AI-based Violent Incident Detection in Surveillance Videos to Enhance Public Safety
DOI:
https://doi.org/10.26636/jtit.2025.4.2328Keywords:
bidirectional gated recurrent unit, deep learning, deep transfer learning, video processing, violence detectionAbstract
Acts of violence may occur at any moment, even in densely populated areas, making it important to monitor human activities to ensure public safety. Although surveillance cameras are capable of detecting the activity of people, around-the-clock monitoring still requires human support. As such, an automated framework capable of detecting violence, issuing early alerts, and facilitating quick reactions is required. However, automation of the entire process is challenging due to issues such as low video resolution and blind spots. This study focuses on detecting acts of violence using three video data sets (movies, hockey game and crowd) by applying and comparing advanced ResNet architectures (ResNet50V2, ResNet101V2, ResNet152V2) with the use of the bidirectional gated recurrent unit (BiGRU) algorithm. Spatial features of each video frame sequence are extracted using these pre-trained deep transfer learning models and classified by means of an optimized BiGRU model. The experimental results were then compared with those achieved by wavelet feature extraction approaches and other classification models, including CNN and LSTM. Such an analysis indicates that the combination of ResNet152V2 and BiGRU offers decent performance in terms of higher accuracy, recall, precision, and F1 score across the different datasets. Furthermore, the results indicate that deeper ResNet models significantly improve overall performance of the model in terms of violence detection scores, relative to shallower ResNet models. ResNet152V2 was found to be the ultimate model across the datasets when it comes to a high degree of accuracy in detecting acts of violence.
Downloads
References
[1] S. Natha et al., "Deep BiLSTM Attention Model for Spatial and Temporal Anomaly Detection in Video Surveillance", Sensors, vol. 25, art. no. 251, 2025. DOI: https://doi.org/10.3390/s25010251
View in Google Scholar
[2] M. Karim et al., "Human Action Recognition Systems: A Review of the Trends and State-of-the-art", IEEE Access, vol. 12, pp. 36372-36390, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3373199
View in Google Scholar
[3] Ragedhaksha, Darshini, Shahil, and J. Arunnehru, "Deep Learning-based Real-world Object Detection and Improved Anomaly Detection for Surveillance Videos", Materials Today: Proceedings, vol. 80, pp. 2911-2916, 2023. DOI: https://doi.org/10.1016/j.matpr.2021.07.064
View in Google Scholar
[4] S. Singla and R. Chadha, "Detecting Criminal Activities from CCTV by Using Object Detection and Machine Learning Algorithms", 2023 3rd International Conference on Intelligent Technologies (CONIT), Hubli, India, 2023. DOI: https://doi.org/10.1109/CONIT59222.2023.10205699
View in Google Scholar
[5] V. Payghode et al., "Object Detection and Activity Recognition in Video Surveillance Using Neural Networks", International Journal of Web Information Systems, vol. 19, pp. 123-138, 2023. DOI: https://doi.org/10.1108/IJWIS-01-2023-0006
View in Google Scholar
[6] P. Negre et al., "Literature Review of Deep-learning-based Detection of Violence in Video", Sensors, vol. 24, art. no. 4016, 2024. DOI: https://doi.org/10.3390/s24124016
View in Google Scholar
[7] T. Santos, H. Oliveira, and A. Cunha, "Systematic Review on Weapon Detection in Surveillance Footage through Deep Learning", Computer Science Review, vol. 51, art. no. 100612, 2024. DOI: https://doi.org/10.1016/j.cosrev.2023.100612
View in Google Scholar
[8] J. Ruiz-Santaquiteria et al., "Improving Handgun Detection through a Combination of Visual Features and Body Pose-based Data", Pattern Recognition, vol. 136, art. no. 109252, 2023. DOI: https://doi.org/10.1016/j.patcog.2022.109252
View in Google Scholar
[9] L.M. Salim and Y. Celik, "Detection of Dangerous Human Behavior by Using Optical Flow and Hybrid Deep Learning", Electronics, vol. 13, art. no. 2116, 2024. -0.5pt DOI: https://doi.org/10.3390/electronics13112116
