面向建筑物变化检测的主体边缘分解与重组神经网络

doi:10.11947/j.AGCS.2023.20210350

测绘学报 ›› 2023, Vol. 52 ›› Issue (1): 71-81.doi: 10.11947/j.AGCS.2023.20210350

面向建筑物变化检测的主体边缘分解与重组神经网络

叶沅鑫^1,2, 孙苗苗¹, 周亮¹, 杨超¹, 刘天逸¹, 郝思媛³

1. 西南交通大学地球科学与环境工程学院, 四川成都 611756;
2. 高速铁路安全运营空间信息技术国家地方联合工程实验室, 四川成都 611756;
3. 青岛理工大学信息与控制工程学院, 山东青岛 266520

收稿日期:2021-06-21 修回日期:2022-05-18 发布日期:2023-02-09
通讯作者: 郝思媛 E-mail:lemonbanana@163.com
作者简介:叶沅鑫(1985—),男,博士,副教授,研究方向为遥感影像分析与处理。E-mail: yeyuanxin@swjtu.edu.cn
基金资助:
国家自然科学基金(41971281)

Main body, edge decomposition and reorganization network for building change detection

YE Yuanxin^1,2, SUN Miaomiao¹, ZHOU Liang¹, YANG Chao¹, LIU Tianyi¹, HAO Siyuan³

1. School of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China;
2. State-Province Joint Engineer Laboratory in Spatial Information Technology for High-Speed Railway Safety, Chengdu 611756, China;
3. College of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, China

Received:2021-06-21 Revised:2022-05-18 Published:2023-02-09
Supported by:
The National Natural Science Foundation of China (No.41971281)

摘要/Abstract

摘要： 针对建筑物变化检测中传统神经网络方法易产生锯齿形边界,难以准确识别密集建筑物区域变化地物边界的问题,本文提出一种基于主体、边缘分解与重组网络的变化检测方法。该方法基于地物主体内部像元间相似性较强,而边缘像元间相似性较弱的特点,构建对地物主体与边缘分别建模的变化检测模型。该模型首先通过孪生残差网络结构提取双时相多尺度差值特征:然后,利用可学习的流域分离出地物的主体特征和边缘特征;其次,设计特征优化结构,利用主体标签和边缘标签对分离后的主体特征和边缘特征进行精准优化;最后,将优化后的主体特征和边缘特征进行重组,形成端到端的变化检测模型。通过在公开的建筑物数据集LEVIR-CD进行试验,结果表明,相较于基于U-Net网络的方法和结合时空注意力的方法,该方法能够准确识别变化建筑物的边界,获得更优的检测结果。

关键词: 特征分离, 特征优化, 特征重组, 变化检测

Abstract: Traditional neural network methods for building change detection tend to produce the saw-tooth boundaries, and they are difficult to accurately identify change boundaries in dense building areas. To address that, this paper proposes a change detection method based on main body, edge decomposition and reorganization network. The proposed method performs change detection by respectively modeling body and edges features of buildings, which is on the basis on the characteristics of strong similarity between the body pixels and weak similarity between the edge pixels. In the definition of the proposed method, we first yield dual-temporal multi-scale difference features using a Siamese ResNet structure, and then separate the body features and edge features of buildings by learning a flow field. Subsequently, a feature optimization structure is designed to refine the body and edge features using the body and edge tags. Finally, the optimized body and edge features are reorganized to generate an end-to-end change detection model. Experiments have been performed by using the publicly available building dataset LEVIR-CD, and the results show that the proposed method can accurately identify the boundaries of changing buildings, and obtain better results compared with the methods based on U-Net network and these combining spatial-temporal attention.

Key words: feature decomposition, feature optimization, feature reorganization, change detection

中图分类号:

P227

叶沅鑫, 孙苗苗, 周亮, 杨超, 刘天逸, 郝思媛. 面向建筑物变化检测的主体边缘分解与重组神经网络[J]. 测绘学报, 2023, 52(1): 71-81.

YE Yuanxin, SUN Miaomiao, ZHOU Liang, YANG Chao, LIU Tianyi, HAO Siyuan. Main body, edge decomposition and reorganization network for building change detection[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(1): 71-81.

