Aircraft detection in remote sensing imagery has drawn much attention in recent years, which plays an important role in various military and civil applications. While many advanced works have been developed with powerful learning algorithms in natural images, there still lacks an effective one to detect aircraft precisely in remote sensing images, especially in some complicated conditions. In this paper, a novel method is designed to detect aircraft precisely, named aircraft detection using Centre-based Proposal regions and Invariant Features (CPIF), which can handle some difficult image deformations, especially rotations. Our framework mainly contains three steps. Firstly, we propose an algorithm to extract proposal regions from remote sensing imagery. Secondly, an ensemble learning classifier with the rotation-invariant HOG is trained for aircraft classification. Lastly, we detect aircraft in remote sensing images by combining the products of the above steps. The proposed method is evaluated on a public dataset RSOD and the results are performed to demonstrate the superiority and effectiveness in comparison with the state-of-the-art methods.

近年来，遥感图像中的飞机检测引起了广泛关注，在各种军事和民用应用中都发挥着重要作用。尽管已经开发了许多具有强大的自然图像学习算法的高级作品，但仍然缺乏有效的工具来准确地检测遥感图像中的飞机，尤其是在某些复杂条件下。本文设计了一种新颖的方法来精确检测飞机，即使用基于中心的提议区域和不变特征（CPIF），可以处理一些困难的图像变形，尤其是旋转。我们的框架主要包含三个步骤。首先，我们提出了一种从遥感影像中提取提议区域的算法。其次，训练具有旋转不变HOG的集成学习分类器以进行飞机分类。最后，我们结合上述步骤的乘积，在遥感图像中检测飞机。在公共数据集RSOD上对所提出的方法进行了评估，并进行了结果验证，以证明与最新方法相比具有优越性和有效性。