干旱区生态环境知识资源中心(Arid): 基于深度学习的寒旱区遥感影像河流提取

Arid

	基于深度学习的寒旱区遥感影像河流提取
其他题名	River Extraction from Remote Sensing Images in Cold and Arid Regions Based on Deep Learning
	沈瑜; 苑玉彬; 彭静; 陈小朋; 杨倩
来源期刊	农业机械学报
ISSN	1000-1298
出版年	2020
卷号	51 期号:7 页码:192-201
中文摘要	寒旱区河流提取对该地区生态环境监测、农业规划、灾害预警等具有重要意义。根据寒旱区特点制作了面向寒旱区遥感影像河流识别的专业数据集;为了提高网络的识别准确率,融合迁移学习与深度学习,将ResNet50网络迁移到Linknet网络,得到R-Linknet网络;为了提取到更多的细节信息和增加提取河流的连贯性,将密集空间金字塔池化与R-Linknet网络相结合,扩大网络的感受野;训练时,将Dice系数损失函数与二分类交叉熵函数相结合,作为新的损失函数。数据集验证结果表明,本文提出的方法与多种语义分割网络相比,像素准确率较FCN_8s、ResNet50、DeeplabV3、Unet和原始Linknet网络分别提高0.216、0.099、0.031、0.056和0.023,交并比分别提高0.19、0.142、0.056、0.105和0.028;加入Dense ASPP之后,像素准确率提高0.023,交并比提高0.050,采用新的损失函数进行训练后,像素准确率和交并比又分别提高0.019和0.022。该方法提取到的河流更加清晰、连贯,能够满足后续的研究需求。
英文摘要	The extraction of rivers in cold and arid regions is of great significance in the application of ecological environment monitoring, agricultural planning, and disaster early warning in cold and arid regions.In recent years, there have been more studies on river extraction, but river extraction for cold and arid regions is still in its infancy.The rapid development of deep learning provides new ideas for river extraction in cold and arid regions.A professional data set was produced based on the characteristics of cold and arid regions to provide support for river extraction in remote sensing images in cold and arid regions.Combining transfer learning and deep learning, the ResNet50 network was migrated to the Linknet network to obtain the R-Linknet network, which was used to improve the recognition accuracy of the network.At the same time, the dense atrous spatial pyramid pooling was combined with the R-Linknet network to expand the receptive field of the network, which can extract more detailed information and increase the coherence of the extracted river.A new loss function was combined with the Dice Loss function and the binary cross entropy loss function during training.The verification on the data set showed that compared with semantic segmentation networks, the proposed method had an accuracy rate of 0.216, 0.099, 0.031, 0.056 and 0.023 higher than that of FCN_8s, ResNet50, DeeplabV3, Unet and the original Linknet network, respectively, and the intersection over union was increased by 0.190, 0.142, 0.056, 0.105 and 0.028, respectively.After adding dense atrous spatial pyramid pooling, it increased the pixel accuracy by 0.023, and improved the intersection over union by 0.050.After training with the new loss function, the pixel accuracy and crossover ratios were increased by 0.019 and 0.022, respectively.The rivers extracted by this method were more clear and consistent, and can meet the needs of subsequent research.
中文关键词	河流提取 ; 寒旱区 ; 深度学习 ; 遥感影像
英文关键词	river extraction cold and arid area deep learning remote sensing image
类型	Article
语种	中文
收录类别	CSCD
WOS研究方向	Computer Science
CSCD记录号	CSCD:6753236
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/336646
作者单位	沈瑜, 兰州交通大学电子与信息工程学院, 兰州, 甘肃 730070, 中国.; 苑玉彬, 兰州交通大学电子与信息工程学院, 兰州, 甘肃 730070, 中国.; 彭静, 兰州交通大学电子与信息工程学院, 兰州, 甘肃 730070, 中国.; 陈小朋, 兰州交通大学电子与信息工程学院, 兰州, 甘肃 730070, 中国.; 杨倩, 兰州交通大学电子与信息工程学院, 兰州, 甘肃 730070, 中国.
推荐引用方式 GB/T 7714	沈瑜,苑玉彬,彭静,等. 基于深度学习的寒旱区遥感影像河流提取[J],2020,51(7):192-201.
APA	沈瑜,苑玉彬,彭静,陈小朋,&杨倩.(2020).基于深度学习的寒旱区遥感影像河流提取.农业机械学报,51(7),192-201.
MLA	沈瑜,et al."基于深度学习的寒旱区遥感影像河流提取".农业机械学报 51.7(2020):192-201.