Aircraft Detection in Airport Remote Sensing Images based on YOLOv5

With the development of remote sensing, aerospace, and other related technologies, remote sensing image application scenarios are more and more extensive. In this paper, the training of remote sensing data in different airports is improved based on the YOLOv5 (You Only Look Once) model. Based on the analysis of existing deep learning frameworks and models, a remote sensing image segmentation program is designed to solve the problems of large-scale, large variation, and multiple data channels of remote sensing images. To improve the performance of small object detection, the original image is segmented on the detector. When the size of the original image is large, it will be reduced in the detector input, and the number of pixel representatives of small targets will be seriously reduced, leading to the degradation of detector detection performance. So, we propose the purpose of image segmentation and separation detection is to reduce the loss of small target pixels during image reduction. It shows great advantages in solving the problem of precision and speed of aircraft identification, and it is feasible to identify aircraft with a computer quickly and efficiently.