Authors : Sai Sanjana Ghanta; Karthikeya Sai M.; Vishnuvardhan K.; Srinidhi G.; Melissa Angel D.

Volume/Issue : Volume 11 - 2026, Issue 1 - January

Google Scholar : https://tinyurl.com/3dd59we3

Scribd : https://tinyurl.com/yux2mawe

DOI : https://doi.org/10.38124/ijisrt/26jan1205

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : GuardAI transforms passive CCTV infrastructure into ethical urban safety ecosystems, empowering cities to govern crowds proactively and prevent crises before they escalate. While YOLOv8-based crowd detection systems provide reliable person detection and counting from images and videos, they primarily function as passive monitoring tools that require continuous human supervision. To address this limitation, this paper proposes an enhanced YOLOv8-based crowd detection system integrated with an automated alarm mechanism and a user-friendly Tkinter graphical interface. The system supports both image and video inputs, performs real-time crowd detection and counting, and triggers instant alerts when the number of detected individuals exceeds a predefined threshold. By incorporating automated decision-making and alert generation, the system transforms conventional monitoring into a proactive safety solution. Experimental results demonstrate enhanced responsiveness, usability, and effectiveness for crowd management in high-density environments.

Keywords : Deep Learning, Human Detection, YOLOv8, Computer Vision, CCTV Surveillance, Real-Time Alert System, Tkinter GUI, Video Analytics, Automated Alarm System.

References :

1. Chen, Y., Cheng, K., & Huang, X. (2020). A Survey of Deep Learning for Big Data. IEEE Transactions on Big Data, 6(4), 606-625.
2. Zhang, Y., Zhang, J., & Li, X. (2019). Smart City Video Surveillance System Based on Machine Learning. 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).
3. Li, S., Li, Y., Liu, Y., Liu, Y., Zhao, D., & Zou, Q. (2020). Intelligent Video Surveillance System Based on Deep Learning. 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE).
4. He, S., Shuai, Z., Zhou, Q., Bai, X., Cheng, M. M., & Zhang, J. (2020). An AI-based Crowd Monitoring System: Unseen Feature Learning and Context Reasoning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
5. Wu, X., & Zhang, Z. (2019). A Survey on Learning to Detect Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8), 1936- 1959.
6. Yang, Y., Zhu, Y., Gao, L., Jiang, H., & Cao, X. (2020). A Survey on Object Detection in Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 58(10), 7215-7238.
7. Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2019). A Survey on Deep Transfer Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
8. Yao, Q., Wang, D., Zhang, K., Chen, S., Liu, Q., & Gong, Y. (2019). Towards Making Unbiased Metric Learning: Adaptive Separation Loss. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
9. Wang, J., Ding, H., Zhou, Y., & Cheng, J. (2019). Vehicle Detection in Aerial Images: A Review and Benchmark Dataset. IEEE Transactions on Geoscience and Remote Sensing, 58(11), 7833-7852.
10. Zhang, H., Wang, Y., & Kong, F. (2020). Crowd Density Estimation via Adversarial Video Generation. 2020 IEEE International Conference on Multimedia and Expo (ICME).
11. Li, Z., & Zhang, Z. (2019). Crowd Counting with Deep Structured Scale Integration Network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
12. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards RealTime Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems (NeurIPS).
13. Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic Understanding of Scenes through ADE20K Dataset. International Journal of Computer Vision, 127(3), 302-321.
14. Luo, W., Li, Y., Urtasun, R., & Zemel, R. (2018). Understanding the Effective Receptive Field in Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems (NeurIPS).
15. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., & Reed, S. (2016). SSD: Single Shot MultiBox Detector. European Conference on Computer Vision (ECCV)