Extracting road network information from satellite remote sensing images is an effective method of dealing with dynamic changes in road networks. At present, the use of deep learning methods to automatically segment road networks from remote sensing images has become mainstream. However, existing methods often produce fragmented extraction results. This is usually caused by insufficient feature extraction and occlusion. In order to solve these problems, we propose an enhanced feature extraction and multi-branch occlusion discrimination network (EFMOD-Net) based on an encoder–decoder architecture. Firstly, a multi-directional feature extraction (MFE) module was proposed as the input for the network, which utilizes multi-directional strip convolution for feature extraction to better capture the linear features of the road. Subsequently, an enhanced feature extraction (EFE) module was designed to enhance the performance of the model in the feature extraction stage by using a dual-branch structure. The proposed multi-branch occlusion discrimination (MOD) module combines the attention mechanism and strip convolution to learn the topological relationship between pixels, enhance the network’s detection of occlusion and complex backgrounds, and reduce the generation of road debris. On the public dataset, the proposed method is compared with other SOTA methods. The experimental results show that the network designed in this paper achieves an IoU of 64.73 and 63.58 on the DeepGlobe and CHN6-CUG datasets, respectively, which is 1.66% and 1.84% higher than the IoU of performance-based methods. The proposed method combines multi-directional bar convolution and a multi-branch structure for road extraction, which provides a new idea for linear object segmentation in complex backgrounds that could be applied directly to urban renewal, disaster assessment, and other application scenarios.

Collaborative geometric reconstruction of building structures can significantly reduce communication consumption for data sharing, protect privacy, and provide support for large-scale robot application management. In recent years, geometric reconstruction of building structures has been partially studied, but there is a lack of alignment fusion studies for multi-UAV (Unmanned Aerial Vehicle)-reconstructed geometric structure models. The vertices and edges of geometric structure models are sparse, and existing methods face challenges such as low feature extraction efficiency and substantial data requirements when processing sparse graph structures after geometrization. To address these challenges, this paper proposes an efficient deep graph matching registration framework that effectively integrates interpretable feature extraction with network training. Specifically, we first extract multidimensional local properties of nodes by combining geometric features with complex network features. Next, we construct a lightweight graph neural network, named EKNet, to enhance feature representation capabilities, enabling improved performance in low-overlap registration scenarios. Finally, through feature matching and discrimination modules, we effectively eliminate incorrect pairings and enhance accuracy. Experiments demonstrate that the proposed method achieves a 27.28% improvement in registration speed compared to traditional GCN (Graph Convolutional Neural Networks) and an 80.66% increase in registration accuracy over the suboptimal method. The method exhibits strong robustness in registration for scenes with high noise and low overlap rates. Additionally, we construct a standardized geometric point cloud registration dataset.

Partial indoor point clouds acquired by light detection and ranging (LiDAR) are frequently affected by occlusion, restricted viewpoints, and non-uniform sampling, making it difficult to recover complete scene geometry while preserving the semantics of architectural structures and interior objects. To address this challenge, we propose the Structure-Aware Dual-Decoder Point Completion Network (SDD-PCN) for joint point-cloud completion and semantic segmentation. SDD-PCN first separates architectural structures from interior objects and applies dedicated multi-resolution encoders to capture their distinct geometric characteristics. The resulting local features are fused with a global scene representation and processed by parallel completion and segmentation streams that exchange information during progressive decoding. We further construct Partial-S3DIS, a partial-scene extension of the Stanford Large-Scale 3D Indoor Spaces (S3DIS) dataset, containing 1632 partial–complete scene pairs generated from 272 annotated rooms through sensor-aware LiDAR simulation. Experiments show that SDD-PCN achieves L1 and squared L2 Chamfer distance (CD-L1 and CD-L2) values of 16.73 and 15.27, respectively, under the ×${10}^{-3}$ reporting convention. Relative to ProtoFormer, the strongest overall baseline, SDD-PCN reduces CD-L1 by 3.96% and CD-L2 by 7.90%, while obtaining the best completion performance in eight of ten scene categories. The model also achieves an overall accuracy (OA) of 87.23%, a mean class accuracy (mAcc) of 74.33%, and a mean intersection over union (mIoU) of 63.62%, outperforming both task-matched semantic scene completion baselines across all three semantic metrics. Ablation and robustness analyses confirm that structure-aware encoding and dual-stream feature interaction improve geometric recovery, particularly under moderate and severe missingness. These results demonstrate that explicitly modeling indoor structural heterogeneity provides an effective basis for unified point-based scene completion and semantic understanding.

With the development of intelligent unmanned systems, it is important for indoor mobile mapping and structural perception to reconstruct building structures in a timely manner from sequential LiDAR point clouds. However, many existing reconstruction methods rely on complete or accumulated point clouds, making them less suitable for partial observations, occlusions, and continuous updates. This paper proposes an incremental geometric reconstruction framework for building structures based on LiDAR point clouds. The method combines temporal state inheritance and orthogonal projection to transform 3D point-cloud processing into 2D plane-based contour updating. A transmissive relationship-based hole detection strategy is introduced to preserve real openings such as doors and windows while completing partially unobserved regions. Simulation and real-world experiments show that the proposed method can recover major planar building structures. In the simulation scene, the proposed method achieves a CD-L1 of 0.088 m, a CD-L2 of 0.007 m², and an F1-score of 0.901, with an average single-frame processing time of 1.02 s. The experimental results indicate that the proposed method provides a compact and interpretable plane-based structural representation for near-real-time incremental reconstruction of building structures from sequential LiDAR point clouds.