Nowadays, airport detection in remote sensing images has attracted
considerable attention due to its strategic role in civilian and military
scopes. In particular, uncrewed and operated aerial vehicles must immediately
detect safe areas to land in emergencies. The previous schemes suffered from
various aspects, including complicated backgrounds, scales, and shapes of the
airport. Meanwhile, the rapid action and accuracy of the method are confronted
with significant concerns. Hence, this study proposes an effective scheme by
extending YOLOV3 and ShearLet transform. In this way, MobileNet and ResNet18,
with fewer layers and parameters retrained on a similar dataset, are parallelly
trained as base networks. According to airport geometrical characteristics, the
ShearLet filters with different scales and directions are considered in the
first convolution layers of ResNet18 as a visual attention mechanism. Besides,
the major extended in YOLOV3 concerns the detection Sub-Networks with novel
structures which boost object expression ability and training efficiency. In
addition, novel augmentation and negative mining strategies are presented to
significantly increase the localization phase's performance. The experimental
results on the DIOR dataset reveal that the framework reliably detects
different types of airports in a varied area and acquires robust results in
complex scenes compared to traditional YOLOV3 and state-of-the-art schemes.

本文提出了一种基于 YOLOV3 和 ShearLet 变换的机场检测方案，使用 MobileNet 和 ResNet18 作为基础网络并重训，同时考虑了 ShearLet 滤波器和新颖的检测子网络结构，实验结果在 DIOR 数据集上表现出明显的优越性。

EYNet：用于遥感图像机场检测的扩展 YOLO

EYNet: Extended YOLO for Airport Detection in Remote Sensing Images

The high complexity of various inverse problems poses a significant challenge
to model-based reconstruction schemes, which in such situations often reach
their limits. At the same time, we witness an exceptional success of data-based
methodologies such as deep learning. However, in the context of inverse
problems, deep neural networks mostly act as black box routines, used for
instance for a somewhat unspecified removal of artifacts in classical image
reconstructions. In this paper, we will focus on the severely ill-posed inverse
problem of limited angle computed tomography, in which entire boundary sections
are not captured in the measurements. We will develop a hybrid reconstruction
framework that fuses model-based sparse regularization with data-driven deep
learning. Our method is reliable in the sense that we only learn the part that
can provably not be handled by model-based methods, while applying the
theoretically controllable sparse regularization technique to the remaining
parts. Such a decomposition into visible and invisible segments is achieved by
means of the shearlet transform that allows to resolve wavefront sets in the
phase space. Furthermore, this split enables us to assign the clear task of
inferring unknown shearlet coefficients to the neural network and thereby
offering an interpretation of its performance in the context of limited angle
computed tomography. Our numerical experiments show that our algorithm
significantly surpasses both pure model- and more data-based reconstruction
methods.

本文提出一种将基于模型的稀疏正则化与数据驱动的深度学习相结合的混合重建框架，通过剪切波变换的分解，将可见和不可见分量分别处理，使神经网络只需要学习不可由基于模型方法处理的部分系数，提高了在有限角度计算机断层扫描中的重建性能。