Enhancing Anomaly Detection Performance: Deep Learning Models Evaluation

Yunusa Mohammed Jeddah; Aisha Hassan Abdalla Hashim; Othman Omran Khalifa; Khmaies Ouhada

doi:10.31436/iiumej.v26i2.3287

Authors

Yunusa Mohammed Jeddah International Islamic University Malaysia https://orcid.org/0009-0002-7643-6030
Aisha Hassan Abdalla Hashim International Islamic University Malaysia https://orcid.org/0000-0001-6331-1373
Othman Omran Khalifa International Islamic University Malaysai https://orcid.org/0000-0002-0847-6017
Khmaies Ouhada University of Johannesburg

DOI:

https://doi.org/10.31436/iiumej.v26i2.3287

Keywords:

Deep Learning Models, Video anomaly detection, Optimization Techniques, Video surveillance, Performance Evaluation

Abstract

Detection of anomalies within video streams continues to be challenging, mostly due to the complexities involved in distinguishing abnormal activities from normal ones. This study aimed to enhance anomaly detection performance by evaluating different deep learning models and optimizers. Utilizing the Keras framework and Python on a Kaggle notebook, the experiment explored the effectiveness of DenseNet121, VGG19, ResNet50, and InceptionV3 models in conjunction with Adam, SGD, RMSprop, and Adagrad optimizers. A UCF Crimes dataset subset focused on Accuracy, F1 Score, and AUC evaluation metrics. The results establish that the InceptionV3 model paired with the Adam optimizer outperforms the other combinations, attaining AUC scores of 0.9918. In contrast to other state-of-the-art models such as DenseNet121 and ResNet50, InceptionV3 presents enhanced precision and adaptability in handling the variability found in video anomaly datasets. This study enhances security by providing insights into enhanced model-optimizer combinations, advancing video surveillance approaches, and providing support for developing robust anomaly detection systems.

ABSTRAK: Pengesanan anomali dalam strim video terus mencabar, kebanyakan disebabkan oleh kerumitan yang terlibat dalam membezakan aktiviti tidak normal dari biasa. Kajian ini cuba meningkatkan prestasi pengesanan anomali dengan menilai model dan pengoptimum pembelajaran mendalam yang berbeza. Menggunakan rangka kerja Keras dan Python pada komputer riba Kaggle, eksperimen ini meneroka keberkesanan model DenseNet121, VGG19, ResNet50 dan InceptionV3 bersama pengoptimum Adam, SGD, RMSprop dan Adagrad. Subset data Jenayah UCF digunakan, memfokuskan pada ketepatan, Skor F1 dan metrik penilaian AUC. Dapatan kajian menunjukkan bahawa model InceptionV3 bersama pengoptimum Adam, mengatasi kombinasi lain, mencapai skor AUC 0.9918. Berbeza dengan model canggih lain seperti DenseNet121 dan ResNet50, InceptionV3 mempunyai ketepatan dan kebolehsuaian yang tinggi dalam mengendalikan kebolehubahan yang terdapat dalam set data anomali video. Kajian ini menyumbang kepada peningkatan keselamatan dengan memberi gabungan pengoptimum bersama model yang dipertingkatkan, memajukan pendekatan pengawasan video dan menyediakan sokongan bagi pembangunan sistem pengesanan anomali yang teguh.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

P. G. I. M. Chandrasekara, L. L. G. Chathuranga, K. A. A. Chathurangi, and D. M. K. N. Seneviratna, “Intelligent Video Surveillance Mechanisms for Abnormal Activity Recognition in Real- Time: A Systematic Literature Review,” vol. 5, no. 1, pp. 26–40, 2023.

B. Gayathri, A. Abhinav, C. H. Reddy, and G. Praneeth, “ANOMALY XPERT: A Deep Learning Approach,” no. March 2024.

N. Gupta, C. Science, B. B. Agarwal, and C. Science, “Recognition of Suspicious Human Activity in Video Surveillance: A Review,” vol. 13, no. 2, pp. 10529–10534, 2023.

A. Tonge, S. Chandak, R. Khiste, U. Khan, and L. A. Bewoor, “Traffic Rules Violation Detection using Deep Learning,” in 2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2020, pp. 1250–1257. doi: 10.1109/ICECA49313.2020.9297495.

U. Y. Reddy, M. S. Nikhil, P. S. S. Krishna, and S. S., “Systematic Harmful Signs Detection for Women’s Safety Using Neural Networks,” in 2023 International Conference on Computer Communication and Informatics (ICCCI), 2023, pp. 1–5. doi: 10.1109/ICCCI56745.2023.10128298.

R. Nayak, U. C. Pati, and S. K. Das, “A comprehensive review on deep learning-based methods for video anomaly detection,” Image Vis Comput, vol. 106, p. 104078, Feb. 2021, doi: 10.1016/J.IMAVIS.2020.104078.

S. Bhakat and G. Ramakrishnan, “Anomaly detection in surveillance videos,” ACM International Conference Proceeding Series, pp. 252–255, 2019, doi: 10.1145/3297001.3297034.

K. Pawar and V. Attar, “Deep learning approaches for video-based anomalous activity detection,” World Wide Web, vol.22, no.2, pp. 571–601, 2019, doi:10.1007/s11280-018-0582-1.

J. Wang, D. Jia, Z. Huang, M. Zhang, and X. Ren, “Normal Spatio-Temporal Information Enhance for Unsupervised Video Anomaly Detection,” Neural Processing Letters, 2023, doi: 10.1007/s11063-023-11347-5.

H. Lv, Z. Cui, B. Wang, and J. Yang, “Spatio-Temporal Relation Learning for Video Anomaly Detection,” Journal of Latex Class Files, vol. 14, no. 8, 2022, doi: 10.48550/arXiv.2209.13116.

R. Chalapathy and S. Chawla, “Deep Learning for Anomaly Detection: A Survey,” pp. 1–50, 2019.

G. Pang, C. Shen, L. Cao, and A. Van Den Hengel, “Deep Learning for Anomaly Detection: A Review,” ACM Computing Surveys, vol. 54, no. 2, pp. 1–36, 2020, doi: 10.1145/3439950.

C. Wu, S. Shao, C. Tunc, and S. Hariri, “Video Anomaly Detection using Pre-Trained Deep Convolutional Neural Nets and Context Mining,” Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA, vol. 2020-Novem, 2020, doi: 10.1109/AICCSA50499.2020.9316538.

A. Lydia and F. Sagayaraj Francis, “A Survey of Optimization Techniques for Deep Learning Networks,” International Journal for Research in Engineering Application & Management (IJREAM), vol. 05, no. August 2020, p. 2, 2019, doi: 10.35291/2454-9150.2019.0100.

W. Sultani, C. Chen, and M. Shah, “Real-World Anomaly Detection in Surveillance Videos,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 6479–6488, 2018, doi: 10.1109/CVPR.2018.00678.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1–14, 2015.

M. F. Amin, Z. Othman, S. S. S. Ahmad, and F. Kasmin, “Analysis on the impact of imagenet preprocessing image mode using VGG19 pre-trained model in plant disease classification,” Proceedings of Mechanical Engineering Research Day 2022, no. August, pp. 154–155, 2022.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-Decem, pp. 2818–2826, 2016, doi: 10.1109/CVPR.2016.308.