Landslide trails are important elements of landslide inventory maps, providing valuable information for landslide risk and hazard assessment. Compared with traditional manual mapping, skeletonization methods offer a more cost-efficient way to map landslide trails, by automatically generating centerlines from landslide polygons. However, a challenge to existing skeletonization methods is that expert knowledge and manual intervention are required to obtain a branchless skeleton, which limits the applicability of these methods. To address this problem, a new workflow for landslide trail extraction (LTE) is proposed in this study. To avoid generating redundant branches and to improve the degree of automation, two endpoints, i.e., the crown point and the toe point, of the trail were determined first, with reference to the digital elevation model. Thus, a fire extinguishing model (FEM) is proposed to generate skeletons without redundant branches. Finally, the effectiveness of the proposed method is verified, by extracting landslide trails from landslide polygons of various shapes and sizes, in two study areas. Experimental results show that, compared with the traditional grassfire model-based skeletonization method, the proposed FEM is capable of obtaining landslide trails without spurious branches. More importantly, compared with the baseline method in our previous work, the proposed LTE workflow can avoid problems including incompleteness, low centrality, and direction errors. This method requires no parameter tuning and yields excellent performance, and is thus highly valuable for practical landslide mapping.
Superpoint Transformers use superpoints as the basic processing units, thereby significantly reducing the number of tokens processed by Transformers. However, they have been seldom employed in point cloud roof plane instance segmentation, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To address this challenge, we establish a set of criteria that high-quality superpoints for Transformers should satisfy and introduce a corresponding two-stage superpoint generation process. The superpoints generated by our method not only have accurate boundaries, but also exhibit consistent geometric sizes and shapes, which greatly benefit the feature learning of superpoint Transformers. To compensate for the limitations of deep learning features when the training set size is limited, we incorporate multidimensional handcrafted features into the model. Additionally, we design a decoder that combines a Kolmogorov–Arnold Network with a Transformer module to improve instance prediction and mask extraction. Finally, our network’s predictions are refined using traditional algorithm-based post-processing. For evaluation, we annotated a real-world dataset and corrected annotation errors in the existing RoofN3D dataset. Experimental results show that our method achieves state-of-the-art performance on our dataset, as well as both the original and corrected RoofN3D datasets. Our model also shows significant advantages over existing methods when handling data with low point density, large density variations, or low 3D point precision. Moreover, it is not sensitive to plane boundary annotations during training, significantly reducing the annotation burden. We will release our code, trained models, and datasets.
Timely and accurate monitoring of surface water dynamics via remote sensing is critical, given water resources’ importance. However, accurate water body delineation based on high-resolution remotely sensed imagery is still challenging due to the complexity of water bodies’ boundaries and the diversity of their shapes and sizes, which can lead to boundary ambiguity and varying degrees of confusion with near-water vegetation in water body maps. To address this challenge, we introduce an uncertainty-aware hybrid CNN–Transformer model for delineating water bodies using remotely sensed imagery. In our designed network, a multi-scale transformer (MST) module is first designed to effectively model and refine the multi-scale global semantic dependencies of water bodies. Subsequently, an uncertainty-guided multi-scale information fusion (MSIF) module is constructed to extract water body mapping information from these multi-scale features output from the MST module and fuse them adaptively. Across different scales, the extracted features differ in their ability to distinguish water bodies from non-water bodies and in their levels of uncertainty. Consequently, during the adaptive fusion of multi-scale water body information in the MSIF module, the mapping uncertainty is quantified and suppressed to minimize its impact, thus yielding enhanced precision in water body delineation. Ultimately, a comprehensive loss function is designed for model optimization to generate the final water body map. Furthermore, to promote water body segmentation models’ development, this study also presents the HBD_Water water body sample dataset, which contains 44 multispectral, 5000 × 5000-pixel images at 2 m spatial resolution, and will be released on the LuojiaSET platform soon. Finally, to verify the proposed model and its constituent MST and MSIF modules, extensive water mapping experiments were performed on three datasets. The experimental results substantiate their effectiveness. Furthermore, comparative experiment results demonstrate that the proposed model performs better at water body extraction than advanced networks including TransUNet, DeeplabV3+, and ADCNN.
