A boundary guidance and cross-scale information interaction network for water body extraction from remote sensing images
CHEN Jiaxue(), XIAO Dongsheng1,2(), CHEN Hongyu3
1. School of Civil Engineering and Geomatics, Southwest Petroleum University, Chengdu 610500, China 2. Disaster Prevention and Emergency Research Center of Geographic and Remote Sensing Geographic Information, Southwest Petroleum University, Chengdu 610500, China 3. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China
Extracting accurate water body information holds great significance for water resources protection and urban planning. However, due to numerous surface features and complex environments, along with different morphologies, scales, and spectral characteristics of different water bodies, remote sensing images inevitably exhibit heterogeneity, spectral similarities, and inter-class similarities between water bodies and other surface features. Existing methods fail to fully exploit boundary cues, the semantic correlation between different layers, and multi-scale representations, rendering the accurate information extraction of water bodies from remote sensing images still challenging. This study proposed a boundary guidance and cross-scale information interaction network (BGCIINet) for information extraction of water bodies from remote sensing images. First, this study proposed a boundary guidance (BG) module for the first time by combing the Sobel operator. This module can be used to effectively capture boundary cues in low-level features and efficiently embed these cues into a decoder to produce rich boundary information. Second, a cross-scale information interaction (CII) module was introduced to enhance the multi-scale representation capability of the network and facilitate information exchange between layers. Extensive experiments on two datasets demonstrate that the proposed method outperforms four state-of-the-art methods, offering rich boundary details and completeness under challenging scenarios. Therefore, the proposed method is more effective in extracting water body information from remote sensing images. This study will provide a valuable reference of methods for future research.
Jiaxue CHEN,Dongsheng XIAO,Hongyu CHEN. A boundary guidance and cross-scale information interaction network for water body extraction from remote sensing images[J]. Remote Sensing for Natural Resources,
2025, 37(1): 15-23.
Tab.1 Details of DeepGlobe dataset and LandCover dataset
Tab.2 Some samples of the dataset
Fig.4 Visual feature maps before and after BG module
Fig.5 Visual feature maps before and after the CII module
方法
IoU
F1
Precision
Recall
OA
Attention Unet
82.62
90.48
92.78
88.30
96.62
PSPNet
88.66
93.99
94.77
93.23
97.83
DANet
81.52
89.82
90.38
89.27
96.32
DeepLabV3+
93.59
96.69
97.00
96.37
98.80
本文方法
94.67
97.26
97.76
96.77
99.01
Tab.3 Quantitative comparison on the DeepGlobe dataset (%)
方法
IoU
F1
Precision
Recall
OA
Attention Unet
86.13
92.55
94.88
90.33
95.94
PSPNet
92.18
95.93
96.25
95.62
97.74
DANet
84.60
91.66
92.64
90.70
95.39
DeepLabV3+
91.99
95.83
94.63
97.06
97.64
本文方法
95.41
97.65
97.30
98.01
98.68
Tab.4 Quantitative comparison on the LandCover dataset (%)
场景类型
影像
Attention Unet
PSPNet
DANet
DeepLabV3+
本文方法
低对比度、光谱相似
不规则水体
小型水体
类间相似性
类内异质性
Tab.5 Visualization results in different challenging scenarios
方法
参数量/106
浮点运 算数/109
模型大 小/MB
FPS/ (帧·)
Attention Unet
34.88
266.27
133.11
35.09
PSPNet
25.35
20.09
97.91
189.22
DANet
66.55
282.83
262.11
76.70
DeepLabV3+
22.34
31.55
85.28
182.54
本文方法
21.95
48.45
83.82
114.49
Tab.6 Comparison of efficiency and complexity
方法
IoU/%
F1/%
OA/%
参数 量/106
浮点运 算数/109
基线网络
90.51
95.02
98.18
21.66
31.22
去除BG模块
92.78
96.25
98.64
21.76
47.21
去除CII模块
92.83
96.28
98.65
21.85
32.47
本文方法
94.67
97.26
99.01
21.95
48.45
Tab.7 Ablation experiment results
Fig.6 Visual analysis of module functions
[1]
Wu Z, Lai X, Li K. Water quality assessment of rivers in Lake Chaohu basin (China) using water quality index[J]. Ecological Indicators, 2021,121:107021.
Yang C, Tong L, Ma N J, et al. Distribution characteristics and influencing factors of antibiotics in water and sediments of Honghu Lake[J]. Safety and Environmental Engineering, 2022, 29(5):78-90.
[3]
Verma U, Chauhan A, M M M P, et al. DeepRivWidth:Deep learning based semantic segmentation approach for river identification and width measurement in SAR images of Coastal Karnataka[J]. Computers & Geosciences, 2021,154:104805.
Du Y Y, Zhou C H. Automatically extracting remote sensing information for water body[J]. Journal of Remote Sensing, 1998, 2(4):264-269.
