深度学习网络支持下的农房侵占耕地自动化监测

doi:10.13474/j.cnki.11-2246.2022.0076

测绘通报 ›› 2022, Vol. 0 ›› Issue (3): 47-53.doi: 10.13474/j.cnki.11-2246.2022.0076

深度学习网络支持下的农房侵占耕地自动化监测

高鸣^1,2, 周鑫鑫^1,2, 刘琦^1,2, 杨光迪^1,2, 吴长彬^1,2

1. 南京师范大学地理科学学院, 江苏南京 210046;
2. 南京师范大学虚拟地理环境教育部重点实验室, 江苏南京 210046

收稿日期:2021-04-08 发布日期:2022-04-01
通讯作者: 吴长彬。E-mail:wuchangbin@njnu.edu.cn
作者简介:高鸣(1997-),男,硕士生,主要从事土地监测监管与城市规划评价研究。E-mail:gaomingnnu@163.com
基金资助:
国家自然科学基金(41471318);江苏省自然资源科技计划(2021013)

Automatic monitoring of farmland occupation by farm house based on deep learning network

GAO Ming^1,2, ZHOU Xinxin^1,2, LIU Qi^1,2, YANG Guangdi^1,2, WU Changbin^1,2

1. School of Geographical Sciences, Nanjing Normal University, Nanjing 210046, China;
2. Key Laboratory of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210046, China

Received:2021-04-08 Published:2022-04-01

摘要/Abstract

摘要： 近年来,违法占用耕地现象屡禁不止,如何利用人工智能等新一代信息技术,快速摸清农村乱占耕地建房底数,做到"早发现、早制止、严查处",是当前整治农村乱占耕地建房工作的研究难点之一。本文通过对高分辨率自然资源影像数据进行预处理,构建基于深度学习网络的自动化监测模型,应用模型进行预测并对输出结果进行GIS优化和空间叠加。试验结果表明,该方法可以快速监测出疑似侵占耕地的违法房屋,为坚守"耕地红线不突破"的底线提供了智能化技术选择,可服务于整治农村乱占耕地建房工作。

关键词: 自然资源监测;基本农田;深度学习;U-Net网络;高分遥感影像

Abstract: In recent years,illegal occupation of arable land has been repeatedly prohibited.How to use artificial intelligence and other new-generation information technology to quickly figure out the number of illegal occupation of arable land and build houses in rural areas,and achieve"early detection,early stop,strict investigation and punishment ",is one of the current research difficulties in the work of rectifying the illegal occupation of farmland in rural areas.This paper preprocesses high-resolution natural resource image data,and then builds an automated monitoring model based on a deep learning network.Thirdly,it applies model to predict and GIS optimization and spatial overlay of output results.Experimental results show that this method can quickly detect illegal houses that are suspected of occupying cultivated land,and provides intelligent technology options for sticking to the bottom line of" not breaking through the red line of cultivated land",and can serve the work of rectifying building houses on the cultivated land in rural areas.

Key words: natural resource monitoring;basic farmland;deep learning;U-Net network;high-resolution remote sensing image

中图分类号:

P237

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.

GAO Ming, ZHOU Xinxin, LIU Qi, YANG Guangdi, WU Changbin. Automatic monitoring of farmland occupation by farm house based on deep learning network[J]. Bulletin of Surveying and Mapping, 2022, 0(3): 47-53.

