The integration of multi-source remote sensing data, bolstered by advancements in deep learning, has emerged as a pivotal strategy for enhancing land use and land cover (LULC) classification accuracy. However, current methods often fail to consider the numerous prior knowledge of remote sensing images and the characteristics of heterogeneous remote sensing data, resulting in data loss between different modalities and the loss of a significant amount of useful information, thus affecting classification accuracy. To tackle these challenges, this paper proposes a LULC classification method based on remote sensing data that combines a Transformer and cross-pseudo-siamese learning deep neural network (TCPSNet). It first conducts shallow feature extraction in a dynamic multi-scale manner, fully leveraging the prior information of remote sensing data. Then, it further models deep features through the multimodal cross-attention module (MCAM) and cross-pseudo-siamese learning module (CPSLM). Finally, it achieves comprehensive fusion of local and global features through feature-level fusion and decision-level fusion combinations. Extensive experiments on datasets such as Trento, Houston 2013, Augsburg, MUUFL and Berlin demonstrate the superior performance of the proposed TCPSNet. The overall accuracy (OA) of the network on the Trento, Houston 2013 and Augsburg datasets is of 99.76%, 99.92%, 97.41%, 87.97% and 97.96%, respectively.

Cylinder point extraction is a crucial prerequisite for applications of industrial scenarios, such as reverse engineering and clearance analysis, using laser point clouds. This task currently suffers from data missing, noise, and interference from the planar objects. The generalization capability for cylindrical objects with different radii is also required. Considering the cylindrical object as the continuously extended cylinder, a region growth algorithm using a multi-scale prospecting strategy is proposed in this paper. Firstly, the preprocess is conducted to subsample the point cloud and estimate each point normal. Secondly, the kernel computation is used to detect the potential cylinder patches as kernels with the multi-scale cylinder prospecting. Then, the rough extraction is performed to compute the cylinder parameters with the iterative growth starting from kernels. Finally, the fine extraction labels the raw point cloud by assigning points to different cylinders under the length constraint. The real-world point clouds, which are collected from four industrial scenarios, the simulated point cloud, and an open dataset are employed to evaluate the proposed method performance. Experimental results demonstrate the effectiveness and robustness of the proposed method. The average precision, recall, and F1-Score on the real-world dataset and open dataset are 0.879, 0.894, 0.885 and 0.931, 0.893, 0.909, respectively.

The highway is a crucial component of modern transportation systems, and its efficient management is essential for ensuring safety and facilitating communication. The automatic understanding and reconstruction of highway environments are therefore pivotal for advanced traffic management and intelligent transportation systems. This work introduces a methodology for the fine-grained semantic segmentation and reconstruction of highway environments using dense 3D point cloud data acquired via mobile laser scanning. First, a multi-scale, object-based data augmentation and down-sampling method is introduced to address the issue of training sample imbalance. Subsequently, a deep learning approach utilizing the KPConv convolutional network is proposed to achieve fine-grained semantic segmentation. The segmentation results are then used to reconstruct a 3D model of the highway environment. The methodology is validated on a 32 km stretch of highway, achieving semantic segmentation across 27 categories of environmental features. When evaluated against a manually annotated ground truth, the results exhibit a mean Intersection over Union (mIoU) of 87.27%. These findings demonstrate that the proposed methodology is effective for fine-grained semantic segmentation and instance-level reconstruction of highways in practical scenarios.

