Currently, reliable and accurate ship detection in optical remote sensing images is still challenging. Even the state-of-the-art convolutional neural network (CNN) based methods cannot obtain very satisfactory results. To more accurately locate the ships in diverse orientations, some recent methods conduct the detection via the rotated bounding box. However, it further increases the difficulty of detection, because an additional variable of ship orientation must be accurately predicted in the algorithm. In this paper, a novel CNN-based ship detection method is proposed, by overcoming some common deficiencies of current CNN-based methods in ship detection. Specifically, to generate rotated region proposals, current methods have to predefine multi-oriented anchors, and predict all unknown variables together in one regression process, limiting the quality of overall prediction. By contrast, we are able to predict the orientation and other variables independently, and yet more effectively, with a novel dual-branch regression network, based on the observation that the ship targets are nearly rotation-invariant in remote sensing images. Next, a shape-adaptive pooling method is proposed, to overcome the limitation of typical regular ROI-pooling in extracting the features of the ships with various aspect ratios. Furthermore, we propose to incorporate multilevel features via the spatially-variant adaptive pooling. This novel approach, called multilevel adaptive pooling, leads to a compact feature representation more qualified for the simultaneous ship classification and localization. Finally, detailed ablation study performed on the proposed approaches is provided, along with some useful insights. Experimental results demonstrate the great superiority of the proposed method in ship detection.

中文翻译：

---

一种新的基于 CNN 的方法，用于通过旋转边界框在 HR 光学遥感图像中准确检测船舶

目前，光学遥感图像中可靠且准确的船舶检测仍然具有挑战性。即使是最先进的基于卷积神经网络 (CNN) 的方法也无法获得非常令人满意的结果。为了更准确地定位不同方向的船只，最近的一些方法通过旋转的边界框进行检测。然而，它进一步增加了检测的难度，因为在算法中必须准确预测船舶方向的附加变量。在本文中，通过克服当前基于CNN的船舶检测方法的一些常见缺陷，提出了一种新的基于CNN的船舶检测方法。具体来说，为了生成旋转区域提议，当前的方法必须预先定义多向锚，并在一个回归过程中一起预测所有未知变量，限制了整体预测的质量。相比之下，基于观察到船舶目标在遥感图像中几乎是旋转不变的，我们能够独立地预测方向和其他变量，并且更有效地使用新型双分支回归网络。接下来，提出了一种形状自适应池化方法，以克服典型的常规 ROI 池化在提取具有各种纵横比的船舶特征时的局限性。此外，我们建议通过空间变化自适应池合并多级特征。这种称为多级自适应池化的新颖方法导致更适合同时进行船舶分类和定位的紧凑特征表示。最后，提供了对所提出的方法进行的详细消融研究，以及一些有用的见解。实验结果证明了该方法在船舶检测中的巨大优越性。