Multi-Dimensional Deep Learning for Unusual Detection in Security Footage: A 3D CNN, LSTM, and Attention-Based Approach
Keywords:
Video Anomaly Detection, 3D Convolutional Neural Networks (3D CNN), Fight Detection, Surveillance Videos, Violence Detection, Spatiotemporal ModelingAbstract
Automated detection of unusual activities in surveillance videos remains a critical challenge due to the vast volume of footage and the rarity of anomalous events. This study proposes a novel deep learning framework that integrates 3D convolutional neural networks for spatiotemporal feature extraction, Long Short-Term Memory networks for modeling temporal dependencies, and an attention mechanism to focus on salient segments. The primary objective is to achieve highly accurate binary classification of video clips into “usual” and “unusual” categories, while addressing class imbalance and environmental variability. The model is trained and evaluated on three large-scale datasets, UCF‑Crime, XD-Violence, and CCTVFights, which comprise surveillance videos covering real-world anomalies. Experimental results show that the proposed method achieves an overall accuracy of 97.41% on the UCF-Crime dataset, 98.11% on the XD-Violence dataset, and 98.50% on the CCTVFights dataset, in addition to high precision, recall, and F1 scores on the three datasets used in the evaluation process, outperforming existing benchmarks. These findings indicate that combining spatiotemporal modeling and attention-driven context aggregation can significantly enhance anomaly detection performance in complex surveillance scenarios.
Downloads
References
A. Khandekar, V. Meneni, H. Uddin, B. Nikhil, M. Tejeshwar, and R. Al–Fatlawy, “Sustainable abnormal events detection and tracking in surveillance system,” E3S Web Conf., vol. 529, p. 04009, 2024.
J. Gao, J. Shi, P. Balla, A. Sheshgiri, B. Zhang, H. Yu, et al., “Camera-based crime behaviour detection and classification,” Smart Cities, vol. 7, pp. 1169–1198, 2024.
K. K. Verma, B. M. Singh, and A. Dixit, “A review of supervised and unsupervised machine learning techniques for suspicious behaviour recognition in intelligent surveillance systems,” Int. J. Inf. Technol., vol. 14, pp. 397–410, 2022.
P. G. I. M. Chandrasekara, L. G. Chathuranga, K. A. A. Chathurangi, D. M. K. N. Seneviratna, and R. M. K. T. Rathnayaka, “Intelligent video surveillance mechanisms for abnormal activity recognition in real-time: a systematic literature review,” KDU J. Multidiscip. Stud., vol. 5, p. 1, 2023.
D. R. Patrikar and M. R. Parate, “Anomaly detection using edge computing in video surveillance system,” Int. J. Multimed. Inf. Retr., vol. 11, pp. 85–110, 2022.
M. M. Islam, S. Nooruddin, F. Karray, and G. Muhammad, “Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and prospects,” Comput. Biol. Med., vol. 149, p. 106060, 2022.
M. S. Mahdi, A. J. Mohammed, and M. M. Jafer, “Unusual activity detection in surveillance video scene,” J. AlQadisiyah Comput. Sci. Math., vol. 13, p. 92, 2021.
W. Ullah, A. Ullah, T. Hussain, K. Muhammad, A. A. Heidari, J. Del Ser, et al., “Artificial Intelligence of Things-assisted two-stream neural network for anomaly detection in surveillance Big Video Data,” Future Gen. Comput. Syst., vol. 129, pp. 286–297, 2022.
W. Ullah, A. Ullah, I. U. Haq, K. Muhammad, M. Sajjad, and S. W. Baik, “CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks,” Multimed. Tools Appl., vol. 80, pp. 16979–16995, 2021.
D. Bouchabou, S. M. Nguyen, C. Lohr, B. LeDuc, and I. Kanellos, “A survey of human activity recognition in smart homes based on IoT sensors algorithms: Taxonomies, challenges, and opportunities with deep learning,” Sensors, vol. 21, p. 6037, 2021.
S. Zhang, Y. Li, S. Zhang, F. Shahabi, S. Xia, Y. Deng, and N. Alshurafa, “Deep learning in human activity recognition with wearable sensors: A review on advances,” Sensors, vol. 22, p. 1476, 2022.
E. Ramanujam, T. Perumal, and S. J. Padmavathi, “Human activity recognition with smartphone and wearable sensors using deep learning techniques: A review,” IEEE Sens. J., vol. 21, pp. 13029–13040, 2021.