参考文献

[1] 张志强, 张新长, 辛秦川, 等. 结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J]. 测绘学报, 2018, 47(1): 102-112. DOI: 10.11947/j.AGCS.2018.20170483. ZHANG Zhiqiang, ZHANG Xinchang, XIN Qinchuan, et al. Combining the pixel-based and object-based methods for building change detection using high-resolution remote sensing images[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(1): 102-112. DOI: 10.11947/j.AGCS.2018.20170483.
[2] JI Shunping, SHEN Yanyun, LU Meng, 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.
[3] 吴纹辉, 慎利, 董新丰, 等. 面向高分辨率遥感影像建筑物变化检测的边缘感知网络[J]. 地理与地理信息科学, 2021, 37(3): 21-28. WU Wenhui, SHEN Li, DONG Xinfeng, et al. Edge sensing network for building change detection in high resolution remote sensing images[J]. Geography and Geo-Information Science, 2021, 37(3): 21-28.
[4] JAVED A, JUNG S, LEE W H, et al. Object-based building change detection by fusing pixel-level change detection results generated from morphological building index[J]. Remote Sensing, 2020, 12(18): 2952.
[5] WANG Chang, WANG Xu. Building change detection from multi-source remote sensing images based on multi-feature fusion and extreme learning machine[J]. International Journal of Remote Sensing, 2021, 42(6): 2246-2257.
[6] 王志盼, 沈彦, 王亮, 等. 单类分类框架下的高分辨率遥感影像建筑物变化检测算法[J]. 武汉大学学报(信息科学版), 2020, 45(10): 1610-1618. WANG Zhipan, SHEN Yan, WANG Liang, et al. High-resolution remote sensing image building change detection based on one-class classifier framework[J]. Geomatics and Information Science of Wuhan University, 2020, 45(10): 1610-1618.
[7] 王昶, 张永生, 纪松, 等. 建筑物变化的多特征融和及随机多图综合检测法[J]. 测绘学报, 2021, 50(2): 235-247.DOI:10.11947/j.AGCS.2021.20200097. WANG Chang, ZHANG Yongsheng, JI Song, et al. Multi-feature fusion and random multi-graph synthetic building change method[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(2): 235-247. DOI:10.11947/j.AGCS.2021.20200097.
[8] CAO Shisong, DU Mingyi, ZHAO Wenji, et al. Multi-level monitoring of three-dimensional building changes for megacities: trajectory, morphology, and landscape[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 167: 54-70.
[9] DAI Yuchao, ZHANG Jing, HE Mingyi, et al. Salient object detection from multi-spectral remote sensing images with deep residual network[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2): 101-110.
[10] SUN Long, WU Tao, SUN Guangcai, et al. Object detection research of SAR image using improved faster region based convolutional neural network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3): 18-28.
[11] FAN Dazhao, DONG Yang, ZHANG Yongsheng. Satellite image matching method based on deep convolutional neural network[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2): 90-100.
[12] JIANG Huiwei, HU Xiangyun, LI Kun, et al. PGA-SiamNet: pyramid feature-based attention-guided Siamese network for remote sensing orthoimagery building change detection[J]. Remote Sensing, 2020, 12(3): 484.
[13] WANG Kexian, ZHENG Shunyi, LI Rui, et al. A deep double-channel dense network for hyperspectral image classification[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 46-62.
[14] SAHA S, BOVOLO F, BRUZZONE L. Building change detection in VHR SAR images via unsupervised deep transcoding[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(3): 1917-1929.
[15] LI Lu, WANG Chao, ZHANG Hong, et al. Urban building change detection in SAR images using combined differential image and residual U-net network[J]. Remote Sensing, 2019, 11(9): 1091.
[16] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
[17] LIU Wei, XU Jiawei, GUO Zihui, et al. Building footprint extraction from unmanned aerial vehicle images via PRU-net: application to change detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 2236-2248.
[18] 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 Yueqing. Building change detection in remote sensing images based on FlowS-unet[J]. Acta Automatica Sinica, 2020, 46(6): 1291-1300.
[19] CHEN Hao, SHI Zhenwei. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J]. Remote Sensing, 2020, 12(10): 1662.
[20] CHEN Jie, YUAN Ziyang, PENG Jian, et al. DASNet: dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 1194-1206.
[21] LIU Yi, PANG Chao, ZHAN Zongqian, et al. Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(5): 811-815.
[22] LI Xiangtai, LI Xia, ZHANG Li, et al. Improving semantic segmentation via decoupled body and edge supervision[M]. Cham: Springer International Publishing, 2020: 435-452.
[23] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, U.S.: IEEE, 2016:770-778.
[24] LI Kaiyu, LI Zhe, FANG Sheng. Siamese NestedUNet networks for change detection of high resolution satellite image[C]//Proceedings of the 1st International Conference on Control, Robotics and Intelligent System. Xiamen, China: ACM Press, 2020: 42-48.
[25] DOSOVITSKIY A, FISCHER P, ILG E, et al. FlowNet: learning optical flow with convolutional networks[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 2758-2766.
[26] YE Yuanxin, SHEN Li, HAO Ming, et al. Robust optical-to-SAR image matching based on shape properties[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(4): 564-568.
[27] HAO Siyuan, WANG Wei, YE Yuanxin, et al. Two-stream deep architecture for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 56(4): 2349-2361.

