【摘要】 航空图像目标具有面积比例较小、排列密集、倾斜角度任意等特点。为了达到航空图像目标精确检测的要求，改进了特征提取网络，同时使用椭圆中心采样方法，优化标签采样策略以解决采样不足问题。最后使用无锚点解耦合目标检测头将边界框回归任务与目标分类任务分离以提高检测精度。实验表明，所提方法在DOTA和HRSC2016数据集上分别达到了75.2%和89.1%的mAP，满足了精确检测的要求。更多还原

【Abstract】 Aerial image objects have the characteristics of small area ratio, dense arrangement, and arbitrary inclination angle. In order to meet the requirements of accurate detection of aerial image objects, the feature extraction network is improved, and the ellipse center sampling method is used to optimize the label sampling strategy to solve the problem of insufficient sampling.Finally, an anchor-free decoupling object detection head is used to separate the bounding box regression task from the object classification task to improve detection accuracy. Experiments show that the proposed method achieves 75.2% and 89.1% mAP on the DOTA and HRSC2016 datasets, respectively, which meets the requirements of accurate detection.更多还原