参考文献

[1] 钱凤魁,王秋兵,边振兴,等.永久基本农田划定和保护理论探讨[J].中国农业资源与区划, 2013, 34(3):22-27.
[2] 王海波,马明国.基于遥感的湖泊水域动态变化监测研究进展[J].遥感技术与应用, 2009, 24(5):674-684.
[3] KARPATNE A, JIANG Z, VATSAVAI R R, et al. Monitoring land-cover changes:a machine-learning perspective[J]. IEEE Geoscience and Remote Sensing Magazine, 2016, 4(2):8-21.
[4] 王立娟,靳晓,贾虎军,等.基于国产高分卫星数据的矿山环境变化检测[J].国土资源遥感, 2018, 30(3):151-158.
[5] 李亮,舒宁,王凯,等.融合多特征的遥感影像变化检测方法[J].测绘学报, 2014, 43(9):945-953, 959.
[6] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Seattle,WA:IEEE, 2016:770-778.
[7] LONG J, SHELHAMER E, DARRELL T, et al. Fully convolutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA:IEEE, 2015:3431-3440.
[8] CHEN G Z, ZHANG X D, WANG Q, et al. Symmetrical dense-shortcut deep fully convolutional networks for semantic segmentation of very-highresolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(5):1633-1644.
[9] FAUVEL M, BENEDIKTSSON J A, CHANUSSOT J, et al. Spectral and spatial classification of hyperspectral data using svms and morphological profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(11):3804-3814.
[10] MALISIEWICZ T, GUPTA A, EFROS A A, et al. Ensemble of exemplar-SVMs for object detection and beyond[C]//Proceedings of 2011 IEEE International Conference on Computer Vision. Barcelona, Spain:IEEE, 2011:89-96.
[11] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:semantic image segmentation with deep convolutional nets, Atrous Convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
[12] ZHOU L, ZHANG C, WU M, et al. D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT:IEEE, 2018:192-196.
[13] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceeding of 2015 International Conference on Medical Image Computing and Computer-assisted Intervention.[S. I.]:Springer,2015:234-241.
[14] KAMIYA R, HOTTA K, ODA K, et al. Road detection from satellite images by improving U-Net with difference of features[C]//Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods. Funchal, PortugaL:SCITEPRESS,2018:603-607.
[15] ZHANG Z, LIU Q, WANG Y. Road extraction by deep residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5):749-753.
[16] 赵俊娟,尹京苑,单新建.基于形状特征的高分辨率遥感影像目标分割[J].测绘通报, 2005(1):10-13.
[17] 崔建军,隋立春,徐花芝,等.基于边缘检测算法的LiDAR数据建筑物提取[J].测绘科学技术学报, 2008, 25(2):98-100.
[18] 曲延云,郑南宁,李翠华,等.基于支持向量机的显著性建筑物检测[J].计算机研究与发展, 2007, 44(1):141-147.
[19] LEI H O U, YIN D, XIAOJIAN Y O U. An automatic building detection method from remote sensing images[J]. Computer Simulation, 2006, 23(4):184-188.
[20] MATIKAINEN L, HYYPPA J, AHOKAS E, et al. Automatic detection of buildings and changes in buildings for updating of maps[J]. Remote Sensing, 2010, 2(5):1217-1248.
[21] 李东子,范大昭,苏亚龙.结合Faster R-CNN模型的遥感影像建筑物检测[J].测绘科学技术学报, 2018, 35(4):389-394.
[22] 伍广明,陈奇, SHIBASAKI R,等.基于U型卷积神经网络的航空影像建筑物检测[J].测绘学报, 2018, 47(6):864-872.
[23] JI S, SHEN Y, LU M, et al. Building instance change detection from large-scale aerial images using convolutional neural networks and simulated samples[J]. Remote Sensing, 2019, 11(11):1343-1362.

深度学习网络支持下的农房侵占耕地自动化监测

Automatic monitoring of farmland occupation by farm house based on deep learning network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王艳军, 林云浩, 王书涵, 李少春, 王孟杰. OSM辅助车载LiDAR点云三维道路边界精细提取[J]. 测绘通报, 2022, 0(7): 18-25.
[2]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[3]	孔瑞瑶, 谢涛, 马明, 孔瑞林. CatBoost模型在水深反演中的应用[J]. 测绘通报, 2022, 0(7): 33-37.
[4]	温雨笑, 吕杰, 马庆勋, 张鹏, 徐汝岭. 高光谱和LiDAR联合反演森林生物量研究[J]. 测绘通报, 2022, 0(7): 38-42.
[5]	江泽霖, 邓健, 栾海军, 李兰晖. 基于逐日夜间灯光遥感的新冠肺炎疫情变化信息快速提取——以北京市为例[J]. 测绘通报, 2022, 0(7): 43-48.
[6]	郑艳, 何欢, 卜丽静, 金鑫. 自相似性和边缘保持分解的超分辨率重建算法[J]. 测绘通报, 2022, 0(7): 54-59.
[7]	冉崇宪, 李森磊. 利用无人机多光谱影像提取树冠信息[J]. 测绘通报, 2022, 0(7): 112-117.
[8]	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.
[9]	艾敏, 景慧, 田禹东, 郭兰勤, 裴渊杰. 近20年哈尔滨市呼兰区土地利用覆盖变化及驱动分析[J]. 测绘通报, 2022, 0(7): 124-128.
[10]	刘玉贤, 阮明浩, 闫臻. 一种基于机载激光点云的门型电塔精确提取方法[J]. 测绘通报, 2022, 0(7): 129-133.
[11]	刘国超, 彭卫平, 杨水华, 胡周文. 地质雷达+三维测量内窥镜的城市道路病害检测与应用[J]. 测绘通报, 2022, 0(7): 134-137.
[12]	刘小玉, 刘扬, 杜明义, 张敏, 贾竞珏, 杨恒. 基于DeeplabV3+的建筑垃圾堆放点识别[J]. 测绘通报, 2022, 0(4): 16-19,43.
[13]	李佳豪, 周吕, 马俊, 杨飞, 咸凌霄. 利用PS-InSAR技术进行城市地铁沿线形变监测与机理分析[J]. 测绘通报, 2022, 0(4): 20-25.
[14]	师芸, 石龙龙, 牛敏杰, 赵侃. 基于单阶段实例分割网络的黄土滑坡多任务自动识别[J]. 测绘通报, 2022, 0(4): 26-31.
[15]	窦世卿, 陈治宇, 徐勇, 郑贺刚, 苗林林, 宋莹莹. 基于多特征融合与典型降维方法的高光谱影像分类[J]. 测绘通报, 2022, 0(4): 32-36,50.