Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (4): 90-96    DOI: 10.6046/gtzyyg.2020.04.13
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
融合Unet网络和IR-MAD的建筑物变化检测方法
徐锐1(), 余小于1, 张驰1, 杨瑨1, 黄宇2, 潘俊1()
1.武汉大学测绘遥感信息工程国家重点实验室,武汉 430079
2.武大吉奥信息技术有限公司,武汉 430223
Building change detection method combining Unet and IR-MAD
XU Rui1(), YU Xiaoyu1, ZHANG Chi1, YANG Jin1, HUANG Yu2, PAN Jun1()
1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
2. Wuda Geoinformatics Company Limited, Wuhan 430223, China
全文: PDF(2287 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

通过遥感影像对城市建筑物进行变化检测,可以全面掌握城市建筑物的规划实施情况,辅助城市管理部门及时发现并依法查处各类违章建筑。提出了一种融合Unet网络和IR-MAD的城市建筑物变化检测方法,首先,分别使用加权小型Unet网络和IR-MAD检测遥感影像中的疑似变化像素; 然后,基于投票的方式融合疑似变化像素检测结果,确定变化像素; 接着通过形态学操作去除斑点噪声、填充变化区域内部孔洞等来优化变化像素区域; 最后,基于建筑物阴影特性去除非建筑物的变化区域,从而得到建筑物变化检测结果。实验表明,该方法比仅使用Unet网络或IR-MAD可更准确地检测出遥感影像中的建筑物变化。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
徐锐
余小于
张驰
杨瑨
黄宇
潘俊
关键词 卷积神经分割网络迭代加权多元变化检测变化检测    
Abstract

The change detection of urban buildings through remote sensing images can help researchers grasp the planning and implementation of urban buildings comprehensively, and assist urban managers to find and investigate illegal buildings. This paper proposes a method for urban building change detection that combines Unet with IR-MAD. This method first uses weighted small Unet and IR-MAD to detect suspected change pixels in remote sensing images, and then fuses the suspected change pixels detection results based on voting to find out change pixels. For optimizing the change pixel areas, morphological operations are performed to remove speckle noise and fill holes in the changed pixel area. Finally, non-building change areas are removed based on the shadow characteristics of the building to obtain building change detection results. Experiments show that this method can detect building changes in remote sensing images more accurately than using only Unet or IR-MAD.

Key wordsconvolutional neural segmentation network    iteratively weighted multivariate change detection    change detection
收稿日期: 2020-01-15      出版日期: 2020-12-23
:  TP79  
基金资助:国家自然科学基金项目“基于临近空间平台的天地一体化信息网络关键技术集成与综合验证”(91738301)
通讯作者: 潘俊
作者简介: 徐 锐(1996-),女,硕士研究生,主要研究方向为遥感影像变化检测、质量改善。Email:sherryxu@whu.edu.cn
引用本文:   
徐锐, 余小于, 张驰, 杨瑨, 黄宇, 潘俊. 融合Unet网络和IR-MAD的建筑物变化检测方法[J]. 国土资源遥感, 2020, 32(4): 90-96.
XU Rui, YU Xiaoyu, ZHANG Chi, YANG Jin, HUANG Yu, PAN Jun. Building change detection method combining Unet and IR-MAD. Remote Sensing for Land & Resources, 2020, 32(4): 90-96.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.04.13      或      https://www.gtzyyg.com/CN/Y2020/V32/I4/90
Fig.1  融合Unet网络和IR-MAD的建筑物变化检测方法流程
Fig.2  非建筑物变化区域去除实例
Fig.3  变化检测样本示例
Fig.4  实验结果
处理步骤 p r F1得分
基于加权小型Unet网络的变化检测结果 0.208 0.620 0.312
基于IR-MAD的变化检测结果 0.246 0.418 0.310
投票融合后的变化检测结果 0.485 0.308 0.376
经过形态学操作优化后的变化检测结果 0.345 0.510 0.412
基于建筑物阴影特性去除非建筑变化区域后的变化检测结果 0.390 0.510 0.442
Tab.1  实验结果
[1] Singh A. Digital change detection techniques using remotely sensed data[J]. International Journal of Remote Sensing, 1988,10(6):989-1003.
[2] Bruzzone L P. Automatic analysis of the difference image for unsupervised change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000,38:1171-1182.
[3] Gupta A P R P. Land-use mapping and change detection in a coal mining area:A case study in the Jharia coalfield,India[J]. International Journal of Remote Sensing, 1998,19(3):391-410.
[4] Jha C S, Unni N V M. Digital change detection of forest conversion of a dry tropical Indian forest region[J]. International Journal of Remote Sensing, 1994,15(13):2543-2552.
[5] Moran M S. A window-based technique for combining Landsat Thematic Mapper thermal data with higher-resolution multispectral data over agricultural lands[J]. Photogrammetric Engineering and Remote Sensing, 1990,56(3):337-342.
