基于协同判读机制的养殖蟹塘遥感智能检测方法

蒋卓然; 周鑫鑫; 曹伟; 王亚华; 吴长彬

doi:10.6046/zrzyyg.2022307

基于协同判读机制的养殖蟹塘遥感智能检测方法

1.南京师范大学地理科学学院,南京 210023

;2.南京邮电大学地理与生物信息学院,南京 210023

;3.南京师范大学虚拟地理环境教育部重点实验室,南京 210023

;4.江苏省地理信息资源开发与利用协同创新中心,南京 210023

;5.南京国图信息产业有限公司,南京 210000

基金项目:
国家自然科学基金项目“不动产统一登记驱动下的地籍混合维度空间数据表达模型研究”(41471318)

南京邮电大学引进人才科研启动基金项目“服务设施空间配置优化算法研究”(NY221143)

虚拟地理环境教育部重点实验室开放基金项目“移动数据驱动下服务设施空间配置量子优化算法研究”(2021VGE02)

详细信息

作者简介: 蒋卓然(1998-),女,硕士研究生,主要从事深度学习影像解译等方面的研究。Email: 201302090@njnu.edu.cn。

通讯作者: 吴长彬(1977-),男,教授,主要从事时空数据模型等方面的研究。Email: wuchangbin@njnu.edu.cn。

中图分类号: TP79

收稿日期: 2022-07-27

修回日期: 2022-08-22

刊出日期: 2023-09-19

Intelligent detection of crab ponds using remote sensing images based on a cooperative interpretation mechanism

1. School of Geography, Nanjing Normal University, Nanjing 210023, China

;2. School of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

;3. Key Lab of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210023, China

;4. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023,China

;5. Nanjing Guotu Information Industry Co., Ltd., Nanjing 210000, China

More Information

Corresponding author: WU Changbin

Received Date: 27 July 2022

Revised Date: 22 August 2022

Publish Date: 19 September 2023

摘要

摘要: 挖塘养蟹是耕地“非粮化”行为的一种,若不及时发现制止,将对国家粮食安全造成危害。为了应对这一行为在遥感智能解译工作中所存在的人工判读量大、核查效率不足的挑战,提出了一种基于协同判读机制的养殖蟹塘遥感智能检测方法,该方法集成了HRNet分割网络和Swin-Transformer分类网络模型,并进一步介入人工核查,提高检测精度和工作效率。以江苏省南京市高淳区为研究区域进行了实验,结果表明,提出的基于协同判读机制的耕地“非粮化”遥感智能检测方法能够自动筛去83.4%的待检测图斑,最终识别精度为0.972,可在大幅降低识别难度与人工核查工作量的同时提高检测精度,为实现准确高效的蟹塘等“非粮”地物检测提供可靠的解决思路。
- 协同判读机制 /
- HRNet /
- Swin-Transformer /
- 蟹塘检测 /
- 非粮化
Abstract: Digging ponds to raise crabs is a non-grain behavior of cultivated land, endangering national food security. However, the intelligent interpretation of remote sensing images targeting this behavior faces challenges such as laborious manual interpretation and low verification efficiency. Based on a cooperative interpretation mechanism, this study proposed an intelligent method for detecting crab ponds using remote sensing images. This method, integrating the HRNet segmentation network and the Swin-Transformer classification network models and combining manual verification, improved the detection accuracy and work efficiency. The application results of this method to Gaochun District, Nanjing City, Jiangsu Province show that the method for intelligent detection can automatically determine 83.4% of the spots for detection, with final identification accuracy of 0.972. The method proposed in this study can significantly reduce the identification difficulty and manual verification workload while improving the detection accuracy. Therefore, this study will provide a reliable solution for the accurate and efficient detection of non-grain surface features such as crab ponds.
- cooperative interpretation mechanism /
- HRNet /
- Swin-Transformer /
- crab pond detection /
- non-grain

HTML全文

施引文献

资源附件(0)

访问统计

计量

文章访问数: 18
PDF下载数: 4
施引文献: 0

中国自然资源航空物探遥感中心	主办
地质出版社	出版

基于协同判读机制的养殖蟹塘遥感智能检测方法

作者简介: 蒋卓然(1998-),女,硕士研究生,主要从事深度学习影像解译等方面的研究。Email: 201302090@njnu.edu.cn。

通讯作者: 吴长彬(1977-),男,教授,主要从事时空数据模型等方面的研究。Email: wuchangbin@njnu.edu.cn。

Intelligent detection of crab ponds using remote sensing images based on a cooperative interpretation mechanism

Corresponding author: WU Changbin

计量

出版历程

目录