Landslide image segmentation model based on multi-layer feature information fusion

doi:10.11947/j.AGCS.2024.20230587

Abstract

Abstract:

Landslide cause serious harm to human living environment. The method of manually identifying the landslides is time-consuming and the hidden area is not easy to detect. The use of remote sensing image to identify the landslides can accurately and quickly realize the landslide disaster warning and rescue. With the rapid development of deep learning, semantic segmentation has been widely used in the field of landslide remote sensing image recognition. Aiming at the problems such as error recognition and image edge information loss in the current landslide image segmentation model, this paper proposes a landslide segmentation model MLFIF-Net, which integrates multi-layer feature information fusion. The model uses MobileNetv3-Small as the main trunk network to improve the feature extraction ability of the model. At the same time, a cascade spatial pyramid pool module is constructed to enhance the texture features of landslide images and obtain multi-scale information. An efficient channel attention module is used to focus on image features, and a multi-layer feature information fusion structure is designed to enhance the edge information of images, so as to improve the segmentation effect of the model. The experimental results show that the accuracy of the proposed model on the landslide data set of Bijie city, Guizhou province is 96.77%, the average accuracy of the class is 95.61%, and the average interaction ratio is 87.69%. Compared with SegNet and other six segmentation models, its segmentation accuracy is better, and it can accurately identify the target area and highlight the edge details of the landslide image.

Key words: semantic segmentation, remote sensing image, landslide, pyramid pooling, attention module, feature information fusion

CLC Number:

P237

Yinsheng ZHANG, Ge CHEN, Xiuxian DUAN, Junyi TONG, Mengjiao SHAN, Huilin SHAN. Landslide image segmentation model based on multi-layer feature information fusion[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(11): 2201-2212.

