In order to promote public safety and quick emergency response, smart cities are depending more and more on networked cameras, Internet-of-things sensors, unmanned aerial vehicles, and edge computing. However, occlusion, illumination fluctuation, camera motion, crowd density, complex relationships, and the temporal evolution of anomalous behaviour make it challenging to identify and forecast important events from continuous urban footage. For real-time critical-event monitoring, this study presents XAI-CityVision, an explainable artificial intelligence platform that combines computer vision, object identification, temporal learning, risk assessment, and visual explanation. The framework uses a synchronised acquisition layer to receive heterogeneous urban observations, preprocesses videos, uses CNN or Vision Transformer backbones to extract spatial representations, uses a YOLO-family detector to identify pertinent objects, and uses ConvLSTM or transformer-based temporal learning to model event evolution. Grad-CAM, SHAP, and attention visualisation offer complementary explanations of the choice, while a risk module integrates event likelihood, temporal persistence, and contextual severity. A universal event ontology including normal activity, accident/collision, fire/smoke, crowd anomaly, intrusion/suspicious behaviour, and traffic-related occurrences is mapped to dataset-specific labels in the experimental design, which employs public urban and surveillance benchmarks. Precision, recall, F1-score, IoU, mean average precision, ROC AUC, false-alarm rate, inference delay, and frames per second are used to assess performance. The contributions of spatial learning, object detection, temporal modelling, and multimodal context are measured by ablation studies. In smart-city settings, the suggested framework offers a repeatable architecture for integrating deployment-aware evaluation, operator-oriented explanations, and predictive performance.

References

1. Samaila, Y. A., et al. ―Video anomaly detection: A systematic review of issues and prospects.‖ Neurocomputing, 591, 127726, 2024. DOI: 10.1016/j.neucom.2024.127726.

2. ―Deep Learning for Video Anomaly Detection: A Review.‖ IEEE Transactions on Neural Networks and Learning Systems, 37(7), 3010–3030, 2026. DOI: 10.1109/TNNLS.2025.3647892.

3. ―Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024.‖ Smart Cities, 10(1), 15, 2025.

4. Sharif, M. H., Jiao, L., & Omlin, C. W. ―Deep crowd anomaly detection: state-of-the-art, challenges, and future research directions.‖ Artificial Intelligence Review, 58, 139, 2025. DOI: 10.1007/s10462 024-11092-8.

5. Liu, J., Liu, Y., Lin, J., et al. ―Networking Systems for Video Anomaly Detection: A Tutorial and Survey.‖ ACM Computing Surveys, 57(10), 2025. DOI: 10.1145/3729222.

6. ―Survey on video anomaly detection in dynamic scenes with moving cameras.‖ Artificial Intelligence Review. DOI: 10.1007/s10462-023-10609-x.

7. Wang, Y., Guo, D., Li, S., Camps, O., & Fu, Y. ―Explainable Anomaly Detection in Images and Videos: A Survey.‖ arXiv:2302.06670, 2023.

8. Ren, Y., et al. ―A Panoramic Review on Cutting-Edge Methods for Video Anomaly Localization.‖ IEEE Access, 12, 186380–186412, 2024. DOI: 10.1109/ACCESS.2024.3510039.

9. Sivakumar, G., Mogesh, G., Pragatheeswaran, N., & Sambathkumar, T. ―Video Anomaly Detection in Crime Analysis Using Deep Learning Architecture—A Survey.‖ Journal of Trends in Computer Science and Smart Technology, 6(1), 1–17, 2024. DOI: 10.36548/jtcsst.2024.1.001.

10. Baala, A., Mostafa, H., & Mohssine, B. ―A Comprehensive Systematic Review of Deep Learning Techniques for Anomaly Detection in Urban Video Surveillance.‖ IEEE IRASET, 2025. DOI: 10.1109/IRASET64571.2025.11008153.

11. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. ―You Only Look Once: Unified, Real-Time Object Detection.‖ CVPR, 779–788, 2016.

12. Dr. J. Anvar Shathik et al. ‖ Deep Ensemble Learning For Accurate Prediction Of Neurodegenerative Disorders Using Temporal Clinical Data . (2025). International Journal of Environmental Sciences, 11(4s), 1246-1253. https://doi.org/10.64252/8dbg7v71

13. Anvar Shathik J, B. R. Chandra, M. D. Nandeesh, T. C. Maniunath, S. Pothala and N. R. Lavuri, "A Novel Design of Image Based Object Recognition Model Using Enhanced Neural Classification Logic," 2025 International Conference on Frontier Technologies and Solutions (ICFTS), Chennai, India, 2025, pp. 1-8, doi: 10.1109/ICFTS62006.2025.11031570.