A. Chatterjee and B. S. Ahmed, “IoT anomaly detection methods and applications: A survey,” Internet Things, vol. 19, p. 100568, 2022.
A. Nadeem, A. Jalal, and K. Kim, “Automatic human posture estimation for sport activity recognition with robust body parts detection and entropy Markov model,” Multimed. Tools Appl., vol. 80, pp. 21465–21498, 2021.
G. Diraco, G. Rescio, P. Siciliano, and A. Leone, “Review on human action recognition in smart living: Sensing technology, multimodality, real-time processing, interoperability, and resource-constrained processing,” Sensors, vol. 23, p. 5281, 2023.
A. Gupta, A. Tickoo, N. Jindal, and A. K. Shrivastava, “Unusual activity detection using machine learning,” in Proc. Int. Conf. Recent Trends Comput. (ICRTC), 2022, pp. 551–559, 2023.
A. Sunil and M. H. Sheth, “Usual and unusual human activity recognition in video using deep learning and artificial intelligence for security applications,” in 2021 Fourth Int. Conf. Electr., Comput. Commun. Technol. (ICECCT), 2021, pp. 1–6.
U. Singh, P. Gupta, and M. Shukla, “Activity detection and counting people using maskRCNN with bidirectional ConvLSTM,” J. Intell. Fuzzy Syst., vol. 43, pp. 6505–6520, 2022.
M. Malekar, “Detecting criminal activities of surveillance videos using deep learning,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., pp. 188–193, 2021.
A. Feroze, A. Daud, T. Amjad, and M. K. Hayat, “Group anomaly detection: past notions, present insights, and future prospects,” SN Comput. Sci., vol. 2, p. 1, 2021.
M. S. Mahdi, A. J. Mohammed, and W. Abdulghafour, “Detection of unusual activity in surveillance video scenes based on deep learning strategies,” J. AlQadisiyah Comput. Sci. Math., vol. 13, p. 4, 2021.
S. Sharma, B. Sudharsan, S. Naraharisetti, V. Trehan, and K. Jayavel, “A fully integrated violence detection system using CNN and LSTM,” Int. J. Electr. Comput. Eng., vol. 11, pp. 3374–3380, 2021.
M. Ramzan, A. Abid, and S. Awan, “Automatic unusual activities recognition using deep learning in academia,” Comput. Mater. Continua, vol. 70, pp. 1829–1844, 2022.
R. Kalshetty and A. Parveen, “Abnormal event detection model using an improved ResNet101 in contextaware surveillance system,” Cogn. Comput. Syst., vol. 5, pp. 153–167, 2023.
A. Shukla, “Detecting impersonation episode using teaching learning–based optimization and support vector machine techniques,” Expert Syst., vol. 40, p. 7, 2023.
Á. JaramilloAlcázar, J. Govea, and W. VillegasCh, “Anomaly detection in a smart industrial machinery plant using IoT and machine learning,” Sensors, vol. 23, p. 8286, 2023.
D. Mane, “Realtime anomaly detection in video surveillance: A mathematical modelling and nonlinear analysis perspective with MobileNet and BiLSTM,” CANA, vol. 31, pp. 306–319, 2024.
M. H. Wani and A. R. Faridi, “EASAD: efficient and accurate suspicious activity detection using deep learning model for IoTbased video surveillance,” Int. J. Inf. Technol., vol. 16, pp. 4309–4321, 2024.
U. Gawande, K. Hajari, and Y. Golhar, “Novel person detection and suspicious activity recognition using enhanced YOLOv5 and motion feature map,” Artif. Intell. Rev., vol. 57, p. 16, 2024.
M. U. Meraj, “AnomalyDetectionDatasetUCF,” Kaggle Dataset, 2021. [Online]. Available: https://www.kaggle.com/datasets/minhajuddinmeraj/anomalydetectiondatasetucf.
P. Wu, J. Liu, Y. Shi, F. Shao, Z. Wu, and Z. Yang, “XDViolence,” Original Metadata [Dataset], TIB LDM Service, 2024. DOI: 10.57702/mt1rr0km. [Online]. Available: https://roc-ng.github.io/XD-Violence/.
M. Perez, A. C. Kot, and A. Rocha, “Detection of realworld fights in surveillance videos,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Brighton, UK, May 12–17, 2019. [Online]. Available: http://rose1.ntu.edu.sg/dataset/cctvFights/.
Published
How to Cite
Issue
Section
Copyright (c) 2025 Nadia Ali (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