Semantic segmentation of transmission-line point clouds is fundamental to intelligent power inspection and grid asset management, as segmentation accuracy directly influences defect detection and facility assessment tasks. However, transmission-line point clouds collected across different voltage levels often show significant variations in density and geometric structure due to heterogeneous LiDAR sensors and flight configurations. Combined with the high cost of large-scale manual annotation, these factors limit the scalability of existing supervised segmentation methods. To overcome these challenges, we propose a geometry-consistency-guided unsupervised domain adaptation framework tailored for cross-voltage transmission-line point-cloud segmentation. The framework employs KPConvX as the backbone and integrates three progressive components. First, a geometric consistency constraint enhances robustness to spatial variations and enables extraction of structural features invariant across voltage levels. Second, a domain feature alignment module reduces distribution shifts through global feature transformation. Third, a minimum-entropy-based pseudo-label refinement strategy improves the reliability of pseudo-labels during self-training. Experiments on a multi-voltage transmission-line dataset demonstrate the effectiveness of the proposed method. With the KPConvX backbone, the framework achieves 66.1% mean Intersection over Union (mIoU) and 94.3% overall accuracy on the unlabeled 110 kV target domain, exceeding the source-only baseline by 15.6% mIoU and outperforming several state-of-the-art UDA methods. This work provides an efficient, annotation-friendly solution for cross-voltage point-cloud segmentation and offers a promising direction for domain adaptation in complex power-grid environments.

Automated positioning of transmission tower keypoints is crucial for drone-based intelligent inspection systems. This paper proposes TPKE (Transmission Pylons Keypoint Extraction), a novel framework designed to extract multiple transmission tower keypoints from LiDAR point clouds. The method targets two core components: insulator string endpoints and ground wire hanging points. For insulator positioning, TPKE introduces adaptive density clustering, a morphological “concavity” index (η) for V-shaped insulators, and a “positioning-verification-compensation” strategy for handling missing data. For ground wire positioning, it combines local geometric feature analysis with spatial orthogonal projection. Using semantic segmentation for preprocessing, the framework reliably identifies components from complex transmission corridor point clouds. Validated on 1427 towers across 14 types, TPKE achieves an MAE of 0.0747 m for insulators and 0.0696 m for ground wires. It maintains centimeter-level accuracy even under challenging conditions like sparse point clouds. With an average processing time of 3.03 s per tower, the method demonstrates high efficiency, significantly reducing manual annotation workload while supporting autonomous navigation for transmission line maintenance.

Accurate urban digital surface model (DSM) reconstruction from satellite stereo imagery is often limited by systematic errors in rational polynomial coefficient (RPC) models, particularly when surveyed ground control points (GCPs) are unavailable. This study proposes a stable-plane-mediated ICESat-2 virtual control-point framework for GCP-free urban DSM reconstruction from multi-source satellite stereo imagery. The method uses ICESat-2/ATL03 observations as an external source of elevation control while exploiting geometrically stable urban surfaces, including flat rooftops, roads, and paved areas, to mitigate surface-association uncertainty caused by photon horizontal geolocation errors. After photon screening, candidate stable surfaces are identified from temporally matched high-resolution reference imagery using DINOv3 features and further validated using ICESat-2 elevation consistency. Within each retained stable surface, planimetric coordinates are derived from the reference imagery, representative elevations are obtained from ICESat-2 photons, and reference-to-stereo matching establishes the corresponding image observations. These independently derived components are integrated within the same physical surface to construct reliable virtual control points for robust RPC refinement. The refined RPC models are subsequently used for adaptive stereo matching, forward intersection, and DSM generation. The framework was evaluated in five urban and peri-urban areas in economically developed regions of China using Pléiades, Jilin-1, and GF-7 stereo imagery. After refinement, planimetric RMSEs ranged from 0.52 to 1.78~m and elevation RMSEs from 0.71 to 2.34~m. The mean elevation RMSE decreased from 15.35 to 1.76~m, corresponding to an 88.5\% reduction. The reconstructed DSMs achieved elevation-profile RMSEs of 2.71--6.89~m and MAEs of 1.26--3.84~m against UAV-LiDAR reference data. These results demonstrate that stable urban surfaces can effectively mediate the integration of reference-imagery-derived planimetry and ICESat-2 elevations, reducing surface-association mismatches near abrupt urban height transitions and enabling meter-level urban DSM reconstruction without surveyed GCPs.