Citation :

R. Gayathri, Tan Kuan Tak, B. Sivaneasan, Siva Shankar S, "Hybrid Deep Visual Intelligence Framework for Public Health and Safety Enforcement," International Journal of Engineering Trends and Technology (IJETT), vol. 73, no. 12, pp. 95-123, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I12P109

Abstract

This study highlights the urgent need for enhanced visual monitoring technologies to support public health and safety enforcement in crowded situations, in which individuals could potentially violate compliance and other norms. Most traditional surveillance methodologies lack either the scalability or precision to squash complaints about compliance violations – for example, improper mask usage, failure to maintain a minimum social distance, or other visible anomalies. To address these issues, we designed a Hybrid Deep Visual Intelligence Framework that integrates multiscale convolutional neural networks (e.g., ResNet-101, YOLOv8) for object detection with a sequence of 3D CNNs for temporal activity modeling. We also utilized Vision Transformers with cross-attention that spans external contextual metadata. The input data source was multimodal (including closed-circuit television footage, drone footage, and thermal imagery) to derive compliance scores or alerts in real-time. The evaluation for the constrained performance refers to independent public datasets representing four scenarios - indoor hospitals, outdoor markets, nighttime transport hubs, and large event stadiums using UCF-Crime datasets, Okutama-Action datasets, and AI City Challenge for autonomous vehicle innovative technology. The performance results demonstrated superior performance, achieving up to 96.4% detection accuracy and anomaly detections with F1-scores of 0.89, compared to traditional approaches, which were improved by 5-10%. The results included significant processing frame rates of greater than 24 frames per second that facilitated near-real-time execution. In conclusion, our proposed solutions represent a valid, privacy-compliant deployment option that adapts and scales for enforcement purposes, demonstrating significant options for supporting public health compliance and security in complex public spaces.

Keywords

Deep Learning, Video Surveillance, Public Health Compliance, Anomaly Detection, Multimodal Fusion, Real-Time Monitoring.

References

[1] B. Rajitha, Intelligent Vision‐Based Systems for Public Safety and Protection via Machine Learning Techniques, Machine Learning for Healthcare Applications, pp. 89-102, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Doyeop Lee, Numan Khan, and Chansik Park, “Rigorous Analysis of Safety Rules for Vision Intelligence-Based Monitoring at Construction Jobsites,” International Journal of Construction Management, vol. 23, no. 10, pp. 1768-1778, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Patricia Haley, and Darrell Norman Burrell, “Using Artificial Intelligence in Law Enforcement and Policing to Improve Public Health and Safety,” Law, Economics and Society, vol. 1, no. 1, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Marwa Qaraqe et al., “PublicVision: A Secure Smart Surveillance System for Crowd Behavior Recognition,” IEEE Access, vol. 12, pp.  26474-26491, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Tarun Kumar Vashishth et al., Enhancing Surveillance Systems through Mathematical Models and Artificial Intelligence: An Image Processing Approach, Mathematical Models Using Artificial Intelligence for Surveillance Systems, pp. 91-120, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Babak Rahimi Ardabili et al., “Understanding Policy and Technical Aspects of AI-Enabled Smart Video Surveillance to Address Public Safety,” Computational Urban Science, vol. 3, no. 1, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

  [7] Chandana Thirunagari, and Lilatul Ferdouse, “Enhanced Public Safety: Real-Time Crime Detection with CNN-LSTM in Video Surveillance” The 7^th International Conference on Wireless, Intelligent and Distributed Environment for Communication, pp. 41-54, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Salama A. Mostafa et al., “A YOLO-Based Deep Learning Model for Real-Time Face Mask Detection via Drone Surveillance in Public Spaces,” Information Sciences, vol. 676, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Bharti Sahu, Bhagwan Phulpagar, and Pramod Patil Dynamic, “Surveillance and Implementation of COVID-19 Social Distancing Measures using Advanced Image Processing and R-CNN,” Library of Progress-Library Science, Information Technology & Computer, vol. 44, no. 3, pp. 13457-13467, 2024.
[Google Scholar] [Publisher Link]

[10] Sarfaraz Natha et al., “Deep BilSTM Attention Model for Spatial and Temporal Anomaly Detection in Video Surveillance,” Sensors, vol. 25, no. 1, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Mohammad Arifuzzaman et al., “Innovation in Public Health Surveillance for Social Distancing during the Covid-19 Pandemic: A Deep Learning and Object Detection based Novel Approach,” Plos One, vol. 19, no. 9, pp. 1-28, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] A.R. Sivakumaran et al., “Hybrid Deep Learning for Crime Anomaly Detection: Integrating CNN and LSTM for Predictive Analysis of Urban Safety,” Journal for Educators, Teachers and Trainers, vol. 15, no. 5, pp. 346-354, 2024.
[Google Scholar] [Publisher Link]

