融合Transformer结构的高分辨率遥感影像变化检测网络

doi:10.13474/j.cnki.11-2246.2022.0229

测绘通报 ›› 2022, Vol. 0 ›› Issue (8): 36-40,92.doi: 10.13474/j.cnki.11-2246.2022.0229

融合Transformer结构的高分辨率遥感影像变化检测网络

冯炜明¹, 张新长¹, 孙颖², 姜明¹, 甘巧¹, 侯幸幸¹

1. 广州大学地理科学与遥感学院, 广东广州 510006;
2. 中山大学地理科学与规划学院, 广东广州 510275

收稿日期:2022-02-17 发布日期:2022-09-01
通讯作者: 张新长。E-mail:zhangxc@gzhu.edu.cn
作者简介:冯炜明(1997-),男,硕士生,主要研究方向为智慧城市与城市遥感。E-mail:942846432@qq.com
基金资助:
国家重点研发计划(2018YFB2100702);国家自然科学基金面上项目(42071441);智慧广州时空信息云平台关键技术——时空大数据一体化整合与自适应动态更新模块研发与咨询服务项目(GZIT2016-A5-147)

High-resolution remote sensing image change detection network with Transformer structure

FENG Weiming¹, ZHANG Xinchang¹, SUN Ying², JIANG Ming¹, GAN Qiao¹, HOU Xingxing¹

1. School of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, China;
2. School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, China

Received:2022-02-17 Published:2022-09-01

摘要/Abstract

摘要： 为解决遥感影像变化检测全局上下文信息捕获的问题,本文提出了基于孪生结构、跳跃连接结构及Transformer结构的TSU-Net。该模型编码器采用混合CNN-Transformers结构,借助自注意力机制捕获遥感影像的全局上下文信息,增强了模型对于像素级遥感影像变化检测任务的长距离上下文建模能力。该模型在LEVIR-CD数据集和CDD数据集进行测试,F1得分分别为90.73和93.14,优于各对比模型。

关键词: 深度学习, 遥感影像变化检测, Transformer, TSU-Net

Abstract: In order to solve the problem of global context information capture in remote sensing image change detection, this paper proposes TSU-Net based on twin structure, jump link structure and Transformer structure. The model encoder adopts a hybrid CNN-Transformers structure to capture the global context information of remote sensing images with the help of self-attention mechanism, which enhances the model's ability of long distance context modeling for pixel-level remote sensing image change detection task. The model is tested in the LEVIR-CD dataset and the CDD dataset, and the F1 scores are 0.9073 and 0.9314, respectively, which are superior to the comparison models.

Key words: deep learning, remote sensing image change detection, Transformer, TSU-Net

中图分类号:

P237

冯炜明, 张新长, 孙颖, 姜明, 甘巧, 侯幸幸. 融合Transformer结构的高分辨率遥感影像变化检测网络[J]. 测绘通报, 2022, 0(8): 36-40,92.

FENG Weiming, ZHANG Xinchang, SUN Ying, JIANG Ming, GAN Qiao, HOU Xingxing. High-resolution remote sensing image change detection network with Transformer structure[J]. Bulletin of Surveying and Mapping, 2022, 0(8): 36-40,92.

参考文献

[1] SINGH A.Review article digital change detection techniques using remotely-sensed data[J].International Journal of Remote Sensing, 1989, 10(6): 989-1003.
[2] 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): 1885-1898.
[3] 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.
[4] CAYE DAUDT R,LE SAUX B,BOULCH A.Fully convolutional Siamese networks for change detection[C]//Proceedings of the 25th IEEE International Conference on Image Processing.Greece: IEEE,2018: 4063-4067.
[5] PENG Daifeng,ZHANG Yongjun,GUAN Haiyan.End-to-end change detection for high resolution satellite images using improved UNet++[J].Remote Sensing,2019,11(11): 1382.
[6] 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.
[7] CHEN Hao,QI Zipeng,SHI Zhenwei.Remote sensing image change detection with transformers[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60: 1-14.
[8] 田青林,秦凯,陈俊,等.基于注意力金字塔网络的航空影像建筑物变化检测[J].光学学报,2020,40(21):47-56.
[9] CHEN01 Jieneng,LU Yongyi,YU Qihang,et al.TransUNet: transformers make strong encoders for medical image segmentation[EB/OL].[2022-02-01].https://arxiv.org/abs/2102.04306.
[10] CHEN Kaiqiang,FU Kun,GAO Xin,et al.Building extraction from remote sensing images with deep learning in a supervised manner[C]//Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium.Fort Worth:IEEE,2017: 1672-1675.
[11] RONNEBERGER O,FISCHER P,BROX T.U-net: convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science.Cham: Springer International Publishing,2015: 234-241.
[12] BROMLEY J,GUYON I,LECUN Y,et al.Signature verification using a “Siamese” time delay neural network[C]//Proceedings of the 6th International Conference on Neural Information Processing Systems.New York: ACM,1993: 737-744.
[13] 向阳,赵银娣,董霁红.基于改进UNet孪生网络的遥感影像矿区变化检测[J].煤炭学报,2019,44(12): 3773-3780.
[14] 倪良波,卢涵宇,卢天健,等.基于孪生残差神经网络的遥感影像变化检测[J].计算机工程与设计,2020,41(12):3451-3457.
[15] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16x16 words: transformers for image recognition at scale[EB/OL].2020: arXiv: 2010.11929.https://arxiv.org/abs/2010.11929.

融合Transformer结构的高分辨率遥感影像变化检测网络

High-resolution remote sensing image change detection network with Transformer structure

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]	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.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	张晋赫, 秦育罗, 张在岩, 宋伟东, 朱洪波. 复杂场景下农村道路裂缝分割方法[J]. 测绘通报, 2022, 0(5): 74-78,88.
[5]	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.
[6]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[7]	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.
[8]	孙琴琴, 蔡国印, 杨柳忠, 张宁, 杜明义. 城市尺度典型地表要素综合提取方法研究[J]. 测绘通报, 2022, 0(2): 62-66.
[9]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[10]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[11]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[12]	淳锦, 张新长, 郭海京, 张建国, 金诗程. 基于多源信息与深度学习特征提取的人口空间抽样方法[J]. 测绘通报, 2021, 0(8): 42-47.
[13]	李梓豪, 唐超. 基于高清工业相机的盾构隧道裂缝智能识别算法分析[J]. 测绘通报, 2021, 0(8): 83-87,101.
[14]	苏艺凡, 党建武, 王阳萍, 杨景玉. 改进的区间二型模糊聚类遥感影像变化检测[J]. 测绘通报, 2021, 0(7): 44-51,58.
[15]	吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.