基于孪生神经网络的土地利用现状年度变化检测

doi:10.13474/j.cnki.11-2246.2021.0084

测绘通报 ›› 2021, Vol. 0 ›› Issue (3): 91-95,104.doi: 10.13474/j.cnki.11-2246.2021.0084

基于孪生神经网络的土地利用现状年度变化检测

张伟良¹, 刘琦^2,3, 吴长彬^2,3, 杨光迪^2,3

1. 南京国图信息产业有限公司, 江苏南京 210000;
2. 南京师范大学地理科学学院, 江苏南京 210023;
3. 南京师范大学虚拟地理环境教育部重点实验室, 江苏南京 210023

收稿日期:2020-12-07 出版日期:2021-03-25 发布日期:2021-04-02
通讯作者: 杨光迪。E-mail:550898845@qq.com
作者简介:张伟良(1977—),男,硕士,高级工程师,主要从事自然资源管理信息系统研究工作。E-mail:sonia627@163.com
基金资助:
2020年江苏省研究生科研与实践创新计划（SJCX20_0429）

Annual change detection of land use status based on siamese neural network

ZHANG Weiliang¹, LIU Qi^2,3, WU Changbin^2,3, YANG Guangdi^2,3

1. Nanjing Guotu Information Industry Co., Ltd., Nanjing 210000, China;
2. School of Geographical Sciences, Nanjing Normal University, Nanjing 210023, China;
3. Key Laboratory of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210023, China

Received:2020-12-07 Online:2021-03-25 Published:2021-04-02

摘要/Abstract

摘要： 近年来，利用多期高分遥感影像，构建土地利用现状年度变化检测模型，并以此为基础支持土地利用现状年度变化检测的智能化发展，正是当前研究的难点所在。本文探讨了构建土地利用现状年度变化检测模型存在的问题。通过对土地资数据进行预处理，构建基于孪生神经网络的变化检测模型，以及对模型输出结果进行GIS优化获取目标区域的变化图斑，实现针对土地利用现状变化区域的快速提取。试验结果表明，该方法可快速发现不同时期影像中土地利用现状的变化位置，有效提升了土地利用现状年度变化检测的智能化水平，可服务于日常土地利用现状年度变更检查工作。

关键词: 土地利用现状年度变化检测, 自然资源调查监测, 影像变化检测, Siamese网络, 高分遥感影像

Abstract: In recent years, multi-phase high-resolution remote sensing images are used to build an annual change detection model of land use status and support the intelligent development of annual change detection of land use status on this basis, which is exactly the difficulty of current research. This paper discusses the construction of land use status quo of annual change detection model. Through the land information and data preprocessing, change detection based on twin neural network model being constructed, and the result of the model output optimizing GIS in to obtain the variation spot target area achieves rapid extraction according to current situation of land use change area. The experimental results show that this method can quickly find the change locations of land use status in the images in different periods, which effectively improve the intelligent level of annual change detection of land use status, and can serve the daily annual change detection of land use status.

Key words: annual change detection of land use status, natural resources survey and monitoring, image change detection, Siamese network, high-resolution remote sensing image

中图分类号:

P237

张伟良, 刘琦, 吴长彬, 杨光迪. 基于孪生神经网络的土地利用现状年度变化检测[J]. 测绘通报, 2021, 0(3): 91-95,104.

ZHANG Weiliang, LIU Qi, WU Changbin, YANG Guangdi. Annual change detection of land use status based on siamese neural network[J]. Bulletin of Surveying and Mapping, 2021, 0(3): 91-95,104.