View in Google Scholar
[10] J. Mahmoodi and A. Salajegheh, "A Classification Method Based on Optical Flow for Violence Detection", Expert Systems with Applications, vol. 127, pp. 121-127, 2019. DOI: https://doi.org/10.1016/j.eswa.2019.02.032
View in Google Scholar
[11] X. Wang, J. Yang, and N. K. Kasabov, "Integrating Spatial and Temporal Information for Violent Activity Detection from Video Using Deep Spiking Neural Networks", Sensors, vol. 23, art. no. 4532, 2023. DOI: https://doi.org/10.3390/s23094532
View in Google Scholar
[12] L. Hsairi, S.M. Alosaimi, and G.A. Alharaz, "Violence Detection Using Deep Learning", Arabian Journal for Science and Engineering, vol. 50, pp. 11669-11679, 2024. DOI: https://doi.org/10.1007/s13369-024-09536-y
View in Google Scholar
[13] S.G. Jaiswal, S.W. Mohod, D. Sharma, and A. Hinge, "Violent Video Classification with Transfer Learning Approach Using Inception-V3 and Support Vector Machine", Indian Journal of Science and Technology, vol. 16, pp. 3018-3026, 2023. DOI: https://doi.org/10.17485/IJST/v16i37.1972
View in Google Scholar
[14] M.Q. Khan, S.N. Sabir, F. Malik, and M. Khan, "Deep Convolutional Network for Automatic Violence Detection in Surveillance Videos Using Transfer Learning", Kashf Journal of Multidisciplinary Research, vol. 2, pp. 251-275, 2025. DOI: https://doi.org/10.71146/kjmr270
View in Google Scholar
[15] M. Magdy, M.W. Fakhr, and F.A. Maghraby, "Violence 4D: Violence Detection in Surveillance Using 4D Convolutional Neural Networks", IET Computer Vision, vol. 17, pp. 282-294, 2023. DOI: https://doi.org/10.1049/cvi2.12162
View in Google Scholar
[16] T. Hassner, Y. Itcher, and O. Kliper-Gross, "Violent Flows: Real-time Detection of Violent Crowd Behavior", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Providence, USA, 2012. DOI: https://doi.org/10.1109/CVPRW.2012.6239348
View in Google Scholar
[17] S. Roshan, G. Srivathsan, K. Deepak, and S. Chandrakala, "Violence Detection in Automated Video Surveillance: Recent Trends and Comparative Studies", in: The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems, Academic Press, pp. 249-270, 2020. DOI: https://doi.org/10.1016/B978-0-12-816385-6.00011-8
View in Google Scholar
[18] A. Gupta, A. Mittal, and R. Jain, "A Novel Sarcasm Detection Approach for Text-image Data: Leveraging Multimodal Fusion and Weighted Latent Factors", Information Fusion, vol. 103, art. no. 103266, 2025. DOI: https://doi.org/10.1016/j.inffus.2025.103266
View in Google Scholar
[19] N. Sutranggono and R. Sarno, "Detection and Sentiment Analysis Based on Mental Disorders Aspects Using Bidirectional Gated Recurrent Unit and Semantic Similarity", International Journal of Intelligent Engineering and Systems, vol. 17, pp. 1-12, 2024. DOI: https://doi.org/10.22266/ijies2024.0831.01
View in Google Scholar
[20] U. Jaishankar, J.H. Nirmal, and G. Gidaye, "Robust Time Domain Scalogram Filter Bank Feature Learning Model for Speech Depression Detection with Metaheuristic Spatio Temporal Residual BIGRU Model", International Journal of Biomedical Engineering and Technology, vol. 47, pp. 348-382, 2025. DOI: https://doi.org/10.1504/IJBET.2025.145219
View in Google Scholar
[21] E.B. Nievas, O.D. Suarez, G.B. García, and R. Sukthankar, "Violence Detection in Video Using Computer Vision Techniques", Lecture Notes in Computer Science, vol. 6855, pp. 332-339, 2011. DOI: https://doi.org/10.1007/978-3-642-23678-5_39
View in Google Scholar
[22] C.M. Akujuobi, "Wavelets", in: Wavelets and Wavelet Transform Systems and Their Applications: A Digital Signal Processing Approach, Switzerland: Springer, pp. 13-44, 2022. DOI: https://doi.org/10.1007/978-3-030-87528-2_2
View in Google Scholar
[23] M. Shafiq and Z. Gu, "Deep Residual Learning for Image Recognition: A Survey", Applied Science, vol. 12, art. no. 8972, 2022. DOI: https://doi.org/10.3390/app12188972
View in Google Scholar
[24] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition", arXiv, 2014.
