar ;
Hussain, Abir Jaafar ;
Sadiq, Ahmed T. .
INTERNATIONAL JOURNAL OF ONLINE AND BIOMEDICAL ENGINEERING, 2022, 18 (02) :71-87
[50]   A pyramidal deep learning architecture for human action recognition [J].
Xie, Lidong ;
Pan, Wei ;
Tang, Chao ;
Hu, Huosheng .
INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL, 2014, 21 (02) :139-146