参考文献

[1] 刘纪远, 张增祥, 张树文,等. 中国土地利用变化遥感研究的回顾与展望——基于陈述彭学术思想的引领[J]. 地球信息科学学报, 2020, 22(4):680-687.
[2] LAMBIN E F, GEIST H. Land-use and land-cover change:Local processes and global impacts[M]. Berlin:Springer, 2006.
[3] 陈玲,贾佳,王海庆.高分遥感在自然资源调查中的应用综述[J].国土资源遥感,2019,31(1):1-7.
[4] 王涛涛,刘龙威,崔秉良.基于多源地理信息大数据的图斑自动分类技术在城镇村国土调查中的应用[J].测绘与空间地理信息,2019,42(6):102-106.
[5] 韩杰, 王争. 无人机遥感国土资源快速监察系统关键技术研究[J]. 测绘通报, 2008(2):4-6.
[6] CHEN H, SHI Z W. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J]. Remote Sensing, 2020, 12(10):1662.
[7] 冯文卿, 眭海刚, 涂继辉, 等. 联合像素级和对象级分析的遥感影像变化检测[J]. 测绘学报, 2017, 46(9):1147-1155.
[8] 周启鸣. 多时相遥感影像变化检测综述[J]. 地理信息世界, 2011, 9(2):28-33.
[9] LI X J, YANG G H. Adaptive fault-tolerant synchronization control of a class of complex dynamical networks with general input distribution matrices and actuator faults[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(3):559-569.
[10] HAN X P, ZHONG Y F, ZHAO B, et al. Scene classifica-tion based on a hierarchical convolutional sparse auto-encoder for high spatial resolution imagery[J]. International Journal of Remote Sensing, 2016, 38(2):514-536.
[11] MAGGIORI E,TARABALKA Y, CHARPIAT G, et al. Fully convolutional neural networks for remote sensing image classification[C]//IEEE International Geoscience and Remote Sensing Symposium. Beijing:IEEE, 2016.
[12] ZHANG Y, ZHANG E, CHEN W J. Deep neural network for halftone image classification based on sparse auto-encoder[J]. Engineering Applications of Artificial Intelligence, 2016, 50:245-255.
[13] MOU L C, BRUZZONE L, ZHU X X. Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019,57(2):924-935.
[14] ZHANG M Y, XU G L, CHEN K, et al. Triplet-based semantic relation learning for aerial remote sensing image change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(2):266-270.
[15] LIU R C, CHENG Z H, ZHANG L L, et al. Remote sensing image change detection based on information transmission and attention mechanism[J]. IEEE Access, 2019, 7:156349-156359.
[16] GONG M G, ZHAO J J, LIU J, et al. Change detection in synthetic aperture radar images based on deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 27(1):125-138.
[17] ZHAN Y, FU K, YAN M L, et al. Change detection based on deep siamese convolutional network for optical aerial images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10):1845-1849.
[18] HUGHES L H, SCHMITT M, MOU L C, et al. Identifying corresponding patches in SAR and optical images with a pseudo-siamese cnn[J]. IEEE Geoscience and Remote Sensing Letters, 2018,15(5):784-788.

基于孪生神经网络的土地利用现状年度变化检测

Annual change detection of land use status based on siamese neural network

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	刘立, 董先敏, 刘娟, 文学虎. 人机融合智能的遥感解译生产新方法[J]. 测绘通报, 2022, 0(7): 118-123,137.
[2]	高鸣, 周鑫鑫, 刘琦, 杨光迪, 吴长彬. 深度学习网络支持下的农房侵占耕地自动化监测[J]. 测绘通报, 2022, 0(3): 47-53.
[3]	陈海鹏, 张莉, 李淼, 谢雯君, 邱博. 自然资源调查监测地表覆盖成果质检关键技术探讨[J]. 测绘通报, 2022, 0(1): 96-99.
[4]	苏艺凡, 党建武, 王阳萍, 杨景玉. 改进的区间二型模糊聚类遥感影像变化检测[J]. 测绘通报, 2021, 0(7): 44-51,58.
[5]	毛召武, 程结海, 袁占良. 一种高分遥感影像物体分割质量评价方法[J]. 测绘通报, 2016, 0(5): 36-40.