面向建筑物变化检测的主体边缘分解与重组神经网络

Main body, edge decomposition and reorganization network for building change detection

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]	张祖勋, 姜慧伟, 庞世燕, 胡翔云. 多时相遥感影像的变化检测研究现状与展望[J]. 测绘学报, 2022, 51(7): 1091-1107.
[2]	梁哲恒, 黎宵, 邓鹏, 盛森, 姜福泉. 融合多尺度特征注意力的遥感影像变化检测方法[J]. 测绘学报, 2022, 51(5): 668-676.
[3]	罗卿莉, 崔峰志, 魏钜杰, 明磊. SAR影像变化检测的前景特征流形排序法[J]. 测绘学报, 2022, 51(11): 2365-2378.
[4]	王昶, 张永生, 纪松, 张磊. 建筑物变化的多特征融和及随机多图综合检测法[J]. 测绘学报, 2021, 50(2): 235-247.
[5]	叶沅鑫, 孙苗苗, 王蒙蒙, 谭鑫. 结合邻域信息和结构特征的遥感影像变化检测[J]. 测绘学报, 2021, 50(10): 1349-1357.
[6]	赵生银, 安如, 朱美如. 联合像元-深度-对象特征的遥感图像城市变化检测[J]. 测绘学报, 2019, 48(11): 1452-1463.
[7]	Yun ZHANG. 智能摄影测量和图像处理在高分辨率光学遥感影像处理中的应用——CRC-AGIP实验室的案例[J]. 测绘学报, 2018, 47(6): 722-729.
[8]	王建明, 史文中, 邵攀. 自适应距离和模糊拓扑优化的模糊聚类SAR影像变化检测[J]. 测绘学报, 2018, 47(5): 611-619.
[9]	张志强, 张新长, 辛秦川, 杨晓羚. 结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J]. 测绘学报, 2018, 47(1): 102-112.
[10]	冯文卿, 眭海刚, 涂继辉, 孙开敏. 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.
[11]	张鑫龙, 陈秀万, 李飞, 杨婷. 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.
[12]	虢英杰, 朱兰艳. 高分辨率遥感影像变化检测的频域分析预处理方法[J]. 测绘学报, 2017, 46(6): 743-752.
[13]	冯文卿, 眭海刚, 涂继辉, 孙开敏, 黄伟明. 高分辨率遥感影像的随机森林变化检测方法[J]. 测绘学报, 2017, 46(11): 1880-1890.
[14]	张良培, 武辰. 多时相遥感影像变化检测的现状与展望[J]. 测绘学报, 2017, 46(10): 1447-1459.
[15]	庄会富, 邓喀中, 范洪冬. 纹理特征向量与最大化熵法相结合的SAR影像非监督变化检测[J]. 测绘学报, 2016, 45(3): 339-346.