[6] 杨存建, 欧晓昆, 党承林, 等. 森林植被动态变化信息的遥感检测[J]. 地球信息科学, 2000,2(4):71-74.
Yang C J, Ou X K, Dang C L, et al. Detecting the change information of forest vegetation in Lushui County of Yunnan Province[J]. Journal of Geo-Information Science, 2000,2(4):71-74.
[7] Malila W A. Change vector analysis:An approach for detecting forest changes with Landsat[C]// Burroff P G.Machine processing of remotely sensed data,and soil information systems,and remote sensing and soil survey:Sixth annual symposium.Indiana:Institute of Electrical and Electronics Engineers, 1980: 385.
[8] Xian G, Homer C, Fry J. Updating the 2001 National Land Cover Database land cover classification to 2006 by using Landsat imagery change detection methods[J]. Remote Sensing of Environment, 2009,113(6):1133-1147.
[9] 申祎, 王超, 胡佳乐. 一种结合空间与光谱信息的改进CVA变化检测方法[J]. 遥感技术与应用, 2019,34(4):799-806.
Shen Y, Wang C, Hu J L. An improved CVA change detection method combining spatial and spectral information[J]. Remote Sensing Technology and Application, 2019,34(4):799-806.
[10] Celik T. Unsupervised change detection in satellite images using principal component analysis and K-means clustering[J]. IEEE Geoscience and Remote Sensing Letters, 2009,6(4):772-776.
[11] 赵秋菊. 改进主成分分析的遥感影像变化检测算法[J]. 测绘与空间地理信息, 2019,42(6):111-113.
Zhao Q J. Remote sensing image change detection algorithm based on improved principal component analysis[J]. Geomatics and Spatial Information Technology, 2019,42(6):111-113.
[12] Zhong J, Wang R. Multi-temporal remote sensing change detection based on independent component analysis[J]. International Journal of Remote Sensing, 2006,27(10):2055-2061.
[13] 钟家强, 王润生. 基于独立成分分析的多时相遥感图像变化检测[J]. 电子与信息学报, 2006,28(6):994-998.
Zhong J Q, Wang R S. Multitemporal remote sensing images change detection based on ICA[J]. Journal of Elections and Information Technology, 2006,28(6):994-998.
[14] Nielsen A A, Conradsen K, Simpson J J. Multivariate alteration detection (MAD) and MAF postprocessing in multispectral,bitemporal image data:New approaches to change detection studies[J]. Remote Sensing of Environment, 1998,64(1):1-19.
[15] Wu C, Du B, Zhang L. Slow feature analysis for change detection in multispectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014,52(5):2858-2874.
[16] Wu C, Zhang L, Du B. Kernel slow feature analysis for scene change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017,55(4):2367-2384.
[17] Nielsen A A. The regularized iteratively reweighted MAD method for change detection in multi-and hyperspectral data[J]. IEEE Transactions on Image Processing, 2007,16(2):463-478.
pmid: 17269639
[18] 张续, 江涛, 胡世明, 等. 迭代加权多元变化检测算法在高分辨率遥感影像变化检测中应用[J]. 计算机应用, 2019,39(s1):177-181.
Zhang X, Jiang T, Hu S M, et al. Application of iteratively re-weighted multivariate alteration detection in high-resolution remote sensing images change detection[J]. Journal of Computer Applications, 2019,39(s1):177-181.
[19] Xian G, Homer C, Fry J. Updating the 2001 national land cover database land cover classification to 2006 by using Landsat imagery change detection methods[J]. Remote Sensing of Environment, 2009,113(6):1133-1147.
[20] 季顺平, 田思琦, 张驰. 利用全空洞卷积神经元网络进行城市土地覆盖分类与变化检测[J]. 武汉大学学报(信息科学版), 2020,45(2):233-241.
Ji S P, Tian S Q, Zhang C. Urban land cover classification and change detection using fully atrous convolutional neural network[J]. Geomatics and Information Science of Wuhan University, 2020,45(2):233-241.
[21] Gil-Yepes J L, Ruiz L A, Recio J A, et al. Description and validation of a new set of object-based temporal geostatistical features for land-use/land-cover change detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016,121:77-91.
[22] 眭海刚, 冯文卿, 李文卓, 等. 多时相遥感影像变化检测方法综述[J]. 武汉大学学报(信息科学版), 2018,43(12):132-145.
Sui H G, Feng W Q, Li W Z, et al. Review of change detection methods for multi-temporal remote sensing imagery[J]. Geomatics and Information Science of Wuhan University, 2018,43(12):132-145.
[23] Ronneberger O, Fischer P, Brox T. U-net:Convolutional networks for biomedical image segmentation[C]// Navab N,Hornegger J,Wells W,et al.Medical image computing and computer-assisted intervention-MICCAI 2015.Munich:Springer Cham, 2015:234-241.
