Keywords
Computer Vision
Object Detection
Security Surveillance
YOLOv5
Deep Learning.
Article Number
047Abstract
The increasing rate of security threats and the limitations associated with conventional surveillance systems have created a demand for intelligent and automated monitoring solutions. Traditional security systems rely heavily on manual observation, which is often affected by fatigue, delayed response, and human error. This study presents an object identification and detection system for security applications using artificial intelligence and computer vision techniques. The developed system employs the YOLOv5 deep learning algorithm for real-time object detection and classification. The system was implemented using Python programming language with OpenCV and PyTorch libraries for image processing and model deployment. A custom dataset containing humans, vehicles, bags, and weapons was used for model training and testing. Experimental evaluation showed that the system achieved an average detection accuracy of 93% with a processing speed of 28 frames per second (FPS). The system demonstrated efficient performance in detecting multiple objects simultaneously and generating alerts for suspicious objects in real time. The findings reveal that AI-based surveillance systems can significantly improve security monitoring, reduce human intervention, and enhance response efficiency. The study concludes that integrating deep learning models such as YOLOv5 into surveillance infrastructures provides a reliable and scalable solution for intelligent security applications.References
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
Chen, X., Jiang, S., Hu, Y., & Xu, L. (2020). Night-time object detection for surveillance using infrared images and deep learning. Sensors, 20(6), 1730.
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., & Murphy, K. (2017). Speed/accuracy trade-offs for modern convolutional object detectors. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7310–7311.
Jocher, G., Chaurasia, A., & Qiu, J. (2023). YOLO by Ultralytics: Real-time object detection framework. GitHub Repository and Technical Documentation. Available at: https://github.com/ultralytics/yolov5
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single Shot MultiBox Detector. European Conference on Computer Vision (ECCV), 21–37.
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788.
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149.
Tan, M., Pang, R., & Le, Q. V. (2021). EfficientDet: Scalable and efficient object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10781–10790.
Wang, Y., Li, Z., Chen, H., & Zhao, P. (2022). Intelligent surveillance system using deep learning and real-time object tracking. International Journal of Advanced Computer Science and Applications, 13(4), 215–223.
Zhang, H., Wu, C., & Lin, Y. (2023). Lightweight deep learning models for edge-based intelligent surveillance systems. IEEE Access, 11, 45671–45684.
Zhao, Z. Q., Zheng, P., Xu, S. T., & Wang, X. (2019). Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 30(11), 3212–3232.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 2026 Akintunde Michael Yinka, Adeleke Isiaka Adelani, Afolayan Deborah Damilola,, Adebayo Moses Abiodun (Author)