基于改进DeepLabV3+算法的遥感影像建筑物变化检测

doi:10.13474/j.cnki.11-2246.2023.0119

测绘通报 ›› 2023, Vol. 0 ›› Issue (4): 145-149.doi: 10.13474/j.cnki.11-2246.2023.0119

基于改进DeepLabV3+算法的遥感影像建筑物变化检测

齐建伟¹, 王伟峰¹, 张乐², 王光彦³

1. 黄河水利职业技术学院, 河南开封 475004;
2. 中科北纬(北京)科技有限公司, 北京 100043;
3. 江苏省工程勘测研究院有限责任公司, 江苏扬州 225002

收稿日期:2022-12-29 发布日期:2023-04-25
作者简介:齐建伟(1983—),男,硕士,讲师,主要从事无人机遥感测绘等方面的教学和科研工作。E-mail:154515324@qq.com

Building change detection of remote sensing image based on improved DeepLabV3+

QI Jianwei¹, WANG Weifeng¹, ZHANG Le², WANG Guangyan³

1. Yellow River Conservancy Technical Institute, Kaifeng 475004, China;
2. Zhongke Beiwei (Beijing) Technology Co., Ltd., Beijing 100043, China;
3. Jiangsu Engineering Exploration&Surveying Institute Co., Ltd., Yangzhou 225002, China

Received:2022-12-29 Published:2023-04-25

摘要/Abstract

摘要： 变化检测是遥感测绘领域的重要任务,作为执法依据,在耕地非农化等场景监测中发挥重大作用。近年来,使用人工智能相关技术进行变化检测,常见的技术方案为叠加两期影像,再使用语义分割算法求解变化区域。本文使用变化检测数据集LEVIR-CD作为试验数据,在DeepLabV3+算法基础上,针对变化检测场景特点,对模型结构进行改进。以DeepLabV3+的孪生网络为主干,使用多层级特征交互操作,充分融合图像特征。结果表明,改进的网络结构更加适合变化检测任务场景。

关键词: 变化检测, 深度学习, 卷积神经网络, 语义分割

Abstract: As an important task in the field of remote sensing, change detection plays an important role in the scenes of law enforcement inspection of satellite land image, farmland conversion. In recent years, relevant practitioners have used AI related technologies to solve the task of change detection. The common technical solution is to concatenate two images by channel dimension and use semantic segmentation algorithm to predict the change area. This paper uses the change detection dataset LEVIR-CD as experimental data,based on DeepLabV3+algorithm, improves the model structure according to the characteristics of change detection task. The siamese network uses DeepLabV3+as the backbone. This paper uses multi-level feature interaction to fully fuse image features. The results show that the improved network structure is more suitable for change detection task.

Key words: change detection, deep learning, convolutional neural network, sematic segmentation

中图分类号:

P237

齐建伟, 王伟峰, 张乐, 王光彦. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(4): 145-149.

QI Jianwei, WANG Weifeng, ZHANG Le, WANG Guangyan. Building change detection of remote sensing image based on improved DeepLabV3+[J]. Bulletin of Surveying and Mapping, 2023, 0(4): 145-149.

参考文献

[1] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.
[2] DENG Jia, DONG Wei, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA:IEEE, 2009:248-255.
[3] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of 2016 IEEE Transactions on Pattern Analysis and Machine Intelligence.[S.l.]:IEEE, 2016:640-651.
[4] 刘文祥, 舒远仲, 唐小敏, 等. 采用双注意力机制Deeplabv3+算法的遥感影像语义分割[J]. 热带地理, 2020, 40(2):303-313.
[5] 胡智翔, 鲍胜利, 徐传淇, 等. 基于DeepLabV3+的遥感建筑物语义分割算法[J]. 计算机应用, 2021, 41(S2):71-75.
[6] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].[2022-12-20]. https://arxiv.org/abs/1412.7062.
[7] 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, 2018, 40(4):834-848.
[8] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].[2022-12-20]. https://arxiv.org/abs/1706.05587.
[9] CHEN L C, ZHU Yukun, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of Computer Vision:the 15th European Conference, Munich, Germany. New York:ACM, 2018:833-851.
[10] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL].[2022-12-20]. https://arxiv.org/abs/1511.07122.
[11] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1904-1916.
[12] CHOLLET F. Xception:deep learning with depthwise separable convolutions[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA:IEEE, 2017:1800-1807.
[13] 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.
[14] MISHRA P, SARAWADEKAR K. Polynomial learning rate policy with warm restart for deep neural network[C]//Proceedings of 2019 IEEE Region 10 Conference (TENCON). Kochi:IEEE, 2019:2087-2092.
[15] LOSHCHILOV I, HUTTER F. SGDR:stochastic gradient descent with warm restarts[EB/OL].[2022-10-20]. https://arxiv.org/abs/1608.03983.

基于改进DeepLabV3+算法的遥感影像建筑物变化检测

Building change detection of remote sensing image based on improved DeepLabV3+

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]	蔡军, 温日强, 江伟, 严娇, 卢丽娟. 传统村落航拍图像中民族建筑识别的DeepLabV3+改进算法[J]. 测绘通报, 2023, 0(4): 49-53.
[2]	佘佐明, 申勇智, 宋剑虹, 向玉瑨. 利用经典CNN网络方法构建贵阳市道路要素遥感影像自动提取模型[J]. 测绘通报, 2023, 0(4): 177-182.
[3]	李子彧, 周维勋, 耿万轩. 联合类别筛选与重排序的交叉视角图像地理定位[J]. 测绘通报, 2023, 0(2): 40-45.
[4]	张永彬, 刘雅辉, 刘明月, 满卫东, 宋唐雷, 李春雨. 基于Relief F与卷积神经网络的湿地植物群落精细分类[J]. 测绘通报, 2023, 0(2): 58-64.
[5]	施仲添, 沈正伟, 杨四海. 基于前景感知的遥感影像建筑物提取方法[J]. 测绘通报, 2023, 0(2): 134-138.
[6]	王本礼, 王也, 唐先龙, 董胜光. 遥感影像变化图斑智能化提取平台研发与应用[J]. 测绘通报, 2023, 0(2): 150-154.
[7]	向煜, 黄志, 华媛媛, 邓剑峰. 深度学习支持下的宅基地复垦项目真实性智能审查技术研究与应用[J]. 测绘通报, 2023, 0(1): 163-167.
[8]	吴真真, 唐超, 杨晓飞. 基于深度学习的视频识别及动态监测技术应用[J]. 测绘通报, 2022, 0(9): 23-28.
[9]	田有良, 樊廷立, 唐超. 面向地铁隧道表面渗漏水的快速检测技术[J]. 测绘通报, 2022, 0(9): 29-33.
[10]	钱建国, 张宇琦, 汤圣君, 王伟玺, 李晓明. 最小割与深度学习联合优化的室内粘连点云分割方法[J]. 测绘通报, 2022, 0(9): 45-51.
[11]	李睿, 周晓光, 侯东阳. 基于正态分布的三维建筑物变化检测高度差阈值确定方法[J]. 测绘通报, 2022, 0(9): 98-104.
[12]	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.
[13]	黄宇鸿, 周维勋. 高分辨率遥感影像场景变化检测的相似度方法[J]. 测绘通报, 2022, 0(8): 48-53.
[14]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[15]	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.