2026· IEEE Geoscience and Remote Sensing Letters· Vol 23, pp. 2506105-2506105· 0 citations· 23 references
Abstract
Semantic segmentation of remote sensing imagery has been widely applied in landslide identification, effectively addressing the time-consuming and labor-intensive nature of manual visual interpretation. However, existing models still face challenges in extracting multiscale features and accurately delineating boundaries under complex background conditions. To overcome these limitations, this study proposes a multiscale boundary aware network (MBANet) for landslide identification in remote sensing imagery. Specifically, we design a multiscale cross-interaction convolution (MCC) module that captures local details and broader contextual cues through heterogeneous receptive-field branches, and recalibrates the concatenated multiscale features via an adaptive cross-branch interaction strategy. In addition, a boundary sensitive refinement attention (BSRA) module is introduced to enhance boundary localization by combining a Sobel-based gradient prior, learnable boundary estimation, and region-context enhancement for fine-grained boundary refinement. These modules are integrated into an encoder–decoder architecture to jointly achieve semantic consistency and boundary precision. Experimental results on two public datasets show that MBANet outperforms other comparison models in overall segmentation performance and maintains competitive performance in boundary delineation. On the Bijie dataset, it achieves a recall of 83.84% and an $F1$ -score of 85.39%; on the Palu dataset, it reaches a recall of 75.83% and an $F1$ -score of 78.17%, highlighting its superior performance.
Sea–land segmentation (SLS) in optical remote sensing imagery is a fundamental task that faces significant challenges due to the complex morphology of coastlines. Shaped by diverse natural factors and anthropogenic infrastructure, coastal environments exhibit substantial spatial–temporal variability and boundary ambiguity. Existing convolutional neural networks (CNN)-based and vision Transformers-based methods often suffer from high computational costs and insufficient exploitation of frequency-domain cues, which are critical for boundary characterization. To address these issues, we propose CoastMamba, a novel SLS framework. Specifically, to mitigate background interference and structural ambiguity, a grouped coordinate Mamba (GCMamba) block is designed to generate adaptive gating masks for effective feature recalibration and selective boundary emphasis. Moreover, to handle weak contrast and blurred boundaries, a Frequency-Domain Boundary-Enhanced Module is introduced to jointly leverage spatial and frequency representations, enhancing feature discrimination. Furthermore, to preserve fine-grained local details alongside global semantics, a multilevel feature aggregation pyramid (MFAP) decoder is employed to integrate hierarchical features. Finally, to address the limitations of existing SLS datasets regarding low spatial resolution and limited scene coverage, we construct the high-resolution fine-grained Minnan Sea–Land Segmentation dataset. Extensive experiments on this dataset and public benchmarks demonstrate that CoastMamba achieves a boundary intersection over union (IoU) of 60.06%, an IoU of 96.84%, and an F1-score of 98.39%, significantly outperforming state-of-the-art methods.
Peng Yu, Pu Song, Xiaojing Zhong et al.· IEEE Journal of Selected Top...· 0 citations
The semantic interpretation of remote sensing imagery through segmentation has become indispensable for a wide range of applications, including resource exploration, environmental assessment, and land-use analysis. Yet, accurate parsing of such images remains challenging because complex object boundaries and large scale differences often weaken the ability of conventional Convolutional Neural Network (CNN)-based methods to preserve local details. In response, this study constructs a segmentation framework that couples wavelet convolution with the Mamba architecture. To strengthen feature learning in the intermediate stages, an Auxiliary Segmentation Module (ASM) is employed to provide additional supervisory guidance, which supports optimization and encourages the representation of subtle semantic details. Wavelet-transform convolution is also introduced into the downsampling path, enabling spatial cues and frequency-related information to be exploited in a more coordinated manner for finer boundary and texture modeling. Experiments on public remote sensing datasets and mining area imagery further confirm the effectiveness of the method. Compared with several existing segmentation approaches, the proposed model delivers better overall performance in mIoU, F1-score, and recognition accuracy, particularly in scenes where multiple land-cover categories are heavily interlaced. Moreover, these gains are obtained with relatively low model complexity, suggesting good potential for practical deployment in land monitoring and ecological management.
Wenxi He, Zongmin Yin, Yulong Yang et al.· Remote Sensing· 0 citations
A Mahalanobis-Angle Boundary Loss (MABL) is proposed that explicitly enhances boundary and shape consistency and is introduced, built upon MABL, a boundary- aware remote sensing segmentation framework with Struc- tural Penalties.
