In oriented object detection, current representations of oriented bounding boxes (OBBs) often suffer from boundary discontinuity problem. Methods of designing continuous regression losses do not essentially solve this problem. Although Gaussian bounding box (GBB) representation avoids this problem, directly regressing GBB is susceptible to numerical instability. We propose linear GBB (LGBB), a novel OBB representation. By linearly transforming the elements of GBB, LGBB avoids the boundary discontinuity problem and has high numerical stability. In addition, existing convolution-based rotation-sensitive feature extraction methods only have local receptive fields, resulting in slow feature aggregation. We propose ring-shaped rotated convolution (RRC), which adaptively rotates feature maps to arbitrary orientations to extract rotation-sensitive features under a ring-shaped receptive field, rapidly aggregating features and contextual information. Experimental results demonstrate that LGBB and RRC achieve state-of-the-art performance. Furthermore, integrating LGBB and RRC into various models effectively improves detection accuracy.

翻译：在有向目标检测中，当前有向边界框（OBB）的表示方法常受边界不连续问题困扰。设计连续回归损失函数的方法并未从根本上解决此问题。尽管高斯边界框（GBB）表示避免了该问题，但直接回归GBB容易导致数值不稳定性。本文提出线性高斯边界框（LGBB），一种新型OBB表示方法。通过对GBB元素进行线性变换，LGBB既避免了边界不连续问题，又具有较高的数值稳定性。此外，现有基于卷积的旋转敏感特征提取方法仅具有局部感受野，导致特征聚合速度缓慢。我们提出环形旋转卷积（RRC），该方法自适应地将特征图旋转至任意方向，在环形感受野下提取旋转敏感特征，快速聚合特征与上下文信息。实验结果表明，LGBB和RRC达到了最先进的性能。进一步地，将LGBB和RRC集成到多种模型中可有效提升检测精度。