基于语义分割的遥感影像建筑变化检测

doi:10.3969/j.issn.0255-8297.2023.03.007

应用科学学报 ›› 2023, Vol. 41 ›› Issue (3): 448-460.doi: 10.3969/j.issn.0255-8297.2023.03.007

基于语义分割的遥感影像建筑变化检测

尹美杰¹, 倪翠¹, 王朋^1,2, 张广渊¹

1. 山东交通学院信息科学与电气工程学院, 山东济南 250357;
2. 山东省科学院自动化研究所, 山东济南 250013

收稿日期:2022-06-22 出版日期:2023-05-30 发布日期:2023-06-16
通信作者: 倪翠,副教授,研究方向为数字图像处理。E-mail:emilync@126.com E-mail:emilync@126.com
基金资助:
中国博士后科学基金(No.2021M702030)；山东省交通运输厅科技计划项目基金(No.2021B120)资助

Building Change Detection in Remote Sensing Images Based on Semantic Segmentation

YIN Meijie¹, NI Cui¹, WANG Peng^1,2, ZHANG Guangyuan¹

1. School of Information Science and Electric Engineering, Shandong Jiaotong University, Jinan 250357, Shandong, China;
2. Institute of Automation, Shandong Academy of Sciences, Jinan 250013, Shandong, China

Received:2022-06-22 Online:2023-05-30 Published:2023-06-16

摘要/Abstract

摘要： 遥感影像变化检测是利用多时相影像确定一定时间内地物或现象的变化，提供地物空间变化的定性与定量信息。传统遥感影像变化检测方法主要基于地面纹理及空间特征的方法，存在着难以精确识别遥感影像中新增建筑物的问题，为此该文提出了一种基于 UNet网络的遥感影像建筑物变化检测方法。首先，将轻量级高效通道注意力机制网络（efficientchannel attention network, ECANet），注入到原 UNet 网络模型，调整并优化网络结构，提升影像分割的准确度。然后改进 SENet 网络参数，提高遥感影像中的建筑物变化检测的精度。该文在高分辨率数据集 LIVER-CD 上进行实验，结果表明，所提方法的语义分割准确度达到99.03%，建筑变化检测准确率达到 98.62%。相比于其他方法，该方法增强了影像的有效特征，提升了遥感影像中地面建筑物的检测精度。

关键词: 改进 UNet, 注意力机制, 语义分割, 遥感影像, 建筑物变化检测

Abstract: Remote sensing image change detection is to use multi-temporal images to determine the changes of objects or phenomena within a certain period of time, and to provide qualitative and quantitative information on spatial changes of objects. Traditional remote sensing image change detection methods are mainly based on ground texture and spatial features, which is difficult to accurately identify new buildings in remote sensing images. Therefore, this paper adopts a building change detection method based on UNet network. Firstly, the lightweight efficient channel attention network (ECANet) is injected into the original UNet network model to adjust and optimize the network structure and improve the accuracy of image segmentation. The parameters of SENet are then tuned to enhance the accuracy of building change detection in remote sensing images. Experiments on a high-resolution dataset LIVER-CD show that the accuracy of the proposed method reaches a semantic segmentation accuracy of 99.03% and a building change detection accuracy of 98.62%. Compared with other methods, the proposed method can effectively enhance the effective features of images and improve the detection accuracy of ground buildings in remote sensing images.

Key words: improved UNet, attentional mechanism, semantic segmentation, remote sensing image, building change detection

中图分类号:

P237

尹美杰, 倪翠, 王朋, 张广渊. 基于语义分割的遥感影像建筑变化检测[J]. 应用科学学报, 2023, 41(3): 448-460.

YIN Meijie, NI Cui, WANG Peng, ZHANG Guangyuan. Building Change Detection in Remote Sensing Images Based on Semantic Segmentation[J]. Journal of Applied Sciences, 2023, 41(3): 448-460.

