• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2023, Volume: 16, Issue: 37, Pages: 3018-3026

Original Article

Violent Video Classification with Transfer Learning Approach Using Inception-V3 and Support Vector Machine

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)


  1. Omarov B, Narynov S, Zhumanov Z, Gumar A, Khassanova M. State-of-the-art violence detection techniques in video surveillance security systems: a systematic review. PeerJ Computer Science. 2022;8:e920. Available from: https://doi.org/10.7717/peerj-cs.920
  2. Min FU, Obaidat MS, Ullah A, Ullah K, Hijji M, Baik SW. A Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos. ACM Computing Survey. 2023;55. Available from: https://doi.org/10.1145/3561971
  3. Peixoto B, Lavi B, Bestagini P, Dias Z, Rocha A. Multimodal Violence Detection in Videos. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp. 2957-2961) IEEE. 2020.
  4. Kaur G, Singh S. Violence Detection in Videos Using Deep Learning: A Survey. In: Advances in Information Communication Technology and Computing. (Vol. 392, pp. 165-173) Springer Nature Singapore. 2022.
  5. Mumtaz N, Ejaz N, Habib S, Mohsin SM, Tiwari P, Band SS, et al. An overview of violence detection techniques: current challenges and future directions. Artificial Intelligence Review. 2023;56(5):4641–4666. Available from: https://doi.org/10.1007/s10462-022-10285-3
  6. Accattoli S, Sernani P, Falcionelli N, Mekuria DN, Dragoni AF. Violence Detection in Videos by Combining 3D Convolutional Neural Networks and Support Vector Machines. Applied Artificial Intelligence. 2020;34(4):329–344. Available from: https://doi.org/10.1080/08839514.2020.1723876
  7. Zhou P, Ding Q, Luo H, Hou X. Violence detection in surveillance video using low-level features. PLOS ONE. 2018;13(10):e0203668. Available from: https://doi.org/10.1371/journal.pone.0203668
  8. Nova D, Ferreira A, Cortez P. A Machine Learning Approach to Detect Violent Behaviour from Video. In: A, T., eds. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. (Vol. 273, pp. 85-94) Springer International Publishing. 2019.
  9. Gao Y, Hong L, Xiaohu S, Wang , Liu Y. Violence detection using Oriented VIolent Flows. 2016. Available from: https://doi.org/10.1016/j.imavis.2016.01.006
  10. Zhang Q, Zhang M, Chen T, Sun Z, Ma Y, Yu B. Recent advances in convolutional neural network acceleration. Neurocomputing. 2019;323:37–51. Available from: https://doi.org/10.1016/j.neucom.2018.09.038
  11. Fenil E, Manogaran G, Vivekananda GN, Thanjaivadivel T, Jeeva S, Ahilan A. Real time violence detection framework for football stadium comprising of bigdata analysis and deep learning through bidirectional LSTM. Computer. 2019;151:191–200. Available from: https://doi.org/10.1016/j.comnet.2019.01.028
  12. Naik AJ, Gopalakrishna MT. Deep-violence: individual person violent activity detection in video. Multimedia Tools and Applications. 2021;80(12):18365–18380. Available from: https://doi.org/10.1007/s11042-021-10682-w
  13. Xia Q, Zhang P, Wang J, Tian M, Fei C. Real Time Violence Detection Based on Deep Spatio-Temporal Features. In: Z, J, eaBRC., eds. Biometric Recognition. (Vol. 10996, pp. 157-165) Springer International Publishing. 2018.
  14. Jaiswal SG, Mohod SW. 2021. Available from: https://link.springer.com/chapter/10.1007/978-981-15-8335-3_56
  15. Nievas EB, Suarez OD, García GB, Sukthankar R. Violence Detection in Video Using Computer Vision Techniques. In: Computer Analysis of Images and Patterns. (Vol. 6855, pp. 332-339) Springer Berlin Heidelberg. 2011.
  16. Mu G, Cao H, Jin Q. Violent Scene Detection Using Convolutional Neural Networks and Deep Audio Features. In: C, H., eds. Communications in Computer and Information Science. (Vol. 663, pp. 451-463) Springer Singapore. 2016.
  17. Jaiswal SG, Mohod DSW. Classification Of Violent Videos Using Ensemble Boosting Machine Learning Approach With Low Level Features. Indian Journal of Computer Science and Engineering. 2021;12(6):1789–1802. Available from: https://doi.org/10.21817/indjcse/2021/v12i6/211206165
  18. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (pp. 2818-2826) IEEE. 2016.
  19. Himeur Y, Al-Maadeed S, Kheddar H, Al-Maadeed N, Abualsaud K, Mohamed A, et al. Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization. Engineering Applications of Artificial Intelligence. 2023;119:105698. Available from: https://doi.org/10.1016/j.engappai.2022.105698
  20. SGJ, Mohod SW, Sharma D. Machine Learning Approach for Violent Video Classification. Indian Journal of Science & Technology. 2023;16(34):2709–2718. Available from: https://doi.org/10.17485/IJST/v16i34.1777
  21. Soliman MM, Kamal MH, Nashed MAEM, Mostafa YM, Chawky BS, Khattab D. Violence Recognition from Videos using Deep Learning Techniques. In: 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS). (pp. 80-85) IEEE. 2019.
  22. Keceli AS, Kaya A. Violent activity classification with transferred deep features and 3d-Cnn. Signal, Image and Video Processing. 2023;17(1):139–146. Available from: https://doi.org/10.1007/s11760-022-02213-3


©  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.