Landslide susceptibility assessment (LSA) is crucial for regional landslide risk evaluation and mitigation strategy formulation. Previous studies mostly adopted single-scale features, while landslide formation is influenced by multi-scale factors, making multi-scale information extraction more appropriate for assessment. This study proposes a deep learning framework integrating multi-scale and attention modules for object-based LSA. A multi-scale network extracts geo-environmental features at different scales, which are input into attention networks using multi-head attention and Squeeze-and-Excitation, termed MSMHA and MSSE, respectively, to enhance relevant features and suppress irrelevant ones. Finally, features are fused for classification and prediction. In a case study in Hong Kong, CNN-based and ML-based methods were compared using 9814 landslides and 11 influencing factors. Results show the proposed MSMHA (area under the curve, AUC 0.91) and MSSE (AUC 0.90) outperform conventional methods (e.g., random forest with AUC 0.86; multi-layer perceptron and support vector machine with AUC 0.85; DenseNet with AUC 0.86; CNN with AUC 0.88; VGG with AUC 0.87; GoogLeNet and ResNet with AUC 0.81). CNN-based methods outperformed ML-based ones, indicating that incorporating neighborhood information improves model performance. The rationality of the susceptibility map generated by MSMHA was verified via comparative analysis. Results confirm that the proposed multi-scale and attention-integrated framework outperforms traditional single-scale methods consistently. Equally importantly, the case study provides advanced CNN-based landslide susceptibility maps for Hong Kong, which can serve as a critical reference for regional landslide risk management and the formulation of targeted mitigation strategies.
Indoor space segmentation is essential for indoor navigation, 3D reconstruction, and Building Information Modeling (BIM). However, reliable segmentation from unstructured 3D point clouds remains challenging due to structural voids caused by occlusion and noise, as well as the difficulty of distinguishing permanent structural elements from dense non-structural clutter. To address these issues, this paper proposes a semantic-grid structural completion method for indoor space segmentation from 3D point clouds. The method first integrates RandLA-Net-based semantic segmentation with geometric similarity correction to improve structural consistency. Subsequently, a semantic-grid structural completion algorithm detects and fills structural voids under height constraints; this process employs dual-grid structural marking with a 2D semantic occupancy grid and a 3D voxel grid to identify missing observations and generates synthetic points with inherited semantic labels to restore structural integrity within the scene. A density-aware height difference filtering method is then applied to remove non-structural clutter and clearly separate structural elements from the rest of the scene. Finally, indoor spaces are delineated through connectivity-based segmentation and inverse distance-weighted label propagation. Experiments on public datasets, including S3DIS, UZH and Structured3D, demonstrate that the proposed method consistently outperforms existing approaches, achieving a mean F1 Score of 0.99, an Intersection over Union (IoU) of 0.98, and a Segmentation Error Rate (SER) of 0 in most scenarios, particularly in occlusion-affected and structurally complex indoor environments.
Waterbody extraction is of great significance for water resource investigation and monitoring. In addition to RGB bands, most common satellite images have a near-infrared (NIR) band. By combining these RGB-NIR bands, certain water, vegetation, and shadow indices can be calculated. The near-infrared band and these indices are very similar to the X modality in RGB+X data (common examples include RGB-D and RGB-Thermal). However, at present, no studies have thoroughly examined multimodal feature fusion from the RGB+X perspective in order to extract waterbodies with high precision. As a result, existing algorithms do not fully utilize satellite image information and have limited generalization ability. To overcome this limitation, we propose a dual-complexity backbone for waterbody extraction from the perspective of RGB+X data semantic segmentation. Its complex Transformer branch is used to extract RGB modality features, while its simple CNN branch is used to extract X modality features. This network structure can effectively capture multimodal, global, and local features in remote sensing images. It can also fully leverage the fact that the scale of RGB image datasets in computer vision is significantly larger than that of remote sensing waterbody extraction datasets. If a large pretrained model is used in the RGB branch, it is unnecessary to freeze the weights. Instead, both branches can be trained jointly, allowing the RGB branch to better adapt to the remote sensing waterbody extraction task without raising concerns that fine-tuning might undermine the pretrained model’s strong representation capability. We also propose two X modality configurations with strong generalization performance. To fully fuse multimodal features, we design a hybrid fusion module combining a CNN and a cross-attention mechanism. To integrate the multi-scale features, we employ a multi-scale Transformer structure in the RGB branch and design a multi-scale decoder. Our algorithm achieves state-of-the-art performance on the GID-5 dataset and competitive performance on the S1S2-Water dataset. Furthermore, it significantly outperforms existing methods in cross-dataset zero-shot transfer between the two datasets, with IoU/F1-score gains of 26.08%/27.33% on GID-5 and 38.74%/31.37% on S1S2-Water over previous SOTA methods. Our processing paradigm of modeling RGB-NIR remote sensing images as RGB+X data shows potential for generalization to other multi-modal remote sensing tasks. The dual-complexity backbone we design also has potential to be extended to other tasks that transfer large pretrained RGB models to remote sensing imagery with RGB-NIR four bands or even more spectral bands. We have open-sourced the code and trained models used in this research.