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

TL;DR

DeepUNet is a novel deep convolutional neural network designed for pixel-level sea-land segmentation in remote sensing images, featuring unique blocks and connections that improve segmentation accuracy in complex maritime environments.

Contribution

The paper introduces DeepUNet, a new CNN architecture with novel blocks and connections tailored for sea-land segmentation, outperforming existing models.

Findings

DeepUNet outperforms SegNet and U-Net on a new challenging sea-land dataset.

DeepUNet achieves higher accuracy in high-resolution remote sensing imagery.

The novel blocks and connections enhance segmentation precision.

Abstract

Semantic segmentation is a fundamental research in 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 are 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 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 our network architecture, we made a new challenging sea-land dataset and compare the DeepUNet on it with the SegNet and the U-Net. Experimental results show that DeepUNet achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.