基于深度学习的高分辨率遥感图像分割方法

High-resolution remote-sensing image segmentation method based on deep learning

以往高分辨率遥感图像分割方法由于没有对遥感图像中的数据模点进行检测,导致分割精度不高,本文设计了一种基于深度学习的高分辨率遥感图像分割方法。首先,通过对遥感图像进行预处理,保留重要的细节信息;其次,对预处理后的遥感图像进行特征提取,并对特征提取后的图像进行滤波处理,增加图像光谱的一致性;最后,利用深度学习方法对遥感图像中的数据模点进行检测,得到遥感图像的最终分割结果。通过实验并与以往的高分辨率遥感图像分割方法进行对比证明基于深度学习的高分辨率遥感图像分割方法具有更高的分割精度。

Previous high-resolution remote sensing image segmentation methods did not detect the data module points in remote sensing images.In this paper,a high-resolution remote-sensing image segmentation method based on deep learning is designed.First of all,the preprocessing on remote sensing image retains the important details.Then feature extraction is conducted on the remote sensing image and the image filtering is used to increase the image spectral consistency.At last deep learning method is used to detect the data module points in remote sensing images and get the final segmentation results.The experiments show that the proposed high-resolution remote sensing image segmentation method has higher segmentation accuracy compared with previous high-resolution remote sensing image segmentation methods.