Synthetic aperture radar (SAR) and optical images provide highly complementary ground information. The fusion of SAR and optical data can significantly enhance semantic segmentation inference results. However, the fusion methods for multimodal data remains a challenge for current research due to significant disparities in imaging mechanisms from diverse sources. Our goal was to bridge the significant gaps between optical and SAR images by developing a dual-input model that utilizes image-level fusion. To improve most existing state-of-the-art image fusion methods, which often assign equal weights to multiple modalities, we employed the principal component analysis (PCA) transform approach. Subsequently, we performed feature-level fusion on shallow feature maps, which retain rich geometric information. We also incorporated a channel attention module to highlight channels rich in features and suppress irrelevant information. This step is crucial due to the substantial similarity between SAR and optical images in shallow layers such as geometric features. In summary, we propose a generic multimodal fusion strategy that can be attached to most encoding–decoding structures for feature classification tasks, designed with two inputs. One input is the optical image, and the other is the three-band fusion data obtained by combining the PCA component of the optical image with the SAR. Our feature-level fusion method effectively integrates multimodal data. The efficiency of our approach was validated using various public datasets, and the results showed significant improvements when applied to several land cover classification models.

Deep learning, which is a dominating technique in artificial intelligence, has completely changed image understanding over the past decade. As a consequence, the sea ice extraction (SIE) problem has reached a new era. We present a comprehensive review of four important aspects of SIE, including algorithms, datasets, applications and future trends. Our review focuses on research published from 2016 to the present, with a specific focus on deep-learning-based approaches in the last five years. We divided all related algorithms into three categories, including the conventional image classification approach, the machine learning-based approach and deep-learning-based methods. We reviewed the accessible ice datasets including SAR-based datasets, the optical-based datasets and others. The applications are presented in four aspects including climate research, navigation, geographic information systems (GIS) production and others. This paper also provides insightful observations and inspiring future research directions.

Accurate building geometry information is crucial for urban planning in constrained spaces, fueling the growing demand for large-scale, high-precision 3D city modeling. Traditional methods like oblique photogrammetry and LiDAR prove time consuming and expensive for low-cost 3D reconstruction of expansive urban scenes. Addressing this challenge, our study proposes a novel approach to leveraging single-view remote sensing images. By integrating shadow information with deep learning networks, our method measures building height and employs a semantic segmentation technique for single-image high-rise building reconstruction. In addition, we have designed complex shadow measurement algorithms and building contour correction algorithms to improve the accuracy of building models in conjunction with our previous research. We evaluate the method’s precision, time efficiency, and applicability across various data sources, scenarios, and scales. The results demonstrate the rapid and accurate acquisition of 3D building data with maintained geometric accuracy (mean error below 5 m). This approach offers an economical and effective solution for large-scale urban modeling, bridging the gap in cost-efficient 3D reconstruction techniques.

Laser altimetry data from the Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) contain a lot of noise, which necessitates the requirement for a signal photon extraction method. In this study, we propose a density clustering method, which combines slope and elevation information from optical stereo images and adaptively adjusts the neighborhood search direction in the along-track direction. The local classification density threshold was calculated adaptively according to the uneven spatial distribution of noise and signal density, and reliable surface signal points were extracted. The performance of the algorithm was validated for strong and weak beam laser altimetry data using optical stereo images with different resolutions and positioning accuracies. The results were compared qualitatively and quantitatively with those obtained using the ATL08 algorithm. The signal extraction quality was better than that of the ATL08 algorithm for steep slope and low signal-to-noise ratio (SNR) regions. The proposed method can better balance the relationship between recall and precision, and its F₁-score was higher than that of the ATL08 algorithm. The method can accurately extract continuous and reliable surface signals for both strong and weak beams among different terrains and land cover types.

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.

For addressing the technical challenges of photon denoising and water level extraction in ICESat-2 satellite-based water monitoring applications, this paper proposes an innovative solution integrating Gaussian function fitting with Hough transform. The method first employs histogram Gaussian fitting to achieve coarse denoising of water body regions. Subsequently, a probability attenuation model based on elevation differences between adjacent photons is constructed to accomplish refined denoising through iterative optimization of adaptive thresholds. Building upon this foundation, the Hough transform technique from image processing is introduced into photon cloud processing, enabling robust water level extraction from ICESat-2 data. Through rasterization, discrete photon distributions are converted into image space, where straight lines conforming to the photon distribution are then mapped as intersection points of sinusoidal curves in Hough space. Leveraging the noise-resistant characteristics of the Hough space accumulator, the interference from residual noise photons is effectively eliminated, thereby achieving high-precision water level line extraction. Experiments were conducted across five typical water bodies (Qinghai Lake, Long Land, Ganquan Island, Qilian Yu Islands, and Miyun Reservoir). The results demonstrate that the proposed denoising method outperforms DBSCAN and OPTICS algorithms in terms of accuracy, precision, recall, F1-score, and computational efficiency. In water level estimation, the absolute error of the Hough transform-based line detection method remains below 2 cm, significantly surpassing the performance of mean value, median value, and RANSAC algorithms. This study provides a novel technical framework for effective global water level monitoring.