AI-Based Military Threat Detection using YOLOv8

This paper presented an AI-Based Military Threat Detection System using the YOLOv8 object detection model for intelligent military surveillance. A custom dataset of soldiers, intruders, and weapons was manually collected and annotated using Roboflow, and the model was trained and tested using surveillance videos. The system successfully detected the predefined object classes by generating bounding boxes, class labels, and confidence scores in real time. Although the model achieved satisfactory detection performance, its accuracy can be further improved by increasing the dataset size and optimizing the training process. Overall, the proposed system provides an efficient and reliable solution for automated military threat detection.

[1]         J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016.  [2]         J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv preprint arXiv:1804.02767, 2018. [3]       A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020. [4]         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," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [5]         G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLOv8 Documentation, Ultralytics, 2023. [6]         D. Kumawat, D. Abhayankar, and S. Tanwani, "Exploring Object Detection Algorithms and Implementation of YOLOv7 and YOLOv8 Based Model for Weapon Detection," International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 7s, pp. 162–168, 2023.