[5]
Koponen S, Pulliainen J, Kallio K, et al. Lake water quality classification with airborne hyperspectral spectrometer and simulated MERIS data[J]. Remote Sensing of Environment, 2002, 79(1):51-59.
[6]
McFeeters S K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.
[7]
Xie C, Huang X, Zeng W, et al. A novel water index for urban high-resolution eight-band WorldView-2 imagery[J]. International Journal of Digital Earth, 2016, 9(10):925-941.
[8]
Liu Q, Huang C, Shi Z, et al. Probabilistic river water mapping from landsat-8 using the support vector machine method[J]. Remote Sensing, 2020, 12(9):1374.
[9]
Wang X, Ling F, Yao H, et al. Unsupervised sub-pixel water body mapping with sentinel-3 OLCI image[J]. Remote Sensing, 2019, 11(3):327.
[10]
Weng L, Xu Y, Xia M, et al. Water areas segmentation from remote sensing images using a separable residual SegNet network[J]. ISPRS International Journal of Geo-Information, 2020, 9(4):256.
[11]
Guo H, He G, Jiang W, et al. A multi-scale water extraction convolutional neural network (MWEN) method for GaoFen-1 remote sensing images[J].ISPRS International Journal of Geo-Information, 2020, 9(4):189.
[12]
Li M, Wu P, Wang B, et al. A deep learning method of water body extraction from high resolution remote sensing images with multisensors[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021,14:3120-3132.
[13]
Dong S, Pang L, Zhuang Y, et al. Optical remote sensing water-land segmentation representation based on proposed SNS-CNN network[C]// IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium.July 28 - August 2, 2019, Yokohama,Japan.IEEE,2019:3895-3898.
[14]
Hu K, Li M, Xia M, et al. Multi-scale feature aggregation network for water area segmentation[J]. Remote Sensing, 2022, 14(1):206.
[15]
Kang J, Guan H, Peng D, et al. Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images[J]. International Journal of Applied Earth Observation and Geoinformation, 2021,103:102499.
[16]
Wang Z, Gao X, Zhang Y. HA-net:A lake water body extraction network based on hybrid-scale attention and transfer learning[J]. Remote Sensing, 2021, 13(20):4121.
Zhang Q G, Zhang X J, Yu H K, et al. A water extraction method for remote sensing with lightweight network model[J]. Science of Surveying and Mapping, 2022, 47(11):64-72.
[18]
Zhang Z, Lu M, Ji S, et al. Rich CNN features for water-body segmentation from very high resolution aerial and satellite imagery[J]. Remote Sensing, 2021, 13(10):1912.
Shen J A, Ma M T, Song Z Y, et al. Water information extraction from high-resolution remote sensing images using the deep-learning based semantic segmentation model[J]. Remote Sensing for Natural Resources, 2022, 34(4):129-135.doi:10.6046/zrzyyg.2021357.
Lin N, Wang Y Y, Guo J, et al. A method of water extraction from remote sensing images based on SegNet_CRF[J]. Geomatics & Spatial Information Technology, 2023, 46(3):12-15,18.
Li H L, Sui B K, Ye Y P, et al. Water information extraction from GF-7 satellite data based on semantic segmentation network[J]. Dam & Safety, 2022(4):50-58.
Liu J D, Song W D, Zhu H B, et al. Research on water extraction from remote sensing images based on improved U-Net model[J]. Science of Surveying and Mapping, 2022, 47(8):230-239.
[23]
Wang B, Chen Z, Wu L, et al. SADA-net:A shape feature optimization and multiscale context information-based water body extraction method for high-resolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022,15:1744-1759.
[24]
Boguszewski A, Batorski D, Ziemba-Jankowska N, et al. LandCover.ai:Dataset for automatic mapping of buildings,woodlands,water and roads from aerial imagery[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) June 19-25,2021, Nashville,TN,USA.IEEE,2021:1102-1110.
[25]
Demir I, Koperski K, Lindenbaum D, et al.DeepGlobe 2018:A challenge to parse the earth through satellite images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). June 18-22,2018, Salt Lake City,UT,USA.IEEE,2018:172-17209.
[26]
Oktay O, Schlemper J, Le Folgoc L, et al. Attention U-net:Learning where to look for the pancreas[EB/OL]. 2018:1804.03999.https://arxiv.org/abs/1804.03999v3.
url: https://arxiv.org/abs/1804.03999v3
[27]
Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 21-26,2017, Honolulu,HI,USA.IEEE,2017:6230-6239.
[28]
Fu J, Liu J, Tian H, et al. Dual attention network for scene segmentation//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 15-20,2019, Long Beach,CA,USA.IEEE,2019:3141-3149.
[29]
Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[M]// Lecture Notes in Computer Science. Cham: Springer International Publishing,2018:833-851.