ISPRS Journal of Photogrammetry and Remote Sensing ( IF 12.7 ) Pub Date : 2020-10-07 , DOI: 10.1016/j.isprsjprs.2020.09.022 Haoran Wei , Yue Zhang , Zhonghan Chang , Hao Li , Hongqi Wang , Xian Sun
Oriented object detection in remote sensing images is an active yet challenging task. State-of-the-art detectors adopt oriented bounding box as a basic representation of an object. The design of them always multiplies the number of anchor boxes with arbitrary angles. Coupled with the rotated Non-Maximum-Suppression (NMS) algorithm, their computational complexities and design difficulties are dramatically increased. In this paper, we propose a novel representation form of oriented objects as pairs of middle lines. Along with the new representation, Oriented Objects Detection Network (O-DNet) is proposed to encode and detect these paired middle lines. By eliminating the pre-designed set of anchor boxes and complicated rotated-NMS post-processing, our model runs in an anchor-free and NMS-free manner. Thereby, compared with state-of-the-art bounding-box and anchor-NMS based detectors, O-DNet is simpler and more efficient in the oriented object detection task. Experiments show that O-DNet achieves excellent performances on the DOTA dataset. In fact, the horizontal objects can also be regarded as a unique form of oriented ones with an angle of 90 degrees. O-DNet can also achieve competitive results on the horizontal box dataset, such as DIOR.
中文翻译:
定向对象为中间线对
遥感图像中的定向物体检测是一项积极而又具有挑战性的任务。最先进的检测器采用定向包围盒作为对象的基本表示。它们的设计总是使任意角度的锚框数量成倍增加。结合旋转的非最大抑制(NMS)算法,它们的计算复杂性和设计难度大大增加。在本文中,我们提出了一种新颖的定向对象表示形式,即成对的中线。与新的表示形式一起,面向对象的检测网络(O-DNet)建议用于编码和检测这些成对的中间线。通过消除预先设计的锚定箱集和复杂的旋转NMS后处理,我们的模型以无锚定和无NMS的方式运行。因此,与最先进的包围盒和基于锚NMS的检测器相比,O-DNet在定向对象检测任务中更简单,更高效。实验表明-DNet在DOTA数据集上表现出色。实际上,水平物体也可以视为具有90度角的定向物体的独特形式。Ø-DNet还可以在水平框数据集(例如DIOR)上获得竞争性结果。