Considerable efforts have been devoted to Oriented Object Detection (OOD). However, one lasting issue regarding the discontinuity in Oriented Bounding Box (OBB) representation remains unresolved, which is an inherent bottleneck for extant OOD methods. This paper endeavors to completely solve this issue in a theoretically guaranteed manner and puts an end to the ad-hoc efforts in this direction. Prior studies typically can only address one of the two cases of discontinuity: rotation and aspect ratio, and often inadvertently introduce decoding discontinuity, e.g. Decoding Incompleteness (DI) and Decoding Ambiguity (DA) as discussed in literature. Specifically, we propose a novel representation method called Continuous OBB (COBB), which can be readily integrated into existing detectors e.g. Faster-RCNN as a plugin. It can theoretically ensure continuity in bounding box regression which to our best knowledge, has not been achieved in literature for rectangle-based object representation. For fairness and transparency of experiments, we have developed a modularized benchmark based on the open-source deep learning framework Jittor's detection toolbox JDet for OOD evaluation. On the popular DOTA dataset, by integrating Faster-RCNN as the same baseline model, our new method outperforms the peer method Gliding Vertex by 1.13% mAP50 (relative improvement 1.54%), and 2.46% mAP75 (relative improvement 5.91%), without any tricks.

翻译：有向目标检测（OOD）领域已投入了大量研究努力。然而，有向边界框（OBB）表示的固有瓶颈——表示不连续性问题——仍未得到根本解决。本文旨在以理论保证的方式彻底解决这一问题，并终结该方向上碎片化的应对尝试。既有研究通常仅能处理两类不连续性情形（旋转与宽高比）之一，且常在不经意间引入解码不连续性，例如文献中讨论的解码不完整性（DI）和解码模糊性（DA）。具体而言，我们提出了一种名为连续OBB（COBB）的新型表示方法，可便捷集成至现有检测器（如Faster-RCNN）中作为插件。该方法能理论上保证边界框回归的连续性——据我们所知，这在基于矩形的目标表示文献中尚未实现。为实现实验的公平性与透明性，我们基于开源深度学习框架计图（Jittor）的检测工具箱JDet，开发了面向OOD评估的模块化基准。在主流DOTA数据集上，以Faster-RCNN为统一基线模型，我们的新方法在不使用任何技巧的情况下，相较对比方法Gliding Vertex实现了1.13%的mAP50提升（相对改善1.54%），以及2.46%的mAP75提升（相对改善5.91%）。