Due to the characteristics of vertical orthophoto imaging, the apparent structural features of the object in the remote sensing (RS) image are relatively stable, such as the cross-shaped structure of the aircraft and the rectangular structure of the vehicle. Compared with the traditional visual features, using these features is conducive to improving the accuracy of object detection. However, there are few studies on such characteristics. In this article, we systematically study the invariant structural features of remote sensing objects and propose a graph focusing aggregation network (GFA-Net) to represent the structural features of remote sensing objects. Among them, in view of the problem that traditional convolutional neural networks (CNNs) are sensitive to the changes in rotation, scale, and other factors, which makes it difficult to extract structural features, we propose the graph focusing process (GFP) based on the idea of graph convolution. Analysis and experiments show that graph structure has significant advantages over Euclidean feature space under CNN in expressing such structural features. In order to realize the end-to-end efficient training of the above model, we design a graph aggregation network (GAN) to update the weight of nodes. We verify the effectiveness of our method on the proposed multitask datasets aircraft component segmentation dataset (ACSD) and the large-scale Fine-grAined object recognItion in high-Resolution RS imagery (FAIR1M). Experiments conducted on the object detection datasets of large-scale Dataset for Object deTection in Aerial images (DOTA) and HRSC2016 prove that the proposed method is superior to the current state-of-the-art (SOTA) method.

中文翻译：

---

基于图建模的遥感目标检测不变结构表示


由于垂直正射影像的特点，遥感图像中物体的表观结构特征相对稳定，如飞行器的十字形结构、车辆的矩形结构等。与传统的视觉特征相比，利用这些特征有利于提高目标检测的准确性。然而，对于这些特性的研究却很少。在本文中，我们系统地研究了遥感物体的不变结构特征，并提出了一种图聚焦聚合网络（GFA-Net）来表示遥感物体的结构特征。其中，针对传统卷积神经网络（CNN）对旋转、尺度等因素的变化敏感，导致难以提取结构特征的问题，我们提出了基于图卷积的思想。分析和实验表明，图结构在表达此类结构特征方面比CNN下的欧氏特征空间具有显着的优势。为了实现上述模型的端到端高效训练，我们设计了图聚合网络（GAN）来更新节点的权重。我们在所提出的多任务数据集飞机部件分割数据集（ACSD）和高分辨率遥感图像中的大规模细粒度对象识别（FAIR1M）上验证了我们的方法的有效性。在大规模航空图像对象检测数据集（DOTA）和HRSC2016的对象检测数据集上进行的实验证明，该方法优于当前最先进的（SOTA）方法。