Building change detection method combining object feature guidance and multiple attention mechanism

doi:10.11947/j.AGCS.2024.20230436

Abstract

Abstract:

High-resolution remote sensing images have rich detail features, and building changes are of variable types with large scale differences. Aiming at the problem that building changes are prone to voids and omissions in complex environments, a building change detection method combining object feature guidance and multiple attention mechanism is proposed to realize fine change information extraction from high-resolution images by enhancing category information through building target-level guidance. The method consists of a building significant enhancement module and a target-guided multi-attention module, which extracts the key areas of the building through global deep feature perception and fusion, combines the target-level feature guidance and multiple self-attention to strengthen the feature expression, enhances the contextual feature correlation, effectively reduces the loss of detailed features, and solves the problem of loss of details caused by the target voids and unclear edges. It is shown through two sets of experiments that this method can improve the accuracy, effectively reduce the change loss in scenes with more kinds of changes, and improve the stability of the algorithm.

Key words: high-resolution remote sensing images, building change detection, object feature, deep learning, attention mechanism

CLC Number:

P237

Shaopeng DING, Xiushan LU, Rufei LIU, Yi YANG, Haiyan GU, Haitao LI. Building change detection method combining object feature guidance and multiple attention mechanism[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1224-1235.

Figures/Tables 15

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Tab.1

Tab.2

Tab.3

Fig.9

Fig.10

Fig.11

Fig.12

References 33

[1]	张继贤, 李海涛, 顾海燕, 等. 人机协同的自然资源要素智能提取方法[J]. 测绘学报, 2021, 50(8):1023-1032. DOI:10.11947/j.AGCS.2021.20210102.
	ZHANG Jixian, LI Haitao, GU Haiyan, et al. Study on man-machine collaborative intelligent extraction for natural resource features[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):1023-1032. DOI:10.11947/j.AGCS.2021.20210102.
[2]	陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
	CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping: fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
[3]	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.
[4]	叶沅鑫, 孙苗苗, 周亮, 等. 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.DOI:10.11947/j.AGCS.2023.20210350.
	YE Yuanxin, SUN Miaomiao, ZHOU Liang, et al. Main body, edge decomposition and reorganization network for building change detection[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(1):71-81.DOI:10.11947/j.AGCS.2023.20210350.
[5]	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.
[6]	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[7]	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: IEEE, 2016: 770-778.
[8]	ZHOU Lichen, ZHANG Chuang, WU Ming. D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City: IEEE, 2018: 182-186.
[9]	SUN Ke, XIAO Bin, LIU Dong, et al. Deep high-resolution representation learning for human pose estimation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5686-5696.
[10]	ZUO Zongcheng, ZHANG Wen, ZHANG Dongying. A remote sensing image semantic segmentation method by combining deformable convolution with conditional random fields[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3):39-49.
[11]	CAYE DAUDT R, LE SAUX B, BOULCH A. Fully convolutional Siamese networks for change detection[C]//Proceedings of 2018 IEEE International Conference on Image Processing. Athens: IEEE, 2018: 4063-4067.
[12]	WANG Moyang, TAN Kun, JIA Xiuping, et al. A deep Siamese network with hybrid convolutional feature extraction module for change detection based on multi-sensor remote sensing images[J]. Remote Sensing, 2020, 12(2):205.
[13]	HE Hao, WANG Shuyang, WANG Shicheng, et al. A road extraction method for remote sensing image based on encoder-decoder network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2):16-25.
[14]	王超, 王帅, 陈晓, 等. 联合UNet++和多级差分模块的多源光学遥感影像对象级变化检测[J]. 测绘学报, 2023, 52(2):283-296.DOI:10.11947/j.AGCS.2023.20220202.
	WANG Chao, WANG Shuai, CHEN Xiao, et al. Object-level change detection of multi-sensor optical remote sensing images combined with UNet++ and multi-level difference module[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(2):283-296. DOI:10.11947/j.AGCS.2023.20220202.
[15]	ZHENG Zhi, WAN Yi, ZHANG Yongjun, et al. CLNet: cross-layer convolutional neural network for change detection in optical remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 175:247-267.
[16]	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.
[17]	PENG Xueli, ZHONG Ruofei, LI Zhen, et al. Optical remote sensing image change detection based on attention mechanism and image difference[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9):7296-7307.
[18]	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.
[19]	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.
[20]	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.
[21]	贾立新, 胡奕标, 金燕, 等. 融合多种注意力机制的结直肠息肉分割神经网络[J]. 计算机辅助设计与图形学学报, 2023, 35(3):138-148.
	JIA Lixin, HU Yibiao, JIN Yan, et al. Polyp segmentation network combined with multi-attention mechanism[J]. Journal of Computer-Aided Design & Computer Graphics, 2023, 35(3):138-148.
[22]	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.
[23]	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.
[24]	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.
[25]	FANG Sheng, LI Kaiyu, SHAO Jinyuan, et al. SNUNet-CD: a densely connected Siamese network for change detection of VHR images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5.
[26]	PENG Daifeng, ZHAI Chenchen, ZHANG Yongjun, et al. High-resolution optical remote sensing image change detection based on dense connection and attention feature fusion network[J]. The Photogrammetric Record, 2023, 38(184):498-519.
[27]	ZHANG Ruiqian, ZHANG Hanchao, NING Xiaogang, et al. Global-aware Siamese network for change detection on remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 199:61-72.
[28]	BANDARA W G C, PATEL V M. A transformer-based Siamese network for change detection[C]//Proceedings of 2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur: IEEE, 2022: 207-210.
[29]	SONG Zixuan, LI Xiongfei, ZHU Rui, et al. ERMF: edge refinement multi-feature for change detection in bitemporal remote sensing images[J]. Signal Processing: Image Communication, 2023, 116:116964.
[30]	ZHANG Hongyan, LIN Manhui, YANG Guangyi, et al. ESCNet: an end-to-end superpixel-enhanced change detection network for very-high-resolution remote sensing images[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(1):28-42.
[31]	CHEN Chen, LI Zhilin, LI Songnian, et al. From digitalized to intelligentized surveying and mapping: fundamental is-sues and research agenda[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2):148-160.
[32]	JI Shunping, WEI Shiqing, LU Meng. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1):574-586.
[33]	陈军, 艾廷华, 闫利, 等. 智能化测绘的混合计算范式与方法研究[J/OL]. 测绘学报: 1-19 [2024-05-18]. http://kns.cnki.net/kcms/detail/11.2089.P.20240415.1049.002.html.
	CHEN Jun, AI Tinghua, YAN Li, et al. Hybrid computational paradigm and methods for intelligentized surveying and mapping[J/OL]. Acta Geodaetica et Cartographica Sinica: 1-19 [2024-05-18]. http://kns.cnki.net/kcms/detail/11.2089.P.20240415.1049.002.html.