View in Google Scholar
[25] X. Yu, Z. Yu, and S. Ramalingam, "Learning Strict Identity Mappings in Deep Residual Networks", 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00466
View in Google Scholar
[26] R.S. Kızıltepe, J.Q. Gan, and J.J. Escobar, "A Novel Keyframe Extraction Method for Video Classification Using Deep Neural Networks", Neural Computing and Applications, vol. 35, pp. 24513-24524, 2023. DOI: https://doi.org/10.1007/s00521-021-06322-x
View in Google Scholar
[27] S.H. Hendi, H.B. Taher, and K.Q. Hussein, "Automated Video Events Detection and Classification Using CNN-GRU Model", Wasit Journal of Computer and Mathematics Science, vol. 2, pp. 77-86, 2023. DOI: https://doi.org/10.31185/wjcms.188
View in Google Scholar
[28] T. Zhang et al., "MoWLD: A Robust Motion Image Descriptor for Violence Detection", Multimedia Tools and Applications, vol. 76, pp. 1419-1438, 2017. DOI: https://doi.org/10.1007/s11042-015-3133-0
View in Google Scholar
[29] S. Keceli and A.Y. Kaya, "Violent Activity Detection with Transfer Learning Method", Electronics Letters, vol. 53, pp. 1047-1048, 2017. DOI: https://doi.org/10.1049/el.2017.0970
View in Google Scholar
[30] H. Rabiee, H. Mousavi, M. Nabi, and M. Ravanbakhsh, "Detection and Localization of Crowd Behavior Using a Novel Tracklet-based Model", International Journal of Machine Learning and Cybernetics, vol. 9, pp. 1999-2010, 2018. DOI: https://doi.org/10.1007/s13042-017-0682-8
View in Google Scholar
[31] A.B. Mabrouk and E. Zagrouba, "Spatio-temporal Feature Using Optical Flow Based Distribution for Violence Detection", Pattern Recognition Letters, vol. 92, pp. 62-67, 2017. DOI: https://doi.org/10.1016/j.patrec.2017.04.015
View in Google Scholar
[32] P. Zhou, Q. Ding, H. Luo, and X. Hou, "Violence Detection in Surveillance Video Using Low-level Features", PLOS.One, vol. 13, art. no. e0203668, 2018. DOI: https://doi.org/10.1371/journal.pone.0203668
View in Google Scholar
[33] I.P. Febin, K. Jayasree, and P.T. Joy, "Violence Detection in Videos for an Intelligent Surveillance System Using MoBSIFT and Movement Filtering Algorithm", Pattern Analysis and Applications, vol. 23, pp. 611-623, 2020. DOI: https://doi.org/10.1007/s10044-019-00821-3
View in Google Scholar
[34] A.S. Keceli and A. Kaya, "Violent Activity Classification with Transferred Deep Features and 3D-CNN", Signal, Image and Video Processing, vol. 17, pp. 139-146, 2023. DOI: https://doi.org/10.1007/s11760-022-02213-3
View in Google Scholar
[35] M.A. Soeleman, C. Supriyanto, and D.P. Prabowo, "An Empirical Study of CNN-LSTM on Class Imbalance Datasets for Violence Video Detection", Proc. of the 2021 International Conference on Computer, Control, Informatics and Its Applications, pp. 81-85, 2021. DOI: https://doi.org/10.1145/3489088.3489126
View in Google Scholar
[36] Y. Gao et al., "Violence Detection Using Oriented Violent Flows", Image and Vision Computing, vol. 48, pp. 37-41, 2016. DOI: https://doi.org/10.1016/j.imavis.2016.01.006
View in Google Scholar
