IMPLEMENTASI DETEKSI KEKERASAN DENGAN PERINGATAN VISUAL MENGGUNAKAN MOBILENETV2 DAN BIDERECTIONAL LONG SHORT-TERM MEMORY (Bi-LSTM)
DOI:
https://doi.org/10.69714/38wan661Keywords:
Deteksi Kekerasan, MobileNetV2, BiLSTM, Real-Time, Kecerdasan BuatanAbstract
This study developed an automatic video-based violence detection system by combining the MobileNetV2 architecture and Bidirectional Long Short-Term Memory (BiLSTM). MobileNetV2 is used to efficiently extract spatial features from each video frame, while BiLSTM is utilized to understand the temporal relationships between frames so that violence patterns can be recognized more accurately. The model is designed to classify videos into two classes: “Violence” and “Non-Violence.” The training process showed a consistent increase in accuracy with a decrease in loss values, without any indication of overfitting. The resulting model achieved an accuracy of 92%, with high precision and recall values, especially in detecting violent actions. The system is implemented in real-time using input from a live camera. When violence is detected, the system automatically displays a visual warning in the form of a red screen with the text “VIOLENCE DETECTED!” and saves a frame clip with a timestamp as documentation. Testing shows that the system can distinguish violent contexts effectively without producing significant false positives. With reliable performance and quick response times, this system has great potential for application in CCTV surveillance in public areas, schools, and conflict-prone regions as an efficient, proactive, and adaptive AI-based solution.
References
F. Abdillah, A. Khoiriyah, A. N. Aziz, and I. G. W. Politeknik Negeri Jember, “Sistem Deteksi Kekerasan Real-Time menggunakan YOLOv5 untuk Keamanan Publik,” SNESTIK Seminar Nasional Teknik Elektro, Sistem Informasi, dan Teknik Informatika, n.d. [Online]. Available: https://doi.org/10.31284/p.snestik.2024.5861
A. D. Fikri, F. Utaminingrum, and E. G. E. Setyawan, “Sistem Pendeteksi Kekerasan di Ruang Publik Menggunakan Metode 3D Convolutional Neural Network,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 1, no. 1, 2017. [Online]. Available: http://j-ptiik.ub.ac.id
A. Khalfaoui, A. Badri, and I. El Mourabit, “Efficient Violence Detection with Bi-directional Motion Attention and MobileNetV3-LSTM,” n.d. [Online]. Available: https://ssrn.com/abstract=5120792
D. Mane, S. Phatangare, S. Nawale, S. Wani, V. Gujarathi, and V. Loya, “Real-Time Anomaly Detection in Video Surveillance: A Mathematical Modeling and Nonlinear Analysis Perspective with MobileNet and Bi-LSTM,” Communications on Applied Nonlinear Analysis, vol. 31, no. 2s, 2024.
N. P. Mohod, “Real-Time Violence Detection in Surveillance Videos Using Deep Learning Approach,” International Journal for Research in Applied Science and Engineering Technology, vol. 12, no. 4, pp. 1267–1274, 2024. [Online]. Available: https://doi.org/10.22214/ijraset.2024.59968
M. M. Mukto, M. Hasan, M. M. Al Mahmud, I. Haque, M. A. Ahmed, T. Jabid, M. S. Ali, M. R. A. Rashid, M. M. Islam, and M. Islam, “Design of a real-time crime monitoring system using deep learning techniques,” Intelligent Systems with Applications, vol. 21, 2024. [Online]. Available: https://doi.org/10.1016/j.iswa.2023.200311
P. Negre, R. S. Alonso, A. González-Briones, J. Prieto, and S. Rodríguez-González, “Literature Review of Deep-Learning-Based Detection of Violence in Video,” Sensors, vol. 24, no. 12, 2024. [Online]. Available: https://doi.org/10.3390/s24124016
M. B. Patel, “Real-Time Violence Detection Using CNN-LSTM,” n.d.
F. J. Rendón-Segador, J. A. Álvarez-García, F. Enríquez, and O. Deniz, “Violencenet: Dense multi-head self-attention with bidirectional convolutional LSTM for detecting violence,” Electronics (Switzerland), vol. 10, no. 13, 2021. [Online]. Available: https://doi.org/10.3390/electronics10131601
J. Silva Deena, M. T. Ahammed, U. M. Boppana, M. Afroj, S. Ghosh, S. Hossain, and P. Balaji, “Real-time based Violence Detection from CCTV Camera using Machine Learning Method,” in 2022 International Conference on Industry 4.0 Technology, I4Tech 2022, 2022. [Online]. Available: https://doi.org/10.1109/I4Tech55392.2022.9952805
M. A. Soeleman, C. Supriyanto, D. P. Prabowo, and P. N. Andono, “Video Violence Detection Using LSTM and Transformer Networks Through Grid Search-Based Hyperparameters Optimization,” International Journal of Safety and Security Engineering, vol. 12, no. 05, pp. 615–622, 2022. [Online]. Available: https://doi.org/10.18280/ijsse.120510
Y. Supartini, E. S. Tambunan, T. Suheri, and R. Ningsih, “Pengembangan Model Deteksi Dini Kekerasan pada Remaja sebagai Upaya Meningkatkan Kemampuan dalam Mendeteksi Adanya Kekerasan pada Remaja,” Quality: Jurnal Kesehatan, vol. 16, no. 2, pp. 82–95, 2022. [Online]. Available: https://doi.org/10.36082/qjk.v16i2.792
UNICEF, Hidden in Plain Sight: A Statistical Analysis of Violence Against Children. New York: United Nations Children’s Fund, 2014. [Online]. Available: https://www.unicef.org/reports/hidden-plain-sight
Y. Zhang, Y. Li, and S. Guo, “Lightweight mobile network for real-time violence recognition,” PLoS ONE, vol. 17, no. 10, 2022. [Online]. Available: https://doi.org/10.1371/journal.pone.0276939