Yuexi Song, Kailai Sun, Zhuoyue Wang et al.· 0 citations
Timely and reliable mapping of landslide-affected areas from high-spatial-resolution optical imagery is essential for disaster investigation and post-event assessment. However, this task remains challenging because landslides usually exhibit large-scale variations, irregular boundaries, and strong spectral–textural similarities with surrounding bare-surface objects, which often cause missed detections, false positives, incomplete delineation, and inaccurate boundary localization. To address these problems, this paper presents a Scale-View Interactive Attention Network, named SIA-Net, for RGB-based landslide segmentation. First, a Multi-Scale Attention Module (MSAM) is constructed to encourage information exchange among features with different spatial resolutions. By doing so, the network can better represent both small scattered landslide patches and large continuous landslide bodies. Second, a Multi-View Attention Module (MVAM) is introduced to aggregate contextual cues from multiple receptive field views. This design strengthens the model’s ability to distinguish landslides from visually confusing objects, including bare soil, roads, riverbanks, and terrain shadows. In addition, a Convolutional Block Attention Module (CBAM) is incorporated during feature reconstruction to enhance landslide-related channel and spatial responses, thereby improving segmentation completeness and boundary localization. Experiments on the CAS Landslide Dataset (CLD) and GVLM Dataset show that SIA-Net provides more accurate landslide masks than the compared segmentation networks under the adopted benchmark settings. These results indicate that integrating scale-level interaction, view-level contextual modeling, and attention-guided decoding can effectively improve landslide extraction in complex optical remote sensing scenes.
The linear computational complexity embraced by Mamba has demonstrated significant application potential in context modeling for the landslide segmentation tasks from remote sensing images. However, existing methods show deficiencies in terms of discrimination and generalization when applied to extreme remote sensing landslide scenarios, such as low resolution and abnormal lighting. To confront these challenges, we propose a remote sensing image landslide segmentation network (VFM-MoME) jointly guided by a vision foundation model and a mixture of Mamba experts. Specifically, we first design a dual-branch joint encoding architecture that integrates a frequency-aware wavelet block as the main encoding branch with the visual foundation model fusion as the auxiliary branch, thereby mitigating the issue of insufficient generalized features in specific landslide study areas. We also construct a mixture of Mamba expert block to enable the decoder to process both global context and local fine-grained features of landslides, addressing the shortcoming of simple serial Mamba in capturing local details and balancing between global semantic relationships and the edges and textural details of objects. Furthermore, we bring in a binary uncertainty enhancement module to guide the model in exploring challenging samples, thus enhancing the model’s ability to handle ambiguous features. Test results on the publicly available datasets of Landslide4Sense and GVLM demonstrate that our method achieves competitive performance.
Jun Liu, Chengqiang Zhao, Yuanzhen Ju et al.· Remote Sensing· 0 citations
Building extraction from high-resolution remote sensing imagery is critical for urban planning and smart city development, yet it faces challenges such as blurred boundaries, missing fine details, and severe background interference. To address these issues, this study proposes an improved model named GSU-HRNet, which integrates attention mechanisms and boundary refinement strategies on the basis of UHRNet's high-resolution parallel backbone. An enhanced Pyramid Squeeze-and-Excitation (PSE) module is embedded in the lateral feature transmission paths of each hierarchical stage, capturing multi-scale contextual information via adaptive average pooling of multiple sizes to strengthen semantic responses for buildings and suppress background noise. A Gated Bottleneck Convolution (GBC) module is further introduced in the feature fusion stage, adopting a dual-branch structure with gating mechanisms and residual connections to selectively regulate fused features, alleviate redundant feature accumulation, and improve the stability of feature representation. Experiments were conducted on the aerial imagery subset of the WHU Building Dataset (covering 450 km2 in Christchurch with 8,189 512×512 image tiles), which was split into training, validation and test sets at a ratio of 6:1:3. Ablation experiments verify the effectiveness and complementarity of PSE and GBC modules, with the combined model achieving optimal performance. Quantitative comparisons show that GSU-HRNet outperforms classical models like U-Net and PSPNet, reaching an IoU of 89.93% and an F1-score of 94.50%. Qualitative analysis demonstrates that the proposed model yields clearer building boundaries, more complete structural preservation, and reduced false detections and omissions, even in challenging scenarios with complex building structures and shadow interference. The results confirm that GS-UHRNet effectively enhances feature representation and boundary delineation accuracy, and exhibits strong generalization ability across different building extraction datasets, providing a robust solution for automated building extraction from hig-hresolution remote sensing imagery.
Shi He, Shiye Zhang, Xiujuan Liang et al.· GEOINFORMATICS· 0 citations