Video Based Violence Detection Using Deep Learning CNN-CHA-SPA Double Attention Mechanism with Mosaicking
Keywords:
Feature extraction, CNN, Mosaicking, enhancement, Violence detection, attention techniqueAbstract
Violence detection refers to the use of various technologies and methods to identify, keep track of, and react to instances of physical or verbal aggressiveness, threatening conduct, or violent acts. Security, public safety, and online content filtering are just a few areas where this use is vital. Due of the differences in the human body, it is challenging to capture more accurate and discriminative features for video-based violence detection. Automatically spotting aggressive behaviour in places with video surveillance, such train stations, gyms, and psychiatric facilities, is crucial. As a result, this research focuses on creating a violence prediction system with improved feature extraction and classification techniques while researching various and efficient feature extraction techniques. Constructing an improvised violence detection system has some difficulties. Deep neural self-attention and CNN feature extraction methods are used to determine if a video contains violent content or not in order to solve the aforementioned complexity, such as focusing on the types of attacks and improving the accuracy of violence detection. The Proposed Method CNN-CHA-SPA Double Attention Mechanism with CNN helps to extract the frames correctly and detect the video is Violent or not. Here, a cutting-edge deep learning approach using video mosaicking is suggested. The extracted images from the video are combined with these mosaic images in the preprocessing stage, which offer a more thorough perspective of the scene and which will aid in accurately extracting the feature and helps to obtain time consistent outcomes and on the other hand improve the performance of the algorithm. This proposed mechanism provides the accurate result compared to the other mechanisms available.
Downloads
References
Naik AJ, Gopalakrishna MT. Automated Violence Detection in Video Crowd Using Spider Monkey-Grasshopper Optimization Oriented Optimal Feature Selection and Deep Neural Network. Journal of Control, Automation and Electrical Systems 2022; 33: 858–880.
Colton D, Hofmann M. Sampling Techniques to Overcome Class Imbalance in a Cyberbullying Context. Journal of Computer-Assisted Linguistic Research 2019; 3: 21.
Fan M, Zhang X, Hu J, Gu N, Tao D. Adaptive Data Structure Regularized Multiclass Discriminative Feature Selection. IEEE Trans Neural Netw Learn Syst 2022; 33: 5859–5872.
Lohithashva BH, Aradhya VNM. Violent Video Event Detection: A Local Optimal Oriented Pattern Based Approach. Communications in Computer and Information Science, Springer Science and Business Media Deutschland GmbH 2021, 268–280.
Peixoto B, Lavi B, Bestagini P, Dias Z, Rocha A. MULTIMODAL VIOLENCE DETECTION IN VIDEOS. .
Deepak K, Srivathsan G, Roshan S, Chandrakala S. Deep Multi-view Representation Learning for Video Anomaly Detection Using Spatiotemporal Autoencoders. Circuits Syst Signal Process 2021; 40: 1333–1349.
Mensa E, Colla D, Dalmasso M et al. Violence detection explanation via semantic roles embeddings. BMC Med Inform Decis Mak 2020; 20.
Albadi N, Kurdi M, Mishra S. Investigating the effect of combining GRU neural networks with handcrafted features for religious hatred detection on Arabic Twitter space. Soc Netw Anal Min 2019; 9.
Vijeikis R, Raudonis V, Dervinis G. Efficient Violence Detection in Surveillance. Sensors 2022; 22.
Gowsikhaa D, Abirami S, Baskaran R. Automated human behavior analysis from surveillance videos: a survey. Artif Intell Rev 2014; 42: 747–765.
Verma P, Charan C, Fernando X, Ganesan S. Lecture Notes on Data Engineering and Communications Technologies 106 Advances in Data Computing, Communication and Security Proceedings of I3CS2021. .
Kang M-S, Park R-H, Park H-M. Efficient Spatio-Temporal Modeling Methods for Real-Time Violence Recognition. IEEE Access 2021; 9: 76270–76285.
Alafif T, Alzahrani B, Cao Y, Alotaibi R, Barnawi A, Chen M. Generative adversarial network based abnormal behavior detection in massive crowd videos: a Hajj case study. J Ambient Intell Humaniz Comput 2022; 13: 4077–4088.
.Mahdi MS, Mohammed AJ, Jafer MM. Unusual Activity Detection in Surveillance Video Scene: Review. Journal of Al-Qadisiyah for Computer Science and Mathematics 2021; 13.
Halder R, Chatterjee R. CNN-BiLSTM Model for Violence Detection in Smart Surveillance. SN Comput Sci 2020; 1: 201.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.