[24] 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, 2016,40(4):834-848.
doi: 10.1109/TPAMI.2017.2699184 pmid: 28463186
[25] Wu H, Zhang J, Huang K, et al. FastFCN:Rethinking dilated convolution in the backbone for semantic segmentation[EB/OL]. (2019-03-28)[2020-01-15]. http://arxiv.org.abs/1903.11816.
[26] Ma L, Liu Y, Zhang X, et al. Deep learning in remote sensing applications:A meta-analysis and review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019,152:166-177.
[27] Chu Y, Cao G, Hayat H. Change detection of remote sensing image based on deep neural networks[C]//Sehiemy R E,Reaz M B I,Lee C J.2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016). Paris:Atlantis Press, 2016:262-267.
[28] Lebedev M A, Vizilter Y V, Vygolov O V, et al. Change detection in remote sensing images using conditional adversarial networks[J]. International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences, 2018,42(2):565-571.
[29] 张鑫龙, 陈秀万, 李飞, 等. 高分辨率遥感影像的深度学习变化检测方法[J]. 测绘学报, 2017,46(8):999-1008.
Zhang X L, Chen X W, Li F, et al. Change detection method for high resolution remote sensing images using deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(8):999-1008.
[30] Vignesh T, Thyagharajan K K, Ramya K. Change detection using deep learning and machine learning techniques for multispectral satellite images[J]. International Journal of Innovative Technology and Exploring Engineering, 2019(9):90-93.
[31] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:A simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014,15(1):1929-1958.
[32] 刘辉, 谢天文. 基于PCA与HIS模型的高分辨率遥感影像阴影检测研究[J]. 遥感技术与应用, 2013,28(1):81-87.
Liu H, Xie T W. Study on shadow detection in high resolution remote sensing image of PCA and HIS model[J]. Remote Sensing of Technology and Application, 2013,28(1):81-87.
[1] 薛白, 王懿哲, 刘书含, 岳明宇, 王艺颖, 赵世湖. 基于孪生注意力网络的高分辨率遥感影像变化检测[J]. 自然资源遥感, 2022, 34(1): 61-66.
[2] 潘建平, 徐永杰, 李明明, 胡勇, 王春晓. 结合相关系数和特征分析的植被区域自动变化检测研发[J]. 自然资源遥感, 2022, 34(1): 67-75.
[3] 李轶鲲, 杨洋, 杨树文, 王子浩. 耦合模糊C均值聚类和贝叶斯网络的遥感影像后验概率空间变化向量分析[J]. 自然资源遥感, 2021, 33(4): 82-88.
[4] 王译著, 黄亮, 陈朋弟, 李文国, 余晓娜. 联合显著性和多方法差异影像融合的遥感影像变化检测[J]. 自然资源遥感, 2021, 33(3): 89-96.
[5] 刁明光, 刘文静, 李静, 刘芳, 王彦佐. 矿山遥感监测矢量成果数据动态变化检测方法[J]. 国土资源遥感, 2020, 32(3): 240-246.
[6] 张春森, 吴蓉蓉, 李国君, 崔卫红, 冯晨轶. 面向对象的高空间分辨率遥感影像箱线图变化检测方法[J]. 国土资源遥感, 2020, 32(2): 19-25.
[7] 冯林艳, 谭炳香, 王晓慧, 陈新云, 曾伟生, 戚曌. 基于分布函数的对象级森林变化快速检测[J]. 国土资源遥感, 2020, 32(2): 73-80.
[8] 刘义志, 赖华荣, 张丁旺, 刘飞鹏, 蒋小蕾, 曹庆安. 多特征混合核SVM模型的遥感影像变化检测[J]. 国土资源遥感, 2019, 31(1): 16-21.
[9] 赵展, 夏旺, 闫利. 基于多源数据的土地利用变化检测[J]. 国土资源遥感, 2018, 30(4): 148-155.
[10] 王立娟, 靳晓, 贾虎军, 唐尧, 马国超. 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.
[11] 朱欣然, 吴波, 张强. 一种改进CVAPS的LUCC分类自动更新方法[J]. 国土资源遥感, 2018, 30(2): 29-37.
[12] 王光辉, 李建磊, 王华斌, 杨化超. 基于多特征融合的遥感影像变化检测算法[J]. 国土资源遥感, 2018, 30(2): 93-99.
[13] 尹凌宇, 覃先林, 孙桂芬, 刘树超, 祖笑锋, 陈小中. 利用KPCA法检测高分一号影像中的森林覆盖变化[J]. 国土资源遥感, 2018, 30(1): 95-101.
[14] 刁娇娇, 龚鑫烨, 李明诗. 利用综合变化检测方法进行土地覆盖变化制图[J]. 国土资源遥感, 2018, 30(1): 157-165.
[15] 何超. 地质灾害体遥感变化信息检测及趋势分析[J]. 国土资源遥感, 2017, 29(s1): 27-33.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发