SVM directed machine learning classifier for human action recognition network
Abstract Understanding human behavior and human action recognition are both essential components of effective surveillance video analysis for the purpose of guaranteeing public safety. However, existing approaches such as three-dimensional convolutional neural networks (3D CNN) and two-stream neural...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83529-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559622329040896 |
|---|---|
| author | Dharmanna Lamani Pramod Kumar A Bhagyalakshmi J. Maria Shanthi Lakshmana Phaneendra Maguluri Mohammad Arif C Dhanamjayulu Sathish Kumar. K Baseem Khan |
| author_facet | Dharmanna Lamani Pramod Kumar A Bhagyalakshmi J. Maria Shanthi Lakshmana Phaneendra Maguluri Mohammad Arif C Dhanamjayulu Sathish Kumar. K Baseem Khan |
| author_sort | Dharmanna Lamani |
| collection | DOAJ |
| description | Abstract Understanding human behavior and human action recognition are both essential components of effective surveillance video analysis for the purpose of guaranteeing public safety. However, existing approaches such as three-dimensional convolutional neural networks (3D CNN) and two-stream neural networks (2SNN) have computational hurdles due to the significant parameterization they require. In this paper, we offer HARNet, a specialized lightweight residual 3D CNN that is built on directed acyclic graphs and was created expressly to handle these issues and achieve effective human action detection. The suggested method presents an innovative pipeline for creating spatial motion data from raw video inputs, which makes successful latent representation learning of human motions easier to accomplish. This generated input is then supplied into HARNet, which processes spatial and motion information in a single stream in an effective manner, maximizing the benefits of both types of cues. The use of traditional machine learning classifiers is done in order to further improve the discriminative capacity of the features that have been learned. To be more specific, we use the latent representations that are stored in HARNet’s fully connected layer and use them as our deep learnt features. After that, these features are entered into the Support Vector Machine (SVM) classifier in order to accomplish action recognition. In order to evaluate the HARNet-SVM method that was developed, empirical tests were run on commonly used action recognition datasets such as UCF101, HMDB51, and the KTH dataset. These tests were carried out in order to gather data for the evaluation. The experimental results show that our method is superior to other state-of-the-art approaches, achieving considerable performance increases of 2.75% on UCF101, 10.94% on HMDB51, and 0.18% on the KTH dataset. These results were obtained by running the method on each dataset separately. Our findings demonstrate the usefulness of HARNet’s lightweight design and highlight the significance of utilizing SVM classifiers with deep learnt features for the purpose of accurate and computationally efficient human activity recognition in surveillance videos. This work helps to the advancement of surveillance technology, which in turn makes video analysis in applications that take place in the real world safer and more dependable. |
| format | Article |
| id | doaj-art-ca474dd0e34f49abb8c910bfc5681d47 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ca474dd0e34f49abb8c910bfc5681d472025-01-05T12:21:18ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-024-83529-7SVM directed machine learning classifier for human action recognition networkDharmanna Lamani0Pramod Kumar1A Bhagyalakshmi2J. Maria Shanthi3Lakshmana Phaneendra Maguluri4Mohammad Arif5C Dhanamjayulu6Sathish Kumar. K7Baseem Khan8Department of Computer Science and Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher EducationDepartment of Computer Science and Engineering, Ganga Institute of Technology and ManagementDepartment of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and TechnologyDepartment of Artificial Intelligence and Machine Learning, J.B. Institute of Engineering and TechnologyDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education FoundationDepartment of Computer Science and Engineering, Alliance UniversitySchool of Electrical Engineering, Vellore Institute of TechnologySchool of Electrical Engineering, Vellore Institute of TechnologyDepartment of Electrical and Computer Engineering, Hawassa UniversityAbstract Understanding human behavior and human action recognition are both essential components of effective surveillance video analysis for the purpose of guaranteeing public safety. However, existing approaches such as three-dimensional convolutional neural networks (3D CNN) and two-stream neural networks (2SNN) have computational hurdles due to the significant parameterization they require. In this paper, we offer HARNet, a specialized lightweight residual 3D CNN that is built on directed acyclic graphs and was created expressly to handle these issues and achieve effective human action detection. The suggested method presents an innovative pipeline for creating spatial motion data from raw video inputs, which makes successful latent representation learning of human motions easier to accomplish. This generated input is then supplied into HARNet, which processes spatial and motion information in a single stream in an effective manner, maximizing the benefits of both types of cues. The use of traditional machine learning classifiers is done in order to further improve the discriminative capacity of the features that have been learned. To be more specific, we use the latent representations that are stored in HARNet’s fully connected layer and use them as our deep learnt features. After that, these features are entered into the Support Vector Machine (SVM) classifier in order to accomplish action recognition. In order to evaluate the HARNet-SVM method that was developed, empirical tests were run on commonly used action recognition datasets such as UCF101, HMDB51, and the KTH dataset. These tests were carried out in order to gather data for the evaluation. The experimental results show that our method is superior to other state-of-the-art approaches, achieving considerable performance increases of 2.75% on UCF101, 10.94% on HMDB51, and 0.18% on the KTH dataset. These results were obtained by running the method on each dataset separately. Our findings demonstrate the usefulness of HARNet’s lightweight design and highlight the significance of utilizing SVM classifiers with deep learnt features for the purpose of accurate and computationally efficient human activity recognition in surveillance videos. This work helps to the advancement of surveillance technology, which in turn makes video analysis in applications that take place in the real world safer and more dependable.https://doi.org/10.1038/s41598-024-83529-7Support vector machine (SVM)Spatial motionThree-dimensional convolutional neural networks (3D CNN)Directed acyclic graphsHuman action recognition network (HARNet) |
| spellingShingle | Dharmanna Lamani Pramod Kumar A Bhagyalakshmi J. Maria Shanthi Lakshmana Phaneendra Maguluri Mohammad Arif C Dhanamjayulu Sathish Kumar. K Baseem Khan SVM directed machine learning classifier for human action recognition network Scientific Reports Support vector machine (SVM) Spatial motion Three-dimensional convolutional neural networks (3D CNN) Directed acyclic graphs Human action recognition network (HARNet) |
| title | SVM directed machine learning classifier for human action recognition network |
| title_full | SVM directed machine learning classifier for human action recognition network |
| title_fullStr | SVM directed machine learning classifier for human action recognition network |
| title_full_unstemmed | SVM directed machine learning classifier for human action recognition network |
| title_short | SVM directed machine learning classifier for human action recognition network |
| title_sort | svm directed machine learning classifier for human action recognition network |
| topic | Support vector machine (SVM) Spatial motion Three-dimensional convolutional neural networks (3D CNN) Directed acyclic graphs Human action recognition network (HARNet) |
| url | https://doi.org/10.1038/s41598-024-83529-7 |
| work_keys_str_mv | AT dharmannalamani svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT pramodkumar svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT abhagyalakshmi svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT jmariashanthi svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT lakshmanaphaneendramaguluri svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT mohammadarif svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT cdhanamjayulu svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT sathishkumark svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork AT baseemkhan svmdirectedmachinelearningclassifierforhumanactionrecognitionnetwork |