• Version
• Download 3
• File Size 278.17 KB
• File Count 1
• Create Date 24 March 2026
• Last Updated 24 March 2026

Yolov8: A Deep Learning-Based Method for Intelligent Surveillance Systems for Real-Time Flying Object Detection

Dr. K. Satyam1, Gandla Saikiran2
1Associate Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati,Andhra Pradesh, India.
2 Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.

Abstract:Real-time detection of flying objects, such as birds and aeroplanes, has grown in importance in contemporary environmental monitoring systems, aviation safety, and surveillance. However, because of differences in object size,motion, lighting, and complicated backdrops, it is difficult to correctly identify these objects. A deep learning-based methodfor real-time flying object recognition utilising the YOLOv8 (You Only Look Once version 8) model is presented in this study. Both live camera detection and image-based detection are made possible by the suggested system's integration of a trained YOLOv8 model with  an intuitive web interface created with Flask. After processing input frames, the system detects flying objects and creates bounding boxes with confidence scores for each one. The model effectively detects things like birds and aeroplanes with high accuracy and low latency, according to experimental data. The system's real-time performance makes it appropriate for real-world uses such as automatic detection systems, airspace monitoring, and smart surveillance. The suggested method demonstrates how well YOLOv8 can detect items quickly and accurately. It also offers a scalable framework for future improvements, such as the recognition of more aerial objects and deployment in expansive locations.
Keywords:YOLOv8, Object Detection, Deep Learning, Real-Time Detection, Computer Vision, Flying Object Detection,Surveillance Systems