Land-Unet: A deep learning network for precise segmentation and identification of non-structured land use types in rural areas for green urban space analysis

被引：0

作者：

Zhao, Yan ^{[1
,3
]}

Xie, Junru ^{[2
]}

Zhu, Huiru ^{[1
]}

Luo, Taige ^{[2
]}

Xiong, Yao ^{[4
]}

Fan, Chenyang ^{[2
]}

Xia, Haoxiang ^{[5
]}

Chen, Yuheng ^{[6
]}

Zhang, Fuquan ^{[2
]}

机构：

[1] Jiangsu Open Univ, Coll Rural Revitalizat, Nanjing 210036, Peoples R China

[2] Nanjing Forestry Univ, Coll Informat Sci & Technol & Artificial Intellige, Nanjing 210037, Peoples R China

[3] Nanjing Forestry Univ, Coll Landscape Architecture, Nanjing 210037, Peoples R China

[4] Nanjing Forestry Univ, Coll Art & Design, Nanjing 210037, Peoples R China

[5] Univ Illinois, Sch Liberal Art & Sci, Champaign, IL 61820 USA

[6] Univ Calif Davis, Sch Liberal Art & Sci, Davis, CA 95616 USA

来源：

ECOLOGICAL INFORMATICS | 2025年 / 87卷

关键词：

Green ecology; Vegetation mapping; Artificial intelligence; Rural planning; Spatial analysis; GIS; Land-form; U-NET; COVER;

D O I：

10.1016/j.ecoinf.2025.103078

中图分类号：

Q14 [生态学（生物生态学）];

学科分类号：

071012 ; 0713 ;

摘要：

Land Use and Land Cover Change (LUCC) have become popular research topics in the environmental field. With the development of artificial intelligence technology, many downstream applications based on intelligent urban-rural semantic analysis have emerged. Scholars have made significant progress in the intelligent analysis of urban imagery, but exploration of unstructured rural remote sensing data has been limited. This paper addresses the existing pixel-level semantic ambiguity issues and proposes a new deep learning model, Land-Unet. The network features a dual-branch Edge-Sensing Block (ESB) structure, including a Spatial and Channel Synergistic Attention (SCSA) branch and a Dynamic Upsampling (DYU) technique, which effectively resolves contour ambiguity in edge semantic information in rural images. Experiments on multiple datasets using various deep learning methods show that compared with the original structure, the proposed method increases mloU by 9.7%, mDice by 5.9%, and mAcc by 12.2%. Compared to transformer-based methods, proposed method also demonstrated improved performance. Additionally, anew rural satellite imagery dataset, RuralUse, has been open-sourced for semantic segmentation research.

引用

页数：18

共 85 条

[1] Aliabad F.A., Malamiri H.R.G., Shojaei S., Sarsangi A., Ferreira C.S.S., Kalantari Z., Investigating the ability to identify new constructions in urban areas using images from unmanned aerial vehicles, Google earth, and sentinel-2, Remote Sens., 14, 13, (2022)
[2] Aljebreen M., Mengash H.A., Alamgeer M., Alotaibi S.S., Salama A.S., Hamza M.A., Land use and land cover classification using river formation dynamics algorithm with deep learning on remote sensing images, IEEE Access, 12, pp. 11147-11156, (2024)
[3] Arulananth T.S., Kuppusamy P.G., Ayyasamy R.K., Alhashmi S.M., Mahalakshmi M., Vasanth K., Chinnasamy P., Semantic segmentation of urban environments: Leveraging U-net deep learning model for cityscape image analysis, PloS One, 19, 4, (2024)
[4] Azad R., Aghdam E.K., Rauland A., Jia Y., Avval A.H., Bozorgpour A., Karimijafarbigloo S., Cohen J.P., Adeli E., Merhof D., Medical image segmentation review: The success of U-Net, IEEE Trans. Pattern Anal. Mach. Intell., 46, 12, pp. 10076-10095, (2024)
[5] Bhatti U.A., Yu Z., Yuan L., Zeeshan Z., Nawaz S.A., Bhatti M., Mehmood A., Ul Ain Q., Wen L., Geometric algebra applications in geospatial artificial intelligence and remote sensing image processing, IEEE Access, 8, pp. 155783-155796, (2020)
[6] Chasia S., Herrnegger M., Juma B., Kimuyu J., Sitoki L., Olang L., Analysis of land-cover changes in the Transboundary Sio-Malaba-Malakisi River Basin of East Africa: Towards identifying potential land-use transition regimes, Afr. Geograph. Rev., 42, 2, pp. 170-186, (2023)
[7] Chen Y., Li R., Tu Y., Lu X., Chen G., Comprehensive representations of subpixel land use and cover shares by fusing multiple geospatial datasets and statistical data with machine-learning methods, Land, 13, 11, (2024)
[8] Chen C., Yuan X., Gan S., Kang X., Luo W., Li R., Bi R., Gao S., A new strategy based on multi-source remote sensing data for improving the accuracy of land use/cover change classification, Sci. Rep., 14, 1, (2024)
[9] Chen L.-C., Zhu Y., Papandreou G., Schroff F., Adam H., Encoder-decoder with atrous separable convolution for semantic image segmentation, Computer Vision – ECCV 2018, pp. 833-851, (2018)
[10] Cheng G., Han J., Guo L., Liu Z., Bu S., Ren J., Effective and efficient midlevel visual elements-oriented land-use classification using VHR remote sensing images, IEEE Trans. Geosci. Remote Sens., 53, 8, pp. 4238-4249, (2015)

← 1 2 3 4 5 6 7 8 9 →