AIR-SCAN: Aircraft Identification and Recognition using Deep Learning Scanning

The research work explores advanced techniques in object detection frameworks, specifically focusing on Faster R-CNN and YOLOv8, to enhance the accuracy of military aircraft detection. Leveraging the multi-stage Faster R-CNN architecture, we investigate the impact of adjusting anchor ratios, systematically evaluating their influence on the model's ability to detect objects with diverse shapes. Departing from the conventional anchor-based approach, YOLOv8 introduces anchor-free detection, eliminating predefined anchors and increasing robustness to object scale variations. Our experimentation includes anchor ratio configurations and explores the innovative components of YOLOv8, such as the CSPDarknet53 backbone and the C2f module. It aims to contribute insights into optimizing military aircraft detection accuracy, catering to the dynamic and critical nature of aerial threats. By providing a comparative analysis of Faster R-CNN and YOLOv8, we shed light on their strengths and weaknesses, offering valuable considerations for deployment in military contexts. The paper's findings contribute to the continual advancement of computer vision applications in national security, emphasizing the importance of automated detection for efficient and timely threat identification.