HOG Ensembled Boosting Machine Learning Approach for Violent Video Classification

Snehil G Jaiswal; Sharad W Mohod; Dinesh Sharma

doi:10.17485/IJST/v16i34.1777

Article

HOG Ensembled Boosting Machine Learning Approach for Violent Video Classification

VIEWS 355
PDF 117

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v16i34.1777

Year: 2023, Volume: 16, Issue: 34, Pages: 2709-2718

Original Article

HOG Ensembled Boosting Machine Learning Approach for Violent Video Classification

Snehil G Jaiswal^1*, Sharad W Mohod², Dinesh Sharma³

¹Research Scholar, Sant Gadge 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, Chandigarh, India

*Corresponding Author
Email: [email protected]

Received Date:16 July 2023, Accepted Date:03 August 2023, Published Date:12 September 2023

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Background: With the proliferation of machine learning and its applications in a variety of spheres that are important to humans in their day-to-day lives, there is a pressing need for automatic detection models that can identify abnormal behaviors or acts of violence. Methods: This study examines a machine learning model that uses ensemble boosting and histograms of oriented gradients (HOG) to detect violent content from a feature vector with a single parameter. Findings: The tests performed on two benchmark datasets, such as the Hockey Dataset and the Peliculas dataset, reveal a high level of performance accuracy for the classification of violent videos. The experiment findings show that the suggested violence detection model performs well in terms of average metrics, with accuracy, precision, and recall being 90.50%, 91.80%, and 89.70%, respectively. Novelty and applications: The proposed method is capable of striking a balance between high performance and a limited number of parameters, and as a result, it can be implemented with a minimal investment of computational resources.

Keywords: Violence detection; Computer Vision; Action Recognition; Machine Learning; Histogram of Oriented Gradients (HOG); Ensemble Boosting

References

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.
Thakkar K, Kadiya K, Suthar M, Chauhan MJ. Anomaly Detection In Surveillance Video. 2021. Available from: https://www.irjet.net/archives/V8/i5/IRJET-V8I5486.pdf
Miah P, Haque AA, Imran AA, Hassan MR, Rahman R. Violent activity detection through surveillance camera using deep learning. 2023. Available from: http://hdl.handle.net/10361/18331
Min FU, Ullah MS, Obaidat A, Ullah K, MH, SWB. A Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos. ACM Computing Surveys. 2023;55. Available from: https://doi.org/10.1145/3561971
Kulbacki M, Segen J, Chaczko Z, Rozenblit JW, Kulbacki M, Klempous R, et al. Intelligent Video Analytics for Human Action Recognition: The State of Knowledge. Sensors. 2023;23(9):4258. Available from: https://doi.org/10.3390/s23094258
Ramzan M, Abid A, Khan HU, Awan SM, Ismail A, Ahmed M, et al. A Review on State-of-the-Art Violence Detection Techniques. IEEE Access. 2019;7:107560–107575. Available from: https://doi.org/10.1109/ACCESS.2019.2932114
Sreenu G, Durai MAS. Intelligent video surveillance: a review through deep learning techniques for crowd analysis. Journal of Big Data. 2019;6(1):48. Available from: https://doi.org/10.1186/s40537-019-0212-5
Gracia IS, Suarez OD, Garcia GB, Kim TK. Fast Fight Detection. PLOS ONE. 2015;10(4):e0120448. Available from: https://doi.org/10.1371/journal.pone.0120448
Xie J, Yan W, Mu C, Liu T, Li P, Yan S. Recognizing violent activity without decoding video streams. Optik. 2016;127(2):795–801. Available from: https://doi.org/10.1016/j.ijleo.2015.10.165
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.
Ding C, Fan S, Zhu M, Feng W, Jia B. Violence Detection in Video by Using 3D Convolutional Neural Networks. In: Advances in Visual Computing. (pp. 551-558) Springer International Publishing. 2014.
Jaiswal SG, Mohod SW. Implementation of Violence Detection System using Soft Computing Approach. 2021. Available from: https://doi.org/10.1007/978-981-15-8335-3_56
Jaiswal SG, Mohod SW. Recapitulating the Violence Detection Systems. 2019. Available from: https://doi.org/10.1007/978-981-13-8715-9_25
Jaiswal SG, Mohod SW. 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
Aslan MF, Durdu A, Sabanci K, Mutluer MA. CNN and HOG based comparison study for complete occlusion handling in human tracking. Measurement. 2020;158:107704. Available from: https://doi.org/10.1016/j.measurement.2020.107704
Shaout A, Crispin B. Streaming Video Classification Using Machine Learning. The International Arab Journal of Information Technology. 2020;17(4):677–682. Available from: https://doi.org/10.34028/iajit/17/4a/13
Paiva BBMD, Pereira PD, Andrade CMVD, Gomes VMR, Souza-Silva MVR, Martins KPMP, et al. Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset. Scientific Reports. 2023;13(1):3463. Available from: https://doi.org/10.1038/s41598-023-28579-z
Nievas EB, Suarez OD, García GB, Sukthankar R. Violence Detection in Video Using Computer Vision Techniques. In: R, P, DP, D, MA, H, et al. , eds. Computer Analysis of Images and Patterns. (Vol. 6855, pp. 332-339) Springer Berlin Heidelberg. 2011.
Yang L, Wu Z, Hong J, Long J. MCL: A Contrastive Learning Method for Multimodal Data Fusion in Violence Detection. IEEE Signal Processing Letters. 2023;30:408–412. Available from: https://doi.org/10.1109/LSP.2022.3227818
Xiao Y, Wang L, Wang T, Lai H. Scoreformer: Score Fusion-Based Transformers for Weakly-Supervised Violence Detection. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp. 1-5) IEEE. 2023.
Das S, Sarker A, Mahmud T. Violence Detection from Videos using HOG Features. In: 2019 4th International Conference on Electrical Information and Communication Technology (EICT). (pp. 1-5) IEEE. 2019.
Jain A, Vishwakarma DK. Deep NeuralNet For Violence Detection Using Motion Features From Dynamic Images. In: 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT). (pp. 826-831) IEEE. 2020.
Lopez DJ, Lien CC. Real-Time Human Violent Activity Recognition Using Complex Action Decomposition. In: 2020 International Computer Symposium (ICS). (pp. 360-364) 2020.
Teja MGSKS, Reddy MR, Aishwarya R. Man-on-Man Brutality Identification on Video data using Haar Cascade Algorithm. In: 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS). (pp. 274-278) IEEE. 2020.

Copyright

© 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)