Journal of Jilin University(Earth Science Edition) ›› 2021, Vol. 51 ›› Issue (1): 296-306.doi: 10.13278/j.cnki.jjuese.20190321

Previous Articles    

Building Change Detectionin High Resolution Remote Sensing Images Based on FPN Res-Unet

Wang Mingchang1,2, Zhu Chunyu1, Chen Xueye2, Wang Fengyan1, Li Tingting1, Zhang Haiming1, Han Youwen3   

  1. 1. College of GeoExploration Science and Technology, Jilin University, Changchun 130026, China;
    2. Key Laboratory of Urban Land Resources Monitoring and Simulation, MNR, Shenzhen 518000, Guangdong, China;
    3. Institute of Remote Sensing and Surveying and Mapping Qinghai, Xining 810001, China
  • Received:2019-12-30 Published:2021-02-02
  • Supported by:
    Supported by the National Natural Science Foundation of China(41430322),the Project Supported by the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, MNR(KF-2018-03-020,KF-2019-04-080),the Scientific Research Project of the 13th Five-Year Plan of Jilin Province Education Department(JJKH20200999KJ) and the Open Fund of Key Laboratory of Land Subsidence Monitoring and Prevention, Ministry of Natural Resources of China(KLLSMP201901)

PDF (PC)

475

Abstract: In view of the complexity, heavy workload,and low degree of automation in current survey of land resource change detection, a building change detection method of high-resolution remote sensing image based on deep learning model is proposed, and the idea of semantic segmentation is applied to change detection. Based on the better extraction performance of the residual structure than convolution layers and the characteristics of multi-scale prediction of feature pyramid networks, the residual structure and FPN are fused into Unet model to establish FPN Res-Unet. The model is based on Unet with ResNet residual structure as its feature extraction layer. After each convolution, padding is used to keep the size of the input image and the output image consistent. In the process of sampling at each level of the decoding path, the branch path is expanded to fuse FPN into the network trunk of the model. It fully combines the advantages of residual structure, Unet and FPN, which makes it pay attention to details while obtaining deep semantic information, and improves the detection accuracy of building change. Experiments show that the accuracy rate, recall rate and F1 of the method in the data set used reach more than 90%.

Key words: remote sensing image, change detection, ResNet18, Unet, FPN, FPN Res-Unet

CLC Number: 