参考文献

[1] Wen D W, Xin H. A novel automatic change detection method for urban high-resolution remotely sensed imagery based on multiindex scene representation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1): 609-625.
[2] Walter V. Object-based classification of remote sensing data for change detection [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58(3/4): 225-238．
[3] Celik T. Multiscale change detection in multitemporal satellite images [J]. Geoscience and Remote Sensing Letters, 2009, 6(4): 820-824.
[4] Celik T, Ma K K. Multitemporal image change detection using undecimated discrete wavelet transform and active contours [J]. IEEE Transactions on Geoscience & Remote Sensing, 2011, 49(2): 706-716.
[5] Mura D M, Jon A B. An unsupervised technique based on morphological filters for change detection in very high-resolution images [J]. Geoscience and Remote Sensing Letters, 2008, 5(3): 433-437.
[6] 李亮，王蕾，孙晓鹏，等．面向对象变化向量分析的遥感影像变化检测[J]. 遥感信息, 2017, 32(3): 71-77. Li L, Wang L, Sun X P, et al． Remote sensing change detection method based on objectoriented change vector analysis [J]． Remote Sensing Information, 2017, 32(3): 71-77. (in Chinese)
[7] Volpi M, Tui D, Bovolo F, et al. Supervised change detection in VHR images using contextual information and support vector machines [J]. International Journal of Applied Earth Observation and Geoinformation, 2013, 20: 77-85.
[8] Wang Q, Zhang X, Chen G, et al. Change detection based on faster R-CNN for high resolution remote sensing images [J]. Remote Sensing Letters, 2018, 9: 923-932.
[9] Lecun Y, Bottou L. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[10] Evan S, Jonathan L, Trevor D. Fully convolutional networks for semantic segmentation [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2017, 39(4): 640-651.
[11] Zhang M Y, Guang L. Triplet-based semantic relation learning for aerial remote sensing image change detection [J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(2): 266-270.
[12] Zhang M, Shi W. A feature difference convolutional neural network-based change detection method [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 99: 1-15.
[13] Liu Y, Pang C, Zhan Z, 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, 2018, 5: 811-815.
[14] Zhang C X, Yue P. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166: 183-200.
[15] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation [C]//International Conference on Medical Image Computing and ComputerAssisted Intervention, 2015, 9351: 234-241.
[16] Jie H, Li S, Gang S. Squeeze-and-excitation networks [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[17] Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2020: 11531-11539.

基于语义分割的遥感影像建筑变化检测

Building Change Detection in Remote Sensing Images Based on Semantic Segmentation

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]	贾宁, 郑纯军. 融合音频、文本、表情动作的多模态情感识别[J]. 应用科学学报, 2023, 41(1): 55-70.
[2]	刘飞, 李欣. 基于AttentionU-Net的陆地卫星影像云检测[J]. 应用科学学报, 2022, 40(6): 906-917.
[3]	崔卫红, 李佳, 刘宇. 高分遥感影像不同形状建筑物半自动提取与规则化[J]. 应用科学学报, 2022, 40(3): 372-388.
[4]	栗风永, 叶彬, 秦川. 基于奇偶交叉卷积的轻量级图像语义分割网络[J]. 应用科学学报, 2022, 40(3): 448-456.
[5]	陈丽芳, 魏梦如. 基于强化局部特征的3D点云分类与分割网络[J]. 应用科学学报, 2022, 40(2): 328-337.
[6]	魏明军, 周太宇, 纪占林, 张鑫楠. 基于Mask-YOLO的复杂场景口罩佩戴检测[J]. 应用科学学报, 2022, 40(1): 93-104.
[7]	雷前慧, 潘丽丽, 邵伟志, 胡海鹏, 黄瑶. 基于三重注意力机制的新冠肺炎病灶分割模型[J]. 应用科学学报, 2022, 40(1): 105-115.
[8]	汪鹏, 郑文凤, 史进, 金硕, 刘子豪. 基于MFANet和上下文特征融合的遥感影像目标检测[J]. 应用科学学报, 2022, 40(1): 131-144.
[9]	范守祥, 姚俊萍, 李晓军, 程开原. 一种多模特征融合的方面信息情感分类方法[J]. 应用科学学报, 2021, 39(6): 969-982.
[10]	彭宁, 陈爱斌, 周国雄, 陈文洁, 刘晶. 基于正弦注意力表征网络的环境声音识别[J]. 应用科学学报, 2021, 39(4): 641-649.
[11]	王胜科, 任鹏飞, 吕昕, 庄新发. 基于中心点和双重注意力机制的无人机高分辨率图像小目标检测算法[J]. 应用科学学报, 2021, 39(4): 650-659.
[12]	晁剑, 张慧芳, 许长军, 张鹏林. 双时相影像联合不确定性对变化检测精度的影响机理探索[J]. 应用科学学报, 2020, 38(6): 916-923.
[13]	张雨欣, 李熙, 宋杨, 李长辉. 基于“珞珈一号”夜光遥感影像的粤港澳大湾区城市空间形态分析[J]. 应用科学学报, 2020, 38(3): 466-477.
[14]	靳华中, 刘潇龙, 胡梓珂. 一种结合全局和局部特征的图像描述生成模型[J]. 应用科学学报, 2019, 37(4): 501-509.
[15]	毕奇, 童心, 张济勇, 许凯, 张涵, 秦昆. 基于PLSA和BoW的高分遥感影像小型港口检测[J]. 应用科学学报, 2019, 37(3): 301-312.