方法	P	R	F₁值	IoU	OA
FC-EF	78.23	82.28	80.20	66.95	97.93
FC-Siam-diff	88.73	85.90	87.29	77.45	98.73
FC-Siam-conc	86.43	85.93	86.18	75.72	98.60
STANet	91.38	85.01	88.08	78.69	98.74
BiT	89.56	90.33	89.94	81.72	98.98
ChangeFormer	88.62	91.78	90.17	82.10	99.02
SNAFF	91.94	89.65	90.78	83.11	99.07
GASNet	90.51	91.61	91.05	83.58	99.08
本文方法	91.82	91.34	91.58	84.47	99.14

方法	P	R	F₁值	IoU	OA
FC-EF	65.59	79.44	71.85	56.07	97.81
FC-Siam-diff	87.18	58.53	70.04	53.89	96.82
FC-Siam-conc	50.93	88.17	64.56	47.67	95.88
STANet	93.03	83.49	88.00	78.58	99.03
BiT	88.47	83.68	86.01	75.45	98.77
ChangeFormer	85.32	89.73	87.47	77.73	98.96
SNAFF	92.76	89.65	91.18	83.79	99.26
GASNet	92.83	90.33	91.56	84.44	99.29
本文方法	92.04	91.38	91.71	84.69	99.30

数据集	方法	P	R	F₁值	IoU	OA
LEVIR-CD	Baseline	88.04	89.90	88.96	80.11	98.86
	Baseline+BISEM	91.42	89.22	90.31	82.33	99.02
	Baseline+FGMAM	90.61	90.33	90.47	82.60	99.03
	本文方法	91.82	91.34	91.58	84.47	99.14
WHU-CD	Baseline	87.63	87.99	87.81	78.27	98.96
	Baseline+BISEM	91.61	88.13	89.83	81.55	99.15
	Baseline+FGMAM	87.47	91.89	89.63	81.21	99.09
	本文方法	92.04	91.38	91.71	84.69	99.30