S2A-AGC-Net: Enhanced Aerial Image Object Detector

Abstract

In naturalistic settings, object detection methodologies utilizing horizontal anchors exhibit commendable performance. However, when applied to remote sensing contexts, these methods may engender complications such as anchor misalignment and target-anchor overlap. This study addresses these challenges by introducing the S2A-AGC-Net, a rotating object enhancement network designed specifically for remote sensing applications. The S2A-AGC-Net integrates online data augmentation, group convolution, and lightweight CARAFE operators. For backbone feature extraction, an advanced strategy combining group convolution with ResNet101 enhances feature extraction capabilities. In the neck segment, the original FPN component is refined with the lightweight CARAFE upsampling operator, improving feature fusion and model speed. Additionally, a novel online data augmentation technique that combines Mosaic, Mixup, and HSV color transformations is introduced at the input to enhance the model’s generalization capacity. Ablation studies conducted on the HRSC2016 datasets reveal that the S2A-AGC-Net attains a mean Average Precision (mAP) value of 0.6048 while achieving 18.5 FPS, surpassing the benchmark S2A-Net by 3.38%. Performance evaluations on the more intricate DOTA datasets show a 1.39% improvement over the S2A-Net benchmark. Comparative analyses with existing state-of-the-art algorithms further corroborate the superior accuracy and efficiency of our proposed method. The findings underscore the effectiveness of integrating advanced augmentation techniques and efficient network architecture in improving detection outcomes. The progressive nature of the S2A-AGC-Net positions it as a promising solution for addressing the challenges of object detection in increasingly complex environments, paving the way for future research and development in remote sensing applications.