Real-time human action recognition using stacked sparse autoencoders

Objectives: In this paper, an automated real-time human and human-action detection system is developed using Histogram of Oriented Gradients (HOG) and Stacked Sparse Auto-encoders respectively. Methods: For human detection, a feature descriptor is trained using SVM classifier and then is used for i...

Full description

Bibliographic Details
Main Authors: Farooq, Adnan, Mohammad, Emad U Din, Ahmad Zarir, Abdullah, Ismail, Amelia Ritahani, Sulaiman, Suriani
Format: Article
Language:English
Published: Indian Society for Education and Environment & Informatics Publishing Limited 2018
Subjects:
Online Access:http://irep.iium.edu.my/62341/
http://irep.iium.edu.my/62341/1/Real-Time%20Human%20Action%20Recognition.pdf
_version_ 1848785828698914816
author Farooq, Adnan
Mohammad, Emad U Din
Ahmad Zarir, Abdullah
Ismail, Amelia Ritahani
Sulaiman, Suriani
author_facet Farooq, Adnan
Mohammad, Emad U Din
Ahmad Zarir, Abdullah
Ismail, Amelia Ritahani
Sulaiman, Suriani
author_sort Farooq, Adnan
building IIUM Repository
collection Online Access
description Objectives: In this paper, an automated real-time human and human-action detection system is developed using Histogram of Oriented Gradients (HOG) and Stacked Sparse Auto-encoders respectively. Methods: For human detection, a feature descriptor is trained using SVM classifier and then is used for identification of humans in the frames. Stacked Sparse autoencoders are a category of deep neural networks, and in the proposed work is used for the feature extraction of human actions from the human action video dataset. The extracted features represent a dictionary which is used to map the input and produce a linear combination, following that soft-max classification is applied to train the model. To reduce the computational complexity, input frames has been changed into binary temporal difference images and fed to the neural network. Analysis: The proposed model matched the other state of the art models applied for human-action recognition classification problems. Applications: The study reveals that using multiple layers can improve the classification performance: 75% with two-layers and 83% with three-layers model.
first_indexed 2025-11-14T16:59:21Z
format Article
id iium-62341
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T16:59:21Z
publishDate 2018
publisher Indian Society for Education and Environment & Informatics Publishing Limited
recordtype eprints
repository_type Digital Repository
spelling iium-623412024-01-02T02:25:46Z http://irep.iium.edu.my/62341/ Real-time human action recognition using stacked sparse autoencoders Farooq, Adnan Mohammad, Emad U Din Ahmad Zarir, Abdullah Ismail, Amelia Ritahani Sulaiman, Suriani QA75 Electronic computers. Computer science Objectives: In this paper, an automated real-time human and human-action detection system is developed using Histogram of Oriented Gradients (HOG) and Stacked Sparse Auto-encoders respectively. Methods: For human detection, a feature descriptor is trained using SVM classifier and then is used for identification of humans in the frames. Stacked Sparse autoencoders are a category of deep neural networks, and in the proposed work is used for the feature extraction of human actions from the human action video dataset. The extracted features represent a dictionary which is used to map the input and produce a linear combination, following that soft-max classification is applied to train the model. To reduce the computational complexity, input frames has been changed into binary temporal difference images and fed to the neural network. Analysis: The proposed model matched the other state of the art models applied for human-action recognition classification problems. Applications: The study reveals that using multiple layers can improve the classification performance: 75% with two-layers and 83% with three-layers model. Indian Society for Education and Environment & Informatics Publishing Limited 2018-01 Article PeerReviewed application/pdf en http://irep.iium.edu.my/62341/1/Real-Time%20Human%20Action%20Recognition.pdf Farooq, Adnan and Mohammad, Emad U Din and Ahmad Zarir, Abdullah and Ismail, Amelia Ritahani and Sulaiman, Suriani (2018) Real-time human action recognition using stacked sparse autoencoders. Indian Journal of Science and Technology, 11 (4). pp. 1-6. ISSN 0974-6846 E-ISSN 0974-5645 http://www.indjst.org/index.php/indjst/article/view/121090/83462
spellingShingle QA75 Electronic computers. Computer science
Farooq, Adnan
Mohammad, Emad U Din
Ahmad Zarir, Abdullah
Ismail, Amelia Ritahani
Sulaiman, Suriani
Real-time human action recognition using stacked sparse autoencoders
title Real-time human action recognition using stacked sparse autoencoders
title_full Real-time human action recognition using stacked sparse autoencoders
title_fullStr Real-time human action recognition using stacked sparse autoencoders
title_full_unstemmed Real-time human action recognition using stacked sparse autoencoders
title_short Real-time human action recognition using stacked sparse autoencoders
title_sort real-time human action recognition using stacked sparse autoencoders
topic QA75 Electronic computers. Computer science
url http://irep.iium.edu.my/62341/
http://irep.iium.edu.my/62341/
http://irep.iium.edu.my/62341/1/Real-Time%20Human%20Action%20Recognition.pdf