Indian Journal of Science and Technology
DOI: 10.17485/IJST/v16i37.1972
Year: 2023, Volume: 16, Issue: 37, Pages: 3018-3026
Original Article
Snehil G Jaiswal1*, Sharad W Mohod2, Dinesh Sharma3, Ankita Hinge4
1Research Scholar, SantGadge Baba Amravati University Amravati and Registrar, G H Raisoni University, Amravati, Maharashtra, India
2Professor and Head of Department, Department of Electronics and Telecommunication
Engineering, Prof. Ram Meghe Institute of Technology & Research, Amravati, Maharashtra, India
3Assistant Professor, Department of Electronics and Telecommunication Engineering, Chandigarh College of Engineering and Technology, (Government Institute Under Chandigarh UT Administration), Chandigarh, India
4M.Tech Student, Department of Electronics and Telecommunication Engineering,G H Raisoni University, Amravati, Maharashtra, India
*Corresponding Author
Email: [email protected]
Received Date:04 August 2023, Accepted Date:30 August 2023, Published Date:30 September 2023
Objectives: Research in surveillance systems is growing, with cameras in public places capturing actions for the live surveillance, goal-driven investigation, event forecasting, and intrusion detection. Violent video classification system plays a critical role in development of violence detection system for public security and safety. Such system is useful in identification of violent behaviors, such as fighting or assault. Methods: The Inception-V3 architecture using Convolutional neural networks extracts the informative features from the input video frames. Support Vector Machine is used to select features for classification once the remaining layers of the Inception-V3 model have been frozen. Findings: The datasets used in many contemporary and current innovative techniques, including the Hockey battle dataset and the Movies dataset, are used to train and assess the proposed hybrid model. The experiment findings show that the suggested violence detection algorithm performs well in terms of average metrics, with accuracy, precision, recall, and F-Score being 96 2%, 98 2%, 96 1%, 0.95 respectively. Novelty: Transfer Learning approach is applied which involves lightly retraining pretrained models on different datasets, resulting in improved performance in terms of computational resources and accuracy.
Keywords: Deep Learning; Convolutional Neural Network; Action Recognition; Violence Detection; Action Recognition; InceptionV3; Support Vector Machine (SVM)
© 2023 Jaiswal et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.