Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique
Human action recognition (HAR) is one of the most active research topics in the field of computer vision. Even though this area is well-researched, HAR algorithms such as 3D Convolution Neural Networks (CNN), Two-stream Networks, and CNN-LSTM (Long Short-Term Memory) suffer from highly complex model...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2023
|
Subjects: | |
Online Access: | http://eprints.utm.my/106922/1/NajeebRehmanMalik2023_MultiViewHumanActionRecognition.pdf http://eprints.utm.my/106922/ http://dx.doi.org/10.3390/s23052745 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.106922 |
---|---|
record_format |
eprints |
spelling |
my.utm.1069222024-08-04T07:12:36Z http://eprints.utm.my/106922/ Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique Rehman Malik, Najeeb Sheikh, Usman Ullah Abu Bakar, Syed Abdul Rahman Channa, Asma TK Electrical engineering. Electronics Nuclear engineering Human action recognition (HAR) is one of the most active research topics in the field of computer vision. Even though this area is well-researched, HAR algorithms such as 3D Convolution Neural Networks (CNN), Two-stream Networks, and CNN-LSTM (Long Short-Term Memory) suffer from highly complex models. These algorithms involve a huge number of weights adjustments during the training phase, and as a consequence, require high-end configuration machines for real-time HAR applications. Therefore, this paper presents an extraneous frame scrapping technique that employs 2D skeleton features with a Fine-KNN classifier-based HAR system to overcome the dimensionality problems.To illustrate the efficacy of our proposed method, two contemporary datasets i.e., Multi-Camera Action Dataset (MCAD) and INRIA Xmas Motion Acquisition Sequences (IXMAS) dataset was used in experiment. We used the OpenPose technique to extract the 2D information, The proposed method was compared with CNN-LSTM, and other State of the art methods. Results obtained confirm the potential of our technique. The proposed OpenPose-FineKNN with Extraneous Frame Scrapping Technique achieved an accuracy of 89.75% on MCAD dataset and 90.97% on IXMAS dataset better than existing technique. MDPI 2023-03-02 Article PeerReviewed application/pdf en http://eprints.utm.my/106922/1/NajeebRehmanMalik2023_MultiViewHumanActionRecognition.pdf Rehman Malik, Najeeb and Sheikh, Usman Ullah and Abu Bakar, Syed Abdul Rahman and Channa, Asma (2023) Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique. Sensors, 23 (5). pp. 1-16. ISSN 1424-8220 http://dx.doi.org/10.3390/s23052745 DOI:10.3390/s23052745 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Rehman Malik, Najeeb Sheikh, Usman Ullah Abu Bakar, Syed Abdul Rahman Channa, Asma Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
description |
Human action recognition (HAR) is one of the most active research topics in the field of computer vision. Even though this area is well-researched, HAR algorithms such as 3D Convolution Neural Networks (CNN), Two-stream Networks, and CNN-LSTM (Long Short-Term Memory) suffer from highly complex models. These algorithms involve a huge number of weights adjustments during the training phase, and as a consequence, require high-end configuration machines for real-time HAR applications. Therefore, this paper presents an extraneous frame scrapping technique that employs 2D skeleton features with a Fine-KNN classifier-based HAR system to overcome the dimensionality problems.To illustrate the efficacy of our proposed method, two contemporary datasets i.e., Multi-Camera Action Dataset (MCAD) and INRIA Xmas Motion Acquisition Sequences (IXMAS) dataset was used in experiment. We used the OpenPose technique to extract the 2D information, The proposed method was compared with CNN-LSTM, and other State of the art methods. Results obtained confirm the potential of our technique. The proposed OpenPose-FineKNN with Extraneous Frame Scrapping Technique achieved an accuracy of 89.75% on MCAD dataset and 90.97% on IXMAS dataset better than existing technique. |
format |
Article |
author |
Rehman Malik, Najeeb Sheikh, Usman Ullah Abu Bakar, Syed Abdul Rahman Channa, Asma |
author_facet |
Rehman Malik, Najeeb Sheikh, Usman Ullah Abu Bakar, Syed Abdul Rahman Channa, Asma |
author_sort |
Rehman Malik, Najeeb |
title |
Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
title_short |
Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
title_full |
Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
title_fullStr |
Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
title_full_unstemmed |
Multi-view human action recognition using skeleton based-FineKNN with extraneous frame scrapping technique |
title_sort |
multi-view human action recognition using skeleton based-fineknn with extraneous frame scrapping technique |
publisher |
MDPI |
publishDate |
2023 |
url |
http://eprints.utm.my/106922/1/NajeebRehmanMalik2023_MultiViewHumanActionRecognition.pdf http://eprints.utm.my/106922/ http://dx.doi.org/10.3390/s23052745 |
_version_ |
1806442426354630656 |
score |
13.18916 |