Improved Sea Ice Image Segmentation Using U2-Net and Dataset Augmentation

Abstract

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Traditional image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning-based semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and severe weather conditions affect image quality, which affects the accuracy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multiscale inflation convolution and a multilayer convolutional block attention module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insufficient number of training samples to a certain extent and improved the accuracy of image segmentation; (2) this study designed a multilevel Gaussian noise data augmentation scheme to improve the network’s ability to resist noise interference and achieve a more accurate segmentation of images with different degrees of noise pollution; (3) the inclusion of a multiscale inflation perceptron and multilayer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

A Method for Extracting Photovoltaic Panels from High-Resolution Optical Remote Sensing Images Guided by Prior Knowledge

“…However, it may introduce redundant and ineffective semantic information. Additionally, the structure built upon RSU is quite flexible and can be trained from scratch without the need for a pretrained backbone; it has minimal performance loss [32]. Ge et al [33] proposed an extraction method for large-scale PV power plants.…”

“…CBAM combines the Channel Attention Module (CAM) and Spatial Attention Module (SAM) in a cascaded manner. As for CAM, Global Average Pooling (GAP) and Global Max Pooling (GMP) are firstly used to compress the spatial dimensions of the input features and condense spatial information [32]. Then, the correlation between channels is modeled through a Multilayer Perceptron (MLP) and the Sigmoid activation function.…”

“…Li et al [32] constructed the SC-U 2 -Net network for sea ice segmentation. They added a multilayer CBAM into multiple locations of the network in order to extract more useful spatial and channel information, pay more attention to local features, and improve the generalization performance.…”

Combined Data Augmentation on EANN to Identify Indoor Anomalous Sound Event

“…Although deep learning has demonstrated its significant practical utility in various fields such as image processing, medical diagnosis, and speech recognition [16][17][18], the performance of deep learning models always relies heavily on data-driven conditions. In real-world applications, the inherent scarcity of abnormal sound data makes it difficult to meet this condition.…”

Automatic Extraction of the Calving Front of Pine Island Glacier Based on Neural Network

“…Moreover, the model maintains high resolution as it becomes deeper while minimizing video memory overhead and computational requirements. Comparative experiments with multiple network models have demonstrated that U 2 -Net enhances accuracy, making it a suitable choice for extracting the features of the calving front[40,56].2.3.2. U -Net Architecture and Post-Processing U 2 -Net, a target detection model based on the traditional U-Net, is utilized in this study.…”