DeepUNet: A Deep Fully Convolutional Network for Pixel-Level Sea-Land Segmentation

By Ruirui Li, Wenjie Liu, Lei Yang, Shihao Sun, Wei Hu, Fan Zhang. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017

334 citations recorded by the source corpus.

Semantic segmentation is a fundamental research in optical remote sensing image processing. Because of the complex maritime environment, the sea-land segmentation is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there were a few of works using CNN for sea-land segmentation and the results could be further improved. This paper proposes a novel deep convolution neural network named DeepUNet. Like the U-Net, its structure has a contracting path and an expansive path to get high-resolution optical output. But differently, the DeepUNet uses DownBlocks instead of convolution layers in the contracting path and uses UpBlock in the expansive path. The two novel blocks bring two new connections that are U-connection and Plus connection. They are promoted to get more precise segmentation results. To verify the network architecture, we construct a new challenging sea-land dataset and compare the DeepUNet on it with the U-Net, SegNet, and SeNet. Experimental results show that DeepUNet can improve 1–2% accuracy performance compared with other architectures, especially in high-resolution optical remote sensing imagery.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Oceanography

View Paper: https://www.semanticscholar.org/paper/57f9ca8e8d396e62ac5f0c869afaf32e1d812685

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

A cloud detection algorithm for satellite imagery based on deep learning (2019, methodology): “Deep learning has been used for various remote sensing tasks, such as road detection (Zhang et al., 2018), sea-land detection (Li et al., 2018a), and land cover mapping (Karakizi et al., 2018).”
Recurrent residual U-Net for medical image segmentation (2019, methodology): “However, U-Net is not only limited to applications in the domain of medical imaging, but nowadays this model is also applied for computer vision tasks.(31,32) Meanwhile, different variants of U-Net models have been proposed, including a very simple variant of U-Net for CNN-based segmentation of medi”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, methodology): “Hence, pixel-level spatial accuracy, especially at the boundary of different objects, is the utmost goal for semantic segmentation of remote sensing imagery (Liu et al., 2018; Marmanis et al., 2018).”
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation (2018, methodology): “However, U-Net is not only limited to the applications in the domain of medical imaging, nowadays this model is massively applied for computer vision tasks as well [30, 31].”
Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey (2020, methodology): “DeepUNet [100], a ResNet based FCN, used to segment sea land.”