  • P237
[1] Huang Xin, Zhang Liangpei, Zhu Tingting. Building Change Detection from Multitemporal High-Resolution Remotely Sensed Images Based on a Morphological Building Index[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(1):105-115.
[2] 孙晓霞,张继贤,燕琴,等.遥感影像变化检测方法综述及展望[J].遥感信息,2011(1):119-123. Sun Xiaoxia, Zhang Jixian, Yan Qin, et al. A Summary on Current Techniques and Prospects of Remote Sensing Change Detection[J]. Remote Sensing Information, 2011(1):119-123.
[3] 明冬萍,骆剑承,沈占锋,等.高分辨率遥感影像信息提取与目标识别技术研究[J].测绘科学,2005,30(3):18-20,3. Ming Dongping, Luo Jiancheng, Shen Zhanfeng, et al. Research on Information Extraction and Target Recognition from High Resolution Remote Sensing Image[J]. Science of Surveying and Mapping, 2005, 30(3):18-20,3.
[4] Wang M, Zhang X,Niu X, et al. Scene Classification of High-Resolution Remotely Sensed Image Based on ResNet[J]. Journal of Geovisualization and Spatial Analysis,2019,3:16. doi:10.1007/s41651-019-0039-9.
[5] 唐文博. 基于卷积神经网络的高分辨率多光谱遥感图像上的城区建筑物变化检测技术[D].杭州:浙江大学,2019. Tang Wenbo. Building Change Detection Technology Based on Convention Neural Network in High Resolution Multispectral Remote Sensing Images[D]. Hangzhou:Zhejiang University, 2019.
[6] 顾炼,许诗起,竺乐庆.基于FlowS-Unet的遥感图像建筑物变化检测[J].自动化学报,2020, 46(6):1291-1300. Gu Lian, Xu Shiqi, Zhu Leqing. Change Detection for Buildings in Remote Sensing Images Based on FlowS-Unet[J]. Acta Automatica Sinica, 2020, 46(6):1291-1300.
[7] Myint Soe Win, Lam Nina S N,Tyler John M. Wavelets for Urban Spatial Feature Discrimination[J]. Photogrammetric Engineering and Remote Sensing, 2004, 70(7):803-812.
[8] 宫鹏,黎夏,徐冰.高分辨率影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006(1):1-5. Gong Peng, Li Xia, Xu Bing. Interpretation Theory and Application Method Development for Information Extraction from High Resolution Remotely Sensed Data[J]. Journal of Remote Sensing, 2006(1):1-5.
[9] 黄昕. 高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D].武汉:武汉大学,2009. Huang Xin. Multiscale Texture and Shape Feature Extraction and Object-Oriented Classification for Very High Resolution Remotely Sensed Imagery[D]. Wuhan:Wuhan University, 2009.
[10] 王明常,张馨月,张旭晴,等. 基于极限学习机的GF-2影像分类[J].吉林大学学报(地球科学版),2018,48(2):373-378. Wang Mingchang, Zhang Xinyue, Zhang Xuqing, et al. GF-2 Image Classification Based on Extreme Learning Machine[J]. Journal of Jilin University (Earth Science Edition), 2018,48(2):373-378.
[11] 杨磊.基于多特征Dempster-Shafe证据融合的高分辨率遥感影像建筑物变化检测[D].成都:西南交通大学,2016. Yang Lei. Building Change Detection from Multitemporal High Resolution Remote Sensing Imagery Based on Multi-Features Fusion Using Dempster-Shafer Evidence Theory[D]. Chengdu:Southwest Jiaotong University,2016.
[12] Bouziani M, Goita K, He Dongchen. Automatic Change Detection of Buildings in Urban Environment from Very High Spatial Resolution Images Using Existing Geodatabase and Prior Knowledge[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2010, 65(1):143-153.
[13] Chini M, Pierdicca N, Emery W J. Exploiting SAR and VHR Optical Images to Quantify Damage Caused by the 2003 Bam Earthquake[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(1):145-152.
[14] Cao Guo, Li Yupeng, Liu Yazhou, et al. Automatic Chang Detection in High-Resolution Remote-Sensing Images by Means of Level Set Evolution and Support Vector Machine Classification[J]. International Journal of Remote Sensing,2014,35(16):6255-6270.
[15] 丁海勇,罗麒杰,王晓英.基于形态学纹理特征的高分辨率遥感影像变化检测[J]. 测绘科学技术, 2017, 5(3):143-151. Ding Haiyong, Luo Qijie, Wang Xiaoying. High-Resolution Remote Sensing Image Change Detection Based on Morphological Texture Features[J]. Geomatics Science and Technology,2017,5(3):143-151.
[16] 刘波,燕琴,刘恒飞,等.一种正样本单分类框架下的高分辨率遥感影像建筑物变化检测算法[J].测绘工程, 2019,28(2):52-56. Liu Bo, Yan Qin, Liu Hengfei, et al. A New Building Change Detection Algorithm of High-Resolution Remote Sensing Image Based on One-Class Classifier Framework[J]. Engineering of Surveying and Mapping, 2019, 28(2):52-56.
[17] 季顺平,魏世清.遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J].测绘学报,2019,48(4):448-459. Ji Shunping, Wei Shiqing. Building Extraction via Convolutional Neural Networks from an Open Remote Sensing Building Dataset[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(4):448-459.
[18] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer Verlag, 2015:234-241.
[19] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE Computer Society, 2016:770-778.
[20] 马玥.基于多源遥感信息的湿地土地覆被分类研究[D].长春:吉林大学,2018. Ma Yue. Land Cover Classification of Wetland Based on Multi-Source Remote Sensing[D]. Changchun:Jilin University,2018.
[21] Lin T Y, Dollár P, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]//30th IEEE Conference on Computer Vision and Pattern Recognition. United States:Institute of Electrical and Electronics Engineers, 2017:936-944.
[22] Glorot X, Bordes A, Bengio Y. Deep Sparse Rectifier Neural Networks[J]. Journal of Machine Learning Research,2011,15:315-323.
[23] Ioffe S, Szegedy C. Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[C]//32nd International Conference on Machine Learning. Lile:International Machine Learning Society, 2015:448-456.
[24] 刘丹枫,刘建霞.面向深度学习过拟合问题的神经网络模型[J].湘潭大学自然科学学报,2018,40(2):96-99. Liu Danfeng, Liu Jianxia. A Neural Network Model for the Overfitting Problem in Deep Learning[J]. Natural Science Journal of Xiangtan University, 2018, 40(2):96-99.
[1] Liu Changyuan, Liu Peng, Bi Xiaojun. Land Use Change Prediction Model Based on Adaptive Variable Filter [J]. Journal of Jilin University(Earth Science Edition), 2019, 49(5): 1477-1485.
[2] Wang Mingchang, Zhang Xinyue, Zhang Xuqing, Wang Fengyan, Niu Xuefeng, Wang Hong. GF-2 Image Classification Based on Extreme Learning Machine [J]. Journal of Jilin University(Earth Science Edition), 2018, 48(2): 373-378.
[3] Zhang Shiyue, Shu Longcang, Min Xing, Hu Huijie, Zou Zhike. Calculation of Precipitation Infiltration Recharge Based on Land-Use Type [J]. Journal of Jilin University(Earth Science Edition), 2017, 47(3): 860-867.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Earth Science Edition), All Rights Reserved.
Tel: +86-431-88502374；13756165364　E-mail: xuebao1956@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd