文章摘要信息

[an error occurred while processing this directive]

世界地质 2023, 42(4) 731-739 DOI: ISSN: 1004-5589 CN: 22-1111/P

本期目录 | 下期目录 | 过刊浏览 | 高级检索 [打印本页] [关闭]

基础地质

	扩展功能

	本文信息
	Supporting info
	PDF(1875KB)
	[HTML全文]
	参考文献[PDF]
	参考文献
	服务与反馈
	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	引用本文
	Email Alert
	文章反馈
	浏览反馈信息
	本文关键词相关文章

	城市核心地物要素
	多特征信息
	语义信息
	卷积神经网络
	本文作者相关文章
	罗修杰
	刘子维
	徐梦霞
	王明常
	PubMed
	Article by Luo X
	Article by Liu Z
	Article by Xu M
	Article by Wang M

基于多特征信息的城市核心地物要素提取方法研究: 以深圳市为例

罗修杰1 , 刘子维2 , 徐梦霞2 , 王明常2

1. 深圳市福田区应急管理局, 广东深圳 518017;

2. 吉林大学地球探测科学与技术学院, 长春 130026

摘要：为了解决由于空间分辨率低导致城市核心地物要素提取精度低的问题, 笔者构建了适用于城市核心地物要素提取的卷积神经网络模型 ( convolutional neural network, CNNs), 同时利用基于遥感影像提取的颜色? 纹理和形状等多特征信息辅助城市地物要素提取? 颜色? 纹理和形状等多特征信息与 CNNs 模型提取的深层信息相结合, 融合浅层与深层特征信息, 充分挖掘影像数据中的高级语义信息, 能够有效地提高结果精度? 实验结果表明, CNNs 模型减少了模型参数量与复杂度, 模型收敛速度快, 具有较高的提取精度? 泛化能力和鲁棒性, 总体精度为 97. 49% , Kappa 系数为 0. 957 5? 该研究可以为城市发展与规划提供技术支持?

关键词：城市核心地物要素多特征信息语义信息卷积神经网络

Extraction method of urban core feature elements based on multi?feature information: a case study of Shenzhen City

LUO Xiujie 1 , LIU Ziwei 2 , XU Mengxia 2 , WANG Mingchang 2

1. Emergency Management Bureau of Futian District, Shenzhen Municipality, Shenzhen 518017, Guangdong, China;

2. College of Geo?Exploration Science and Technology, Jilin University, Changchun 130026, China

Abstract: In order to address the issue of low extraction accuracy of urban core feature elements caused by low spatial resolution, the authors have developed convolutional neural networks (CNNs) applicable to the extrac? tion of urban core feature elements. At the same time, multi?feature information such as color, texture, and shape extracted based on remote sensing images have been used to assist the extraction of urban feature elements. The CNNs model fully exploits the high?level semantic information in the image data by combining multi?feature informa? tion, such as color, texture, and shape, with the deep information it has extracted. This combination can signifi? cantly increase the accuracy of the results. According to the experimental findings, the CNNs model decreases the number and complexity of model parameters, converges quickly, and exhibits good extraction accuracy, generaliza? tion ability, and robustness. Its overall accuracy is 97. 49% , and its Kappa coefficient is 0. 957 5. Thus, the re? search can offer technical assistance for urban planning and development.

Keywords: urban core feature elements multi?feature information semantic information convolutional neural network

收稿日期 修回日期 网络版发布日期

DOI:

基金项目:

通讯作者:

作者简介:

作者Email:

参考文献：

本刊中的类似文章

1．赵汉卿, 李超, 郭诚, 陈晓明, 张博 . 渤海湾盆地莱州湾凹陷沙三上段近源砂质辫状河三角洲沉积特征[J]. 世界地质, 2024,43(1): 37-46

2．付秀丽, 李军辉, 郑强, 崔坤宁, 王跃文,贾琼, 蒙启安. 松辽盆地北部青山口组富烃页岩形成环境与成因[J]. 世界地质, 2024,43(1): 19-36

3．孙乙庭,孟昕,李永林,刘传军,刘建新,刘加利,王树武. 新型单组分喷涂聚氨酯对改进蓄水大坝工程止水性的试验研究[J]. 世界地质, 2024,43(1): 136-142