Camera-based Security Alarming System
Keywords:
Artificial intelligence (AI), CAM module, Camera-based security system, Closed-circuit television (CCTV), Internet of Things (IoT)Abstract
The camera-based security system leverages advanced AI and IoT technologies to provide real-time surveillance and alerting capabilities, ensuring proactive threat detection and response. At its core, it integrates the YOLO object detection model with an ESP32 CAM module for live video streaming, enabling the identification of suspicious activities such as fights, weapons, or theft. By utilizing a pre-trained ONNX model, the system achieves high accuracy in detecting various security threats, reducing false alarms, and improving reliability. When a potential threat is identified, the system immediately captures relevant frames and sends alerts to a designated Telegram chat, attaching images and detailed descriptions of the detected activities. This ensures that security personnel or users receive instant updates, allowing them to take immediate action. Additionally, a built-in alarm feature enhances situational awareness, deterring potential intruders and ensuring swift responses to threats. For comprehensive security analysis, the system also saves detection frames with timestamps, allowing users to review past incidents and enhance future security measures. The user-friendly interface supports live monitoring through OpenCV and provides seamless notification integration via Telegram. With its adaptability, the system is ideal for various applications, including residential security, public spaces, and industrial facilities, delivering enhanced safety and real-time protection.
References
Z. Zou, Z. Shi, Y. Guo, and J. Ye, “Deep learning for object detection: A review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 10, pp. 3212-3232, 2018. Available: https://ieeexplore.ieee.org/document/8334469
L. Zhang, Y. Chen, and M. Li, “Real-time security systems using deep learning and edge computing,” IEEE Transactions on Industrial Informatics, vol. 17, no. 2, pp. 1230-1241, 2021. Available: https://ieeexplore.ieee.org/document/9292473
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. Available: https://arxiv.org/abs/1506.02640.
Y. Zhao et al., “DETRs beat YOLOs on real-time object detection,” arXiv preprint arXiv:2304.08069, Apr. 2023. [Online]. Available: https://arxiv.org/abs/2304.08069
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” arXiv:2207.02696 [cs], Jul. 2022, Available: https://arxiv.org/abs/2207.02696
