Road-network extraction from very high-resolution (VHR) remote-sensing imagery remains a challenging task owing to the structural sparsity, topological complexity, and severe occlusions of road networks. Conventional graph-based approaches preserve topological consistency yet incur considerable computational overhead, whereas prevailing convolutional neural network (CNN) and Transformer architectures struggle to reconcile long-range contextual modeling with computational efficiency. To address these limitations, this study proposes RFM-UNet, a hybrid frequency and state–space network designed for road-network segmentation. Specifically, the encoder integrates Mamba blocks with an Anisotropic Directional Attention (ADA) module to jointly capture local geometric cues and global dependencies at linear computational complexity. In addition, a Multi-Scale Adaptive Fusion Module (MAFM) is introduced to dynamically recalibrate multi-stage features, thereby suppressing cross-scale interference and preserving the connectivity of narrow roads. To enhance robustness against shadow-induced occlusions, a Dual-Spectrum Aggregation Module (DualSpec) decouples the phase and amplitude spectra in the frequency domain and fuses them with spatial features, effectively mitigating spurious responses and background noise characterized by similar textures. Quantitative and qualitative experiments on three public datasets demonstrate that RFM-UNet consistently outperforms current state-of-the-art methods.
Pu Song, Peng Yu, Xiaojing Zhong et al.· Remote Sensing· 0 citations
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
