Swin-UperNet: A Semantic Segmentation Model for Mangroves and Spartina alterniflora Loisel Based on UperNet

Abstract

As an ecosystem in transition from land to sea, mangroves play a vital role in wind and wave protection and biodiversity maintenance. However, the invasion of Spartina alterniflora Loisel seriously damages the mangrove wetland ecosystem. To protect mangroves scientifically and dynamically, a semantic segmentation model for mangroves and Spartina alterniflora Loise was proposed based on UperNet (Swin-UperNet). In the proposed Swin-UperNet model, a data concatenation module was proposed to make full use of the multispectral information of remote sensing images, the backbone network was replaced with a Swin transformer to improve the feature extraction capability, and a boundary optimization module was designed to optimize the rough segmentation results. Additionally, a linear combination of cross-entropy loss and Lovasz-Softmax loss was taken as the loss function of Swin-UperNet, which could address the problem of unbalanced sample distribution. Taking GF-1 and GF-6 images as the experiment data, the performance of the Swin-UperNet model was compared against that of other segmentation models in terms of pixel accuracy (PA), mean intersection over union (mIoU), and frames per second (FPS), including PSPNet, PSANet, DeepLabv3, DANet, FCN, OCRNet, and DeepLabv3+. The results showed that the Swin-UperNet model achieved the best PA of 98.87% and mIoU of 90.0%, and the efficiency of the Swin-UperNet model was higher than that of most models. In conclusion, Swin-UperNet is an efficient and accurate model for mangrove and Spartina alterniflora Loise segmentation synchronously, which will provide a scientific basis for Spartina alterniflora Loise monitoring and mangrove resource conservation and management.

Feature optimization combined with UPerNet-Twins model for eucalyptus extraction from Sentinel-2A image

“…In addition to feature selection, the extraction model is another key factor affecting remote sensing image classification and information extraction. In recent years, UPerNet [9] and Twins [10] models have been proposed in deep learning models. This paper combines the advantages of the UPerNet, and Twins models, recombines the UPerNet-Twins model, and considers the importance of feature construction to the performance of the model.…”

Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence

“…Paired with machine learning automation, studies of long time-series of images can be carried out. Recent improvements in satellite image resolutions (i.e., 0.031 m for the World-View 3 satellite) have allowed for more resolved classification of trees using semantic segmentation neural networks [23,24], detection of individual trees using instance segmentation networks [25][26][27][28] and detection of mangrove forest clearings [29] on highresolution RGB images. Nonetheless, the calculation of certain variables, such as the height of trees extracted from canopy height models (CHMs) is error-prone at the current resolution of satellite imagery and should be paired with low-flying platforms, such as planes or UASs [28] for better validation and performance.…”