Automated segmentation of textured dust storms on mars remote sensing images using an encoder-decoder type convolutional neural network
Automated segmentation of textured dust storms on mars remote sensing images using an encoder-decoder type convolutional neural network
复制标题
DOI：
10.1016/j.cageo.2022.105043
复制
发表时间：
2022-01-29
影响因子：
4.4
通讯作者：
Gichu, Ryusei
中科院分区：
文献类型：
--
作者：
Ogohara, Kazunori;Gichu, Ryusei
提出了一种在遥感图像上探测火星沙尘暴并识别其大小和形状的方法。该方法基于卷积神经网络，这是使用深度学习进行图像分类和识别的算法之一。我们训练了三种不同结构的模型，使用了几个季节观察到的火星两个可见光波段的图像，以及作者手动准备的地面实况图像，这些图像给出了沙尘暴的真实形状。这两个地区是北方半球的阿卡迪亚平原西部和南半球的希腊盆地，这两个地区都是沙尘暴活动频繁的地区。案例研究表明，在阿卡迪亚平原图像上训练的模型往往比在希腊盆地图像上训练的模型表现得更好。虽然在阿卡迪亚平原的图像上测试时，由两个地区的图像训练的第三模型相对于专用模型表现出很少的退化，但在希腊盆地的情况下，它们的性能明显下降。此外，性能退化是更明显的模型与中等深度比最深的模型。这部分是因为希腊盆地全年都比邻近地区更亮，其内部的尘埃光学厚度高，使得沙尘暴的纹理相对不清楚。相比之下，任何模型都表现出可比的性能在阿卡迪亚平原沙尘暴分割和混合数据从两个地区具有完全不同的表面图案只产生轻微的性能下降。它表明，训练模型与来自不同地区的图像可能会产生一个regionindependent模型，可以有效地应用于分割的沙尘暴在一个广泛的区域。
We propose a method for detecting Martian dust storms and recognizing their size and shape on remote sensing images. The method is based on a convolutional neural network, one of algorithms that use deep learning for image categorization and recognition. We trained models with three different structures using images of two regions of Mars in visible wavelengths observed over several seasons, together with ground truth images manually prepared by the authors that give the true shapes of the dust storms. The two regions were the western Arcadia Planitia in the northern hemisphere and the Hellas Basin in the southern hemisphere, both of which are areas where high dust storm activity has been observed. The case study showed that models trained on images of the Arcadia Planitia tended to perform better than comparable models trained by images of the Hellas Basin. While third models trained by images of both regions showed little degradation relative to the dedicated models when tested on image of the Arcadia Planitia, their performances clearly decreased in the case of the Hellas Basin. Furthermore, the performance degradation was more pronounced for a model with moderate depth than for a deepest model. This is partially because the Hellas Basin is brighter than the adjacent areas throughout the year and high optical thickness of dust in its interior makes the textures of dust storms relatively unclear. In contrast, any models showed comparable performances in dust storm segmentation in the Arcadia Planitia and mixing data from the two regions with completely different surface patterns produced only a slight degradation of performance. It suggests that training the model with images from various regions may yield a regionindependent model that can be effectively applied to the segmentation of dust storms over a wide area.