Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary representation as (potentially rotated) ellipses. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a Probabilistic Intersection-over-Union (ProbIoU). Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in publicly available datasets, and that loss functions based on ProbIoU can be successfully used to regress the parameters of the Gaussian representation. Furthermore, we present a simple mapping scheme from traditional (or rotated) bounding boxes to Gaussian representations, allowing the proposed ProbIoU-based losses to be seamlessly integrated into any object detector.

翻译：多数天体探测方法使用捆绑框来编码和代表天体形状和位置。 在这项工作中,我们使用高斯分布式来探索物体区域的模糊表示式。 高斯分布式提供了隐含的二进制表示式( 可能旋转的) 椭圆。 我们还提出了一个基于 Hellinger 距离的高斯分布式的类似测量法, 它可以被视为一种概率性交叉- 联盟( ProbIoU) 。 我们的实验结果表明, 拟议的高斯表示式更接近于在公开的数据集中附加说明的分解面罩, 以 ProbIoU 为基础的损失函数可以成功用于回归高斯表达式参数 。 此外, 我们提出了一个简单的绘图方法, 从传统的( 或旋转的) 捆绑框到高斯 表示式, 使拟议的普罗比约( ProbIoU) 损失能够无缝合在一起到任何天体探测器中。