Next Article in Journal
Estimating Vertical Distribution of Leaf Water Content within Wheat Canopies after Head Emergence
Next Article in Special Issue
Exploring Fuzzy Local Spatial Information Algorithms for Remote Sensing Image Classification
Previous Article in Journal
Application of Optical Flow Technique and Photogrammetry for Rockfall Dynamics: A Case Study on a Field Test
Previous Article in Special Issue
Multispectral Image Change Detection Based on Single-Band Slow Feature Analysis
Article

HA-Net: A Lake Water Body Extraction Network Based on Hybrid-Scale Attention and Transfer Learning

1
School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
2
National Glaciology Geocryology Desert Data Center, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, China
*
Author to whom correspondence should be addressed.
Academic Editor: Pavel Kishcha
Remote Sens. 2021, 13(20), 4121; https://doi.org/10.3390/rs13204121
Received: 11 August 2021 / Revised: 27 September 2021 / Accepted: 10 October 2021 / Published: 14 October 2021
(This article belongs to the Special Issue Advances in Optical Remote Sensing Image Processing and Applications)
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. View Full-Text
Keywords: deep convolutional neural network; remote sensing image; semantic segmentation; tibetan plateau; transfer learning; attention mechanism deep convolutional neural network; remote sensing image; semantic segmentation; tibetan plateau; transfer learning; attention mechanism
Show Figures

Graphical abstract

MDPI and ACS Style

Wang, Z.; Gao, X.; Zhang, Y. HA-Net: A Lake Water Body Extraction Network Based on Hybrid-Scale Attention and Transfer Learning. Remote Sens. 2021, 13, 4121. https://doi.org/10.3390/rs13204121

AMA Style

Wang Z, Gao X, Zhang Y. HA-Net: A Lake Water Body Extraction Network Based on Hybrid-Scale Attention and Transfer Learning. Remote Sensing. 2021; 13(20):4121. https://doi.org/10.3390/rs13204121

Chicago/Turabian Style

Wang, Zhaobin, Xiong Gao, and Yaonan Zhang. 2021. "HA-Net: A Lake Water Body Extraction Network Based on Hybrid-Scale Attention and Transfer Learning" Remote Sensing 13, no. 20: 4121. https://doi.org/10.3390/rs13204121

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop