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

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...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2023-09, Vol.15 (18), p.4488
Main Authors: Lin, Na, Quan, Hailin, He, Jing, Li, Shuangtao, Xiao, Maochi, Wang, Bin, Chen, Tao, Dai, Xiaoai, Pan, Jianping, Li, Nanjie
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
Classification
Deep learning
dense connection
Gaofen-1 imagery
Image resolution
Methods
Motor task performance
Neural networks
Remote sensing
SD-UNet
Semantics
separable convolution
Suburban areas
urban vegetation extraction
Vegetation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15184488