基于多层特征信息融合的滑坡图像分割模型

doi:10.11947/j.AGCS.2024.20230587

测绘学报 ›› 2024, Vol. 53 ›› Issue (11): 2201-2212.doi: 10.11947/j.AGCS.2024.20230587

• 摄影测量学与遥感 • 上一篇

基于多层特征信息融合的滑坡图像分割模型

张银胜¹^,²^,³(), 陈戈², 段修贤¹, 童俊毅², 单梦姣², 单慧琳¹^,²^,³()

^1.无锡学院江苏省集成电路可靠性技术及检测系统工程研究中心，江苏　无锡　214105
^2.南京信息工程大学电子与信息工程学院，江苏　南京　210044
^3.南京信息工程大学复杂环境智能保障技术教育部重点实验室，江苏　南京　210044

收稿日期:2023-12-22 发布日期:2024-12-13
通讯作者: 单慧琳 E-mail:yorkzhang@nuist.edu.cn;shanhuilin@nuist.edu.cn
作者简介:第一张银胜（1975—），男，博士，教授，研究方向为智能图像处理与目标检测。　E-mail：yorkzhang@nuist.edu.cn
基金资助:
国家自然科学基金(62071240);无锡市科技发展资金“太湖之光”科技攻关（基础研究）项目(K20231004)

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

Yinsheng ZHANG¹^,²^,³(), Ge CHEN², Xiuxian DUAN¹, Junyi TONG², Mengjiao SHAN², Huilin SHAN¹^,²^,³()

^1.Jiangsu Integrated Circuit Reliability Technology and Testing System Engineering Research Center, Wuxi University, Wuxi 214105, China
^2.School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
^3.Key Laboratory of Intelligent Support Technology for Complex Environment in Nanjing University of Information Science and Techno-logy, Ministry of Education, Nanjing 210044, China

Received:2023-12-22 Published:2024-12-13
Contact: Huilin SHAN E-mail:yorkzhang@nuist.edu.cn;shanhuilin@nuist.edu.cn
About author:ZHANG Yinsheng (1975—), male, PhD, professor, majors in intelligent image processing and object detection.　E-mail: yorkzhang@nuist.edu.cn
Supported by:
The National Natural Science Foundation of China(62071240);Wuxi City Science and Technology Development Fund “Taihu Light” Science and Technology Key Project (Basic Research)(K20231004)

摘要/Abstract

摘要：

滑坡对人类生存环境造成严重的危害，人工识别滑坡区域的方式比较耗时且隐蔽区域不易被探测，而利用遥感图像识别滑坡区域，能够准确快速地实现滑坡灾害预警和救援。随着深度学习的快速发展，语义分割已经广泛应用于滑坡遥感图像识别领域。针对当前滑坡图像分割模型容易出现错误识别、图像边缘信息丢失等问题，本文提出了一种多层特征信息融合的滑坡分割模型MLFIF-Net，该模型以MobileNetv3-Small为主干网络，提高模型对滑坡图像的特征提取能力，同时构建级联带状空间金字塔池化模块增强滑坡图像的纹理特征，获取多尺度信息，利用高效通道注意力模块关注图像特征，设计了多层特征信息融合结构增强图像的边缘信息，从而提升模型的分割效果。试验结果表明，本文模型在贵州毕节市滑坡数据集上的准确率为96.77%，类别平均准确率为95.61%，平均交并比达到了87.69%，与SegNet等6种分割模型相比，其分割精度较为优异，能够准确识别目标区域，突出滑坡图像边缘细节。

关键词: 语义分割, 遥感图像, 滑坡, 金字塔池化, 注意力模块, 特征信息融合

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

中图分类号:

P237

张银胜, 陈戈, 段修贤, 童俊毅, 单梦姣, 单慧琳. 基于多层特征信息融合的滑坡图像分割模型[J]. 测绘学报, 2024, 53(11): 2201-2212.

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.

图/表 18

图1

图2

表1

图3

图4

图5

图6

图7

表2

表3

图8

表4

图9

表5

图10

表6

表7

图11

参考文献 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

基于多层特征信息融合的滑坡图像分割模型

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

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

主干网络	推理时间/ms	帧率	参数量
Vgg16	13.52	71.24	29.3×10⁶
Xception	35.38	28.25	55.7×10⁶
MobileNetv3-Small	12.34	80.97	6.1×10⁶

模型	主干网络	PA	MPA	MIoU
Seg Net	—	93.14	89.43	80.85
PSP-Net	Res Net50	94.41	92.84	81.64
E-Deep Lab V3+^[28]	Efficient Net	96.54	95.42	87.25
DA-Net^[27]	ResNet50	96.26	95.35	86.80
DFPENet^[29]	ResNet101	96.15	95.08	86.96
HADeen Net^[30]	Res Net50	95.85	94.78	86.41
MLFIF-Net	MobileNetv3-Small	96.77	95.61	87.69

[1]	胡波, 陈翰新, 任松, 屈英豪, 刘清屹, 涂歆玥, 王大涛. 一种基于分割掩码的隧道裂缝病害自动识别后处理算法[J]. 测绘学报, 2024, 53(9): 1715-1724.
[2]	徐涛, 杨元维, 高贤君, 王志威, 潘越, 李少华, 许磊, 王艳军, 刘波, 余静, 吴凤敏, 孙浩宇. 融合图卷积与多尺度特征的接触网点云语义分割[J]. 测绘学报, 2024, 53(8): 1624-1633.
[3]	王威, 郑薇, 王新. 面向遥感图像场景分类的LAG-MANet模型[J]. 测绘学报, 2024, 53(7): 1371-1383.
[4]	刘雅婷, 陈传法. 顾及空间异质性和特征优选的滑坡易发性评价方法[J]. 测绘学报, 2024, 53(7): 1417-1428.
[5]	蒋亚楠, 郑林枫, 许强, 汤明高, 朱星. 机理引导下的阶跃型滑坡位移预测深度学习模型[J]. 测绘学报, 2024, 53(6): 1128-1139.
[6]	许豪, 张勤, 王利, 舒宝, 杜源, 黄观文. 无人机抛投式GNSS滑坡监测设备智能化部署选址方法[J]. 测绘学报, 2024, 53(6): 1140-1153.
[7]	袁维, 籍晓蕾, 王东坡, 管凯歌, 裴子豪, 钟辉亚, 唐佳, 孙瑞峰, 王伟, 郑贺民, 郭帅杰, 李红旭. 降雨和库水位变动联合作用下滑坡位移加权反分析及监测预警方法[J]. 测绘学报, 2024, 53(5): 917-932.
[8]	曹帆之, 石添鑫, 韩开杨, 汪璞, 安玮. 多模态遥感图像模板匹配Log-Gabor滤波方法[J]. 测绘学报, 2024, 53(3): 526-536.
[9]	林云浩, 王艳军, 李少春, 蔡恒藩. 一种耦合DeepLab与Transformer的农作物种植类型遥感精细分类方法[J]. 测绘学报, 2024, 53(2): 353-366.
[10]	陈帅, 苗则朗, 吴立新. 顾及坡体赋存环境的概率地震滑坡危险性制图[J]. 测绘学报, 2023, 52(9): 1548-1561.
[11]	连仁包, 张振敏, 廖一鹏, 邹长忠, 黄立勤. 结合测地距离场与曲线平滑的遥感图像道路中心线快速提取[J]. 测绘学报, 2023, 52(8): 1317-1329.
[12]	胡功明, 杨春成, 徐立, 尚海滨, 王泽凡, 秦志龙. 改进U-Net的遥感图像语义分割方法[J]. 测绘学报, 2023, 52(6): 980-989.
[13]	刘帅, 李笑迎, 于梦, 邢光龙. 高分辨率遥感图像双解耦语义分割网络模型[J]. 测绘学报, 2023, 52(4): 638-647.
[14]	沈秭扬, 倪欢, 管海燕. 遥感图像跨域语义分割的无监督域自适应对齐方法[J]. 测绘学报, 2023, 52(12): 2115-2126.
[15]	王威, 邓纪伟, 王新, 李智勇, 袁平. 面向遥感图像场景分类的GLFFNet模型[J]. 测绘学报, 2023, 52(10): 1693-1702.