首页|基于改进U-Net的遥感图像语义分割

基于改进U-Net的遥感图像语义分割

扫码查看
原文链接
  • 万方数据
  • 维普
全卷积神经网络在遥感图像语义分割中得到了广泛应用,该方法地物分类精度和效率较高,但对地物分布不均匀遥感图像占比较少地物的分类准确率较低.为了提高遥感图像的分类精度,本文通过添加先验知识方法丰富输入数据特征,采用密集链接方式提高上下采样过程中特征的重复利用率,采用可以优化交并比的损失函数Dice Loss和可以提高难分类类别精度的损失函数Focal Loss相加组合作为网络模型的损失函数,采用LayerScale模块加快模型收敛、抑制无用特征、突出有效特征的方式,对U-Net的输入、网络结构、损失函数进行改进,优化语义分割效果.结果表明,基于高分影像数据集(GID)改进的U-Net相较于原始U-Net像素精度、均类像素精度、平均交并比分别提高了 0.023 3、0.040 9、0.066 5,提升了地物分类精度,取得了较好的分类效果.
Semantic Segmentation of Remote Sensing Images Based on Improved U-Net
Fully convolutional neural network has been widely used in semantic segmentation of remote sensing images,and the accuracy and efficiency of feature classification are high,but for remote sensing images with uneven distribution of features,the accuracy of feature classification is low.In order to improve the classification accuracy of remote sensing images,this paper enriches the input data features by adding priori knowledge methods,uses the dense link method to improve the reuse rate of features in the process of up and down sampling,combines the loss function Dice Loss that can optimize the intersection of union and the Focal Loss that can improve the accuracy of difficult classification categories as the loss function of the network,and uses the LayerScale module to accelerate the model convergence and suppress irrelevant features while emphasizing useful features,improves input,network structure and loss function of U-Net to optimize the effect of semantic segmentation.The results show that,compared with the original U-Net,the improved U-Net based on Gaofen image dataset is improved by 0.023 3,0.040 9 and 0.066 5 in terms of pixel accuracy,average pixel accuracy and mean intersection of union,respectively,which improves the classification accuracy of ground objects and achieves better classification effects.

deep learningmulti-featuredense linkingFocal LossDice LossLayerScale moduleimproved U-Netsemantic segmentation

高康哲、王凤艳、刘子维、王明常

展开 >

吉林大学地球探测科学与技术学院,长春 130026

深度学习 多特征 密集链接 Focal Loss Dice Loss LayerScale模块 改进U-Net 语义分割

国家自然科学基金项目国家自然科学基金项目自然资源部城市国土资源监测与仿真重点实验室开放基金项目吉林省自然科学基金项目

4207724242171407KF-2020-05-02420210101098JC

2024

10.13278/j.cnki.jjuese.20230145

吉林大学学报(地球科学版)
吉林大学

吉林大学学报(地球科学版)

CSTPCD北大核心
影响因子：1.062
ISSN：1671-5888
年,卷(期)：2024.54(5)