Abstract
Due to the large quantity of noise and complex spatial background of the remote sensing images, how to improve the accuracy of semantic segmentation has become a hot topic. Lake water body extraction is crucial for disaster detection, resource utilization, and carbon cycle, etc. The the area of lakes on the Tibetan Plateau has been constantly changing due to the movement of the Earth’s crust. Most of the convolutional neural networks used for remote sensing images are based on single-layer features for pixel classification while ignoring the correlation of such features in different layers. In this paper, the two-branch encoder is presented, which is a multiscale structure that combines the features of ResNet-34 with a feature pyramid network. Secondly, adaptive weights are distributed to global information using the hybrid-scale attention block. Finally, PixelShuffle is used to recover the feature maps’ resolution, and the densely connected block is used to refine the boundary of the lake water body. Likewise, we transfer the best weights which are saved on the Google dataset to the Landsat-8 dataset to ensure that our proposed method is robust. We validate the superiority of Hybrid-scale Attention Network (HA-Net) on two given datasets, which were created by us using Google and Landsat-8 remote sensing images. (1) On the Google dataset, HA-Net achieves the best performance of all five evaluation metrics with a Mean Intersection over Union (MIoU) of 97.38%, which improves by 1.04% compared with DeepLab V3+, and reduces the training time by about 100 s per epoch. Moreover, the overall accuracy (OA), Recall, True Water Rate (TWR), and False Water Rate (FWR) of HA-Net are 98.88%, 98.03%, 98.24%, and 1.76% respectively. (2) On the Landsat-8 dataset, HA-Net achieves the best overall accuracy and the True Water Rate (TWR) improvement of 2.93% compared to Pre_PSPNet, which proves to be more robust than other advanced models.
Highlights
The Tibetan Plateau is the security barrier of the Asian ecosystem and is wellknown as the world’s third pole [1] and Asia’s water tower [2]
A large number of remote sensing image analyses are based on the Landsat8 remote sensing satellite. Since both the Landsat-8 dataset and the Google dataset consist of RGB images, we can transfer the optimal parameters saved on the Google dataset directly to the Landsat-8 dataset, which validates the robustness of Hybrid-scale Attention Network (HA-Net) and demonstrates that it can be used as a foundation for other lake water body extraction researches
MSLWENet, Pre_DeepLab V3+, and MWFE may lose a large amount of information due to the presence of dilated convolutions in the atrous spatial pyramid pooling (ASPP)
Summary
The Tibetan Plateau is the security barrier of the Asian ecosystem and is wellknown as the world’s third pole [1] and Asia’s water tower [2]. There are numerous lakes on the Tibetan Plateau, which differ greatly in size and account for the majority of the lake area in China [3]. It has been shown that global warming accelerates glacial melt [5] and permafrost degradation [6], with most of the lakes expanding in the last 30 years. It can be confirmed that the lake area of the Tibetan. Plateau expands at a pace of 0.83%/year due to increased glacial runoff [7]. The overflow of the salt lakes causes pollution of the land and freshwater lakes, which damages the ecological environment, and disturbs the life of the residents
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