[13] Jieqiong Zhao et al., “MetricsVis: A Visual Analytics System for Evaluating Employee Performance in Public Safety Agencies,” IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 1, pp. 1193-1203, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Maryam Pishgar et al., “Redeca: A Novel Framework to Review Artificial Intelligence and its Applications in Occupational Safety and Health,” International Journal of Environmental Research and Public Health, vol. 18, no. 13, pp. 1-42, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Ahmad Alnabulsi et al., “IoT Machine Learning-Based Health Compliance Monitoring System,” International IOT, Electronics and Mechatronics Conference, pp. 235-249, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Ratnam Dodda et al., “Real-Time Face Mask Detection Using Deep Learning: Enhancing Public Health and Safety,” E3S Web of Conferences, vol. 616, pp. 1-8, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Yang Zhang et al., “A Crowdsourcing-Driven AI Model Design Framework to Public Health Policy-Adherence Assessment,” IEEE Transactions on Emerging Topics in Computing, vol. 13, no. 3, pp. 768-783, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] S. Chakradhar Amingad et al., “Enhancing Public Safety with AI-Powered Intelligent Surveillance: An Examination of Immediate Incident Detection and Rapid Response in Urban Settings,” 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), Faridabad, India, pp. 205-210, 2023. [CrossRef] [Google Scholar] [Publisher Link]

[19] Weida Yin, “Monitoring and Early Warning of Artificial Intelligence System in Public Health Safety Law,” Soft Computing, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Tomi D. Räty, “Survey on Contemporary Remote Surveillance Systems for Public Safety,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 40, no. 5, pp. 493-515, 2010.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Yanjinlkham Myagmar-Ochir, and Wooseong Kim, “A Survey of Video Surveillance Systems in Smart City,” Electronics, vol. 12, no. 17, pp. 1-34, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Geetamma Tummalapalli et al., “Enhancing Blurred Image Processing with IoT Integration for Improved Clarity,” 2024 International Conference on Emerging Research in Computational Science (ICERCS), Coimbatore, India, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Mohammed Talha Tabrez et al., “Deep Learning Based Low Light Image Enhancement for Improved Visibility,” Material Science, vol. 23, no. 04, pp. 1-5, 2024.
[Google Scholar] [Publisher Link]

[24] Sebastian Tufvesson, and Kalle Josefsson, “Non-Destructive Anonymization of Training Data for Object Detection,” Master's Thesis in Mathematical Sciences, 2025.
[Google Scholar] [Publisher Link]

[25] Umair Muneer Butt et al., “Spatio-Temporal Crime Predictions by Leveraging Artificial Intelligence for Citizens Security in Smart Cities,” IEEE Access, vol. 9, pp. 47516-47529, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Abdulrahman Alshalawi, Wadood Abdul, and Ghulam Muhammad, “Advanced Detection of Violence from Video: Performance Evaluation of Transformer and State of the Art of Convolution of Neural Network Transformer,” IEEE Access, vol. 13, pp. 74200-74216, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Mallepogu Sivalakshmi, K. Rajendra Prasad, and Chigarapalle Shoba Bindu, “Analysis of Convolutional-Based Variational Autoencoders for Privacy Protection in Realtime Video Surveillance,” Expert Systems with Applications, vol. 274, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Humaid Ahmad Al Falasi, “Predictive Rescue System through Real-Time Accident Monitoring Leveraging Artificial Intelligence,” Master of Science in Professional Studies: Data Analytics, Rochester Institute of Technology ProQuest Dissertations & Theses, 2024.
[Google Scholar] [Publisher Link]

[29] Yuanbin Qian et al., “UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 6, pp. 6577-6585. 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Mohd. Sadiq, Sarfaraz Masood, and Om Pal, “FD-YOLOv5: A Fuzzy Image Enhancement based Robust Object Detection Model for Safety Helmet Detection,” International Journal of Fuzzy Systems, vol. 24, no. 5, pp. 2600-2616, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Aniello De Santo et al., “Deep Learning for HDD Health Assessment: An Application based on LSTM,” IEEE Transactions on Computers, vol. 71, no. 1, pp. 69-80, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Ramna Maqsood et al., “Anomaly Recognition from Surveillance Videos using 3D Convolution Neural Network,” Multimedia Tools and Applications, vol. 80, no. 12, pp. 18693-18716, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Chengcheng Shi, and Shuxin Liu, “Human Action Recognition with Transformer based on Convolutional Features,” Intelligent Decision Technologies, vol. 18, no. 2, pp. 881-896, 2024.  
[CrossRef] [Google Scholar] [Publisher Link]