[37] J. Mahmoodi, H. Nezamabadi-pour, and D. Abbasi-Moghadam, "Violence Detection in Videos Using Interest Frame Extraction and 3D Convolutional Neural Network", Multimedia Tools and Applications, vol. 81, pp. 20945-20961, 2022. DOI: https://doi.org/10.1007/s11042-022-12532-9
View in Google Scholar
[38] I. Serrano, O. Deniz, J.L. Espinosa-Aranda, and G. Bueno, "Fight Recognition in Video Using Hough Forests and 2D Convolutional Neural Network", IEEE Transactions on Image Processing, vol. 27, pp. 4787-4797, 2018. DOI: https://doi.org/10.1109/TIP.2018.2845742
View in Google Scholar
[39] W. Song et al., "A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks", IEEE Access, vol. 7, pp. 39172-39179, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2906275
View in Google Scholar
[40] F.U.M. Ullah et al., "An Intelligent System for Complex Violence Pattern Analysis and Detection", International Journal of Intelligent Systems, vol. 37, pp. 10400-10422, 2022. DOI: https://doi.org/10.1002/int.22537
View in Google Scholar
[41] F.U.M. Ullah et al., "Violence Detection Using Spatiotemporal Features with 3D Convolutional Neural Network", Sensors, vol. 19, art. no. 2472, 2019. DOI: https://doi.org/10.3390/s19112472
View in Google Scholar
[42] Q. Liang, Y. Li, B. Chen, and K. Yang, "Violence Behavior Recognition of Two-cascade Temporal Shift Module with Attention Mechanism", Journal of Electronic Imaging, vol. 30, art. no. 043009, 2021. DOI: https://doi.org/10.1117/1.JEI.30.4.043009
View in Google Scholar
[43] W. Ullah et al., "Intelligent Dual Stream CNN and Echo State Network for Anomaly Detection", Knowledge-Based Systems, vol. 253, art. no. 109456, 2022. DOI: https://doi.org/10.1016/j.knosys.2022.109456
View in Google Scholar
[44] Ş. Aktı, G.A. Tataroğlu, and H.K. Ekenel, "Vision-based Fight Detection from Surveillance Cameras", 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA), Istanbul, Turkey, 2019. DOI: https://doi.org/10.1109/IPTA.2019.8936070
View in Google Scholar
[45] F.U.M. Ullah et al., "AI-assisted edge vision for violence detection in IoT-based industrial surveillance networks", IEEE Transactions on Industrial Informatics, vol. 18, pp. 5359-5370, 2021. DOI: https://doi.org/10.1109/TII.2021.3116377
View in Google Scholar
[46] M. Shoaib et al., "Augmenting the Robustness and Efficiency of Violence Detection Systems for Surveillance and Non-surveillance Scenarios", IEEE Access, vol. 11, pp. 123295-123313, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3329062
View in Google Scholar
[47] J. Mahmoodi and H. Nezamabadi-pour, "A Spatio-temporal Model for Violence Detection Based on Spatial and Temporal Attention Modules and 2D CNNs", Pattern Analysis and Applications, vol. 27, art. no. 46, 2024. DOI: https://doi.org/10.1007/s10044-024-01265-0
View in Google Scholar
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Khaled Merit, Mohammed Beladgham
This work is licensed under a Creative Commons Attribution 4.0 International License.