Figures/Tables 18

Fig.1

Fig.2

Tab.1

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Tab.2

Tab.3

Fig.8

Tab.4

Fig.9

Tab.5

Fig.10

Tab.6

Tab.7

Fig.11

References 31

[1]	王岩. 滑坡地质灾害勘查与防治治理研究[J]. 中国高新科技, 2023(14): 92-93.
	WANG Yan. Research on exploration, prevention and treatment of landslide geological disaster[J]. China High-Tech, 2023(14): 92-93.
[2]	许强. 对地质灾害隐患早期识别相关问题的认识与思考[J]. 武汉大学学报(信息科学版), 2020, 45(11): 1651-1659.
	XU Qiang. Understanding and consideration of related issues in early identification of potential geohazards[J]. Geomatics and Information Science of Wuhan University, 2020, 45(11): 1651-1659.
[3]	马博, 朱杰勇, 刘帅, 等. 联合时序InSAR和滑坡灾害易发性的元阳县滑坡灾害隐患识别[J]. 地质灾害与环境保护, 2023, 34(3): 8-14.
	MA Bo, ZHU Jieyong, LIU Shuai, et al. Hidden landslide disaster identification in Yuanyang county with combined time-series InSAR and landslide disasters susceptibility[J]. Journal of Geological Hazards and Environment Preservation, 2023, 34(3): 8-14.
[4]	LIU Guang, ZBIGNIEW P, STEFANO S, et al. Land surface displacement geohazards monitoring using multi-temporal InSAR techniques[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(1): 77-87.
[5]	张勤, 白正伟, 黄观文, 等. GNSS滑坡监测预警技术进展[J]. 测绘学报, 2022, 51(10): 1985-2000.DOI:. doi: 10.11947/j.AGCS.2022.20220299
	ZHANG Qin, BAI Zhengwei, HUANG Guanwen, et al. Review of GNSS landslide monitoring and early warning[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10): 1985-2000. DOI:. doi: 10.11947/j.AGCS.2022.20220299
[6]	黄海峰, 薛蓉花, 赵蓓蓓, 等. 孕灾机理与综合遥感结合的三峡库首顺层岩质滑坡隐患识别[J]. 测绘学报，2022, 51(10): 2056-2068. DOI:. doi: 10.11947/j.AGCS.2022.20220306
	HUANG Haifeng, XUE Ronghua, ZHAO Beibei, et al. The bedding rock landslide identification in the head area of the Three Gorges Reservoir combined with disaster pregnant mechanism and comprehensive remote sensing method[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10): 2056-2068. DOI:. doi: 10.11947/j.AGCS.2022.20220306
[7]	ZHANG Ruixuan, ZHU Wu, LI Zhenhong, et al. Re-Net: multibranch network with structural reparameterization for landslide detection in optical imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 2828-2837.
[8]	PRAKASH N, MANCONI A, LOEW S. Mapping landslides on EO data: performance of deep learning modelsvs. traditional machine learning models[J]. Remote Sensing, 2020, 12(3): 346.
[9]	LIU Xinran, PENG Yuexing, LU Zili, et al. Feature-fusion segmentation network for landslide detection using high-resolution remote sensing images and digital elevation model data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:4500314.
[10]	BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[11]	ZHAO Hengshuang, SHI Jianping, QI Xiaojuan, et al. Pyramid scene parsing network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6230-6239.
[12]	CHEN L C, ZHU Yukun, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of 2018 European Conference on Computer Vision. Cham: Springer, 2018: 833-851.
[13]	GARCIA G P B, SOARES L P, ESPADOTO M, et al. Relict landslide detection using deep-learning architectures for image segmentation in rainforest areas: a new framework[J]. International Journal of Remote Sensing, 2023, 44(7): 2168-2195.
[14]	ULLO S, MOHAN A, SEBASTIANELLI A, et al. A new mask R-CNN-based method for improved landslide detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 3799-3810.
[15]	LIU Peng, WEI Yongming, WANG Qinjun, et al. Research on post-earthquake landslide extraction algorithm based on improved U-Net model[J]. Remote Sensing, 2020, 12(5): 894.
[16]	ZHOU Yongxiu, WANG Honghui, YANG Ronghao, et al. A novel weakly supervised remote sensing landslide semantic segmentation method: combining CAM and cycleGAN algorithms[J]. Remote Sensing, 2022, 14(15): 3650.
[17]	ZHENG Xiangxiang, HAN Lingyi, HE Guojin, et al. Semantic segmentation model for wide-area coseismic landslide extraction based on embedded multichannel spectral-topographic feature fusion: a case study of the Jiuzhaigou Ms7.0 earthquake in Sichuan, China[J]. Remote Sensing, 2023, 15(4): 1084.
[18]	HOWARD A, SANDLER M, CHEN Bo, et al. Searching for MobileNetV3[C]//Proceedings of 2019 IEEE/CVF International Confe-rence on Computer Vision. Seoul: IEEE, 2019: 1314-1324.
[19]	SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[20]	HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[21]	HOU Qibin, ZHANG Li, CHENG Mingming, et al. Strip pooling: rethinking spatial pooling for scene parsing[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 4002-4011.
[22]	WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11531-11539.
[23]	YANG Shuang, WANG Yuzhu, WANG Panzhe, et al. Automatic identification of landslides based on deep learning[J]. Applied Sciences, 2022, 12(16): 8153.
[24]	CHANDRA N, SAWANT S, VAIDYA H. An efficient U-Net model for improved landslide detection from satellite images[J]. PFG—Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2023, 91(1): 13-28.
[25]	JI Shunping, YU Dawen, SHEN Chaoyong, et al. Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks[J]. Landslides, 2020, 17(6): 1337-1352.
[26]	HOU Qibin, ZHOU Daquan, FENG Jiashi. Coordinate attention for efficient mobile network design[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13713-13722.
[27]	ZHANG Hu, ZU Keke, LU Jian, et al. EPSANet: an efficient pyramid squeeze attention block on convolutional neural network[C]//Proceedings of 2003 Asian Conference on Computer Vision. Cham: Springer, 2023: 541-557.
[28]	CHEN Rongjun, YAN Xuanhui, WANG Shiping, et al. DA-Net: dual-attention network for multivariate time series classification[J]. Information Sciences, 2022, 610: 472-487.
[29]	GAO Ouyang, NIU Chaoyang, LIU Wei, et al. E-DeepLabV3+: a landslide detection method for remote sensing images[C]//Procee-dings of the 10th Joint International Information Technology and Artificial Intelligence Conference. Chongqing: IEEE, 2022: 573-577.
[30]	XU Qingsong, OUYANG Chaojun, JIANG Tianhai, et al. DFPENet-geology: a deep learning framework for high precision recognition and segmentation of co-seismic landslides[EB/OL]. [2023-12-01].https://arxiv.org/abs/1908.10907v3.
[31]	YU Bo, XU Chong, CHEN Fang, et al. HADeenNet: a hierarchical-attention multi-scale deconvolution network for landslide detection[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 111: 102853.

输入尺寸	参数	输出尺寸
224×224×3	Conv，3×3	112×112×16
112×112×16	Bottleneck，3×3	56×56×16
56×56×16	Bottleneck，3×3	28×28×24
28×28×24	Bottleneck，3×3	28×28×24
28×28×24	Bottleneck，5×5	14×14×40
14×14×40	Bottleneck，5×5	14×14×40
14×14×40	Bottleneck，5×5	14×14×40
14×14×40	Bottleneck，5×5	14×14×48
14×14×48	Bottleneck，5×5	14×14×48
14×14×48	Bottleneck，5×5	7×7×96
7×7×96	Bottleneck，5×5	7×7×96
7×7×96	Bottleneck，5×5	7×7×96
7×7×96	Conv，1×1	7×7×576
7×7×576	Pool，7×7	1×1×576
1×1×576	Conv，1×1	1×1×576

配置名称	参数
CPU	Intel（R）Core（TM）i9-12900KF
GPU	NVIDIA GeForce RTX3090
操作系统	Windows10
框架	Pytorch1.12
编程语言	Python

注意力模块	PA	MPA	MIoU
CA	96.25	95.08	87.05
SE	96.58	95.42	87.28
PSA	96.05	95.27	86.72
ECA	96.77	95.61	87.69

试验	模块	膨胀率	MIoU/（%）
1	ASPP	（6，12，18）	86.62
2	ASPP	（3，6，9）	86.72
3	SASPP	（6，12，18）	86.79
4	SASPP	（5，9，13）	86.84
5	SASPP	（3，6，9）	86.94
6	CSASPP	（6，12，18）	87.35
7	CSASPP	（5，9，13）	87.42
8	CSASPP	（3，6，9）	87.69

试验	模型	MIoU/（%）
1	Baseline	86.15
2	Baseline+CSASPP	86.75
3	Baseline+CSASPP+ECA	87.21
4	Baseline+CSASPP+ECA+MLFIFS	87.69