Next Article in Journal
Updating of the Archival Large-Scale Soil Map Based on the Multitemporal Spectral Characteristics of the Bare Soil Surface Landsat Scenes
Next Article in Special Issue
Recurrent Residual Deformable Conv Unit and Multi-Head with Channel Self-Attention Based on U-Net for Building Extraction from Remote Sensing Images
Previous Article in Journal
Historical Attributions and Future Projections of Gross Primary Productivity in the Yangtze River Basin under Climate Change Based on a Novel Coupled LUE-RE Model
Previous Article in Special Issue
C-RISE: A Post-Hoc Interpretation Method of Black-Box Models for SAR ATR
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Urban Vegetation Extraction from High-Resolution Remote Sensing Imagery on SD-UNet and Vegetation Spectral Features

1
School of Smart City, Chongqing Jiaotong University, Chongqing 400074, China
2
Chongqing Liangping District Planning and Natural Resources Bureau, Chongqing 405200, China
3
Chongqing Geomatics and Remote Sensing Center, Chongqing 401125, China
4
School of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China
5
College of Earth Science, Chengdu University of Technology, Chengdu 610059, China
6
School of Management, Chongqing University of Technology, Chongqing 400054, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2023, 15(18), 4488; https://doi.org/10.3390/rs15184488
Submission received: 27 July 2023 / Revised: 7 September 2023 / Accepted: 9 September 2023 / Published: 12 September 2023

Abstract

Urban vegetation plays a crucial role in the urban ecological system. Efficient and accurate extraction of urban vegetation information has been a pressing task. Although the development of deep learning brings great advantages for vegetation extraction, there are still problems, such as ultra-fine vegetation omissions, heavy computational burden, and unstable model performance. Therefore, a Separable Dense U-Net (SD-UNet) was proposed by introducing dense connections, separable convolutions, batch normalization layers, and Tanh activation function into U-Net. Furthermore, the Fake sample set (NIR-RG), NDVI sample set (NDVI-RG), and True sample set (RGB) were established to train SD-UNet. The obtained models were validated and applied to four scenes (high-density buildings area, cloud and misty conditions area, park, and suburb) and two administrative divisions. The experimental results show that the Fake sample set can effectively improve the model’s vegetation extraction accuracy. The SD-UNet achieves the highest accuracy compared to other methods (U-Net, SegNet, NDVI, RF) on the Fake sample set, whose ACC, IOU, and Recall reached 0.9581, 0.8977, and 0.9577, respectively. It can be concluded that the SD-UNet trained on the Fake sample set not only is beneficial for vegetation extraction but also has better generalization ability and transferability.
Keywords: Gaofen-1 imagery; deep learning; dense connection; separable convolution; SD-UNet; urban vegetation extraction; NIR Gaofen-1 imagery; deep learning; dense connection; separable convolution; SD-UNet; urban vegetation extraction; NIR

Share and Cite

MDPI and ACS Style

Lin, N.; Quan, H.; He, J.; Li, S.; Xiao, M.; Wang, B.; Chen, T.; Dai, X.; Pan, J.; Li, N. Urban Vegetation Extraction from High-Resolution Remote Sensing Imagery on SD-UNet and Vegetation Spectral Features. Remote Sens. 2023, 15, 4488. https://doi.org/10.3390/rs15184488

AMA Style

Lin N, Quan H, He J, Li S, Xiao M, Wang B, Chen T, Dai X, Pan J, Li N. Urban Vegetation Extraction from High-Resolution Remote Sensing Imagery on SD-UNet and Vegetation Spectral Features. Remote Sensing. 2023; 15(18):4488. https://doi.org/10.3390/rs15184488

Chicago/Turabian Style

Lin, Na, Hailin Quan, Jing He, Shuangtao Li, Maochi Xiao, Bin Wang, Tao Chen, Xiaoai Dai, Jianping Pan, and Nanjie Li. 2023. "Urban Vegetation Extraction from High-Resolution Remote Sensing Imagery on SD-UNet and Vegetation Spectral Features" Remote Sensing 15, no. 18: 4488. https://doi.org/10.3390/rs15184488

APA Style

Lin, N., Quan, H., He, J., Li, S., Xiao, M., Wang, B., Chen, T., Dai, X., Pan, J., & Li, N. (2023). Urban Vegetation Extraction from High-Resolution Remote Sensing Imagery on SD-UNet and Vegetation Spectral Features. Remote Sensing, 15(18), 4488. https://doi.org/10.3390/rs15184488

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop