基于轻量化卷积神经网络模型的云与云阴影检测方法

大多数遥感影像数据不可避免地受到云层的污染导致数据的失效。因此，对云进行检测是非常必要的预处理步骤。随着航天技术的飞速发展，更加轻便的卫星被设计出来，为了在这些算力有限的微小卫星上配备遥感影像预处理模型。设计一种高精度、算力要求低的轻量化云与云阴影检测网络模型具有重要意义。针对上述问题，本研究提出一种基于深度可分离卷积的轻量化卷积神经网络模型（Lightweight M-shaped Network，L-MNet），L-MNet网络模型是在M-Net（ M-shaped Network）网络模型的基础上引入深度可分离卷积（Depthwise Separable Convolution），设计一种深度可分离卷积模块（DS-Conv Block），以减小算法的复杂度及计算量。实验结果表明，本研究所提方法在保证检测精度的前提下，可以有效减小像素级云检测的模型大小及计算量，有助于实现微小卫星在轨云检测的任务。

Research on Lightweight Cloud and Cloud Shadow Detection Method Based on Depthwise Separable Convolution

Most remote sensing image data is inevitably contaminated by clouds, resulting in data failure. Therefore, detecting clouds is a necessary preprocessing step. With the rapid development of space technology, more portable satellites have been designed to equip these micro satellites with remote sensing image preprocessing models. Designing a high-precision and low computational power requirement lightweight cloud and cloud shadow detection network model is of great significance. In response to the above issues, this study proposes a lightweight M-Shaped Network (L-MNet) based on deep separable convolution. The L-MNet network model introduces deep separable convolution (DS Conv Block) on top of the M-Shaped Network model to reduce the complexity and computational complexity of the algorithm. The experimental results show that the proposed method in this study can effectively reduce the model size and computational complexity of pixel level cloud detection while ensuring detection accuracy, and is helpful in achieving the task of small satellite in orbit cloud detection.