14. R. R, J. Anvar. Shathik, J. Sivakumar, P. Manothini, G. S. J. Asha and M. Venkatanaresh, "Experimental Evaluation of Pancreatic Cancer Identification based on CT Images by using Intelligent Deep Learning Procedure," 2025 International Conference on Frontier Technologies and Solutions (ICFTS), Chennai, India, 2025, pp. 1-9, doi: 10.1109/ICFTS62006.2025.11031801.

15. J. Anvar Shathik, S. Hashini, A. Pandiaraj, N. Ramshankar, N. G and A. K B, "Identification of Different Medicinal Plants Through Image Processing," 2024 International Conference on SmartTechnologies for Sustainable Development Goals(ICSTSDG),

Chennai - 600077, Tamil Nadu, India, 2024, pp. 1-5, doi: 10.1109/ICSTSDG61998.2024.11026565.

16. Raju, K., Ramshankar, N., Anvar Shathik J et al. Blockchain Assisted Cloud Security and Privacy Preservation using Hybridized Encryption and Deep Learning Mechanism in IoT-Healthcare Application. J Grid Computing 21, 45 (2023). https://doi.org/10.1007/s10723-023-09678-7

17. Madhavikatamaneni, R. K. S, Anvar Shathik J and K. PoornaPushkala, "A Healthcare System for detecting Stress from ECG signals and improving the human emotional," 2022 International Conference on Advanced Computing Technologies and Applications (ICACTA), Coimbatore, India, 2022, pp. 1-8, doi: 10.1109/ICACTA54488.2022.9753564.

18. VijayaVardan Reddy S P; Armstrong Joseph J; Priscilla M; Anvar Shathik J; R.ThandaiahPrabu, "HDP-IoT: An IoT Framework for Cardiac Status Prediction System using Machine Learning," 2022 International Conference on Inventive Computation Technologies (ICICT), Nepal, 2022, pp. 855-861, doi: 10.1109/ICICT54344.2022.9850897.

19. K. Vikranth, Anvar Shathik J, and K. Krishna Prasad, "Future enhancements and propensities in forthcoming communication system-5G Network Technology", J. Phys, pp. 12006, 2020.

20. Yarramsetti, S., Anvar Shathik J, & Renisha, P. S. (2021). Intelligent estimation of social media sentimental features using Deep Learning with Natural Language Processing Strategies. International Journal of Innovative Technology and Exploring Engineering, 10(6), 74-79.

21. Ramshankar, N., Anvar Shathik, J.., Raju, K. et al. Integrated deep learning and blockchain-based framework for cloud manufacturing with improved customer satisfaction. KnowlInfSyst 67, 5301 5334 (2025). https://doi.org/10.1007/s10115-025-02373-x

22. Mr.G. Silambarasan , J.Anvar Shathik (2017) ―Ensemble text classifier: a document classification technique to predict and categorizes regularised and novel classes using incremental learning ― , International Journal of Applied Engineering Research , 2017, Volume 12, issue -22 , Pages12454 12459

23. Mr.G. Silambarasan , J. Anvar Shathik (2019) ― Automated Ensemble Framework for Integration of Ontology Based Large Scale Semantic Knowledge Base ― Journal of Engineering and Applied Sciences 14(2)

24. J. Anvar Shathik, Anil Saroliya,et al.(2025) ―Smart Vision Systems for Public Safety: Real-Time Crowd Monitoring and Anomaly Detection in Urban Spaces Using Deep Learning and Edge Computing‖, International Journal of Applied Mathematics, 38 (6) DOI: https://doi.org/10.12732/ijam.v38i6s.430

25. Anvar Shathik J; , B. R. Chandra, M. D. Nandeesh, T. C. Maniunath, S. Pothala and N. R. Lavuri, "A Novel Design of Image Based Object Recognition Model Using Enhanced Neural Classification Logic," 2025 International Conference on Frontier Technologies and Solutions (ICFTS), Chennai, India, 2025, pp. 1-8, doi: 10.1109/ICFTS62006.2025.11031570.