The complex design of transportation infrastructure hinders communication between different roles in the project, which makes it difficult to promote the Integrated Project Delivery (IPD) mode. This paper discusses a design simulation and communication system based on Building Information Modeling and Virtual Reality for transportation infrastructure (DSC-BV-TI system), integrated with BIM, with VR developed by using a game engine. Based on an analysis of the user’s demand, the system introduces a three-dimensional BIM model of traffic infrastructure in an immersive VR environment and realizes the simulation design, weather simulation, virtual driving, sight distance calculation, visual simulation and other functions of traffic infrastructure project by using the system’s safety assessment and scheme decision. The system is applied to the design of the Jinjiazhuang Extra-Long Tunnel project of the Yan-Chong Expressway in Hebei Province, which was built for the 2022 Winter Olympics. The results show that, using the DSC-BV-TI system, the designer has completed a display of the overall scheme: the user can use the steering wheel to drive a vehicle; use the head-mounted display to play the picture; realize the simulation and interaction in a variety of simulated weather conditions and environments; and use IPD mode to communicate and make decisions on the design scheme of the traffic infrastructure, tunnel speed limit and other aspects that play a key role. The DSC-BV-TI system has 8 advantages and 4 disadvantages identified through a questionnaire survey, the advantages including high fidelity, high efficiency and low cost. At the same time, according to the research results, three suggestions to help improve the system are discussed. DSC-BV-TI system as a communication bridge between the design team and other stakeholders reduces the communication gap and promotes the implementation of the IPD mode in transportation infrastructure projects.
Cross-view geo-localization (CVGL) between UAV and satellite imagery is crucial for GNSS-denied navigation but brittle under domain shift due to background shortcuts and layout misalignment. We present SURFNet, a surface-aware two-stage framework that boosts accuracy and cross-dataset generalization via explicit ground-structure modeling. A Satellite Semantic Augmentation Algorithm (SSAA) preserves salient surface elements and synthesizes structure-preserving pseudo-backgrounds to diversify satellite training data. A Dual Positional Encoding (DPE) combines learnable 2D embeddings with rotation-aware encodings, while a Ground-Aware Aggregation Block (GAB) performs dynamic multi-branch integration of local–global cues.On University-1652 and SUES-200, SURFNet delivers competitive in-dataset results and achieves state-of-the-art zero-shot generalization from University-1652→SUES-200 across altitudes. Additional transfers underline deployability: University-1652→DenseUAV exposes a large style/coverage gap that is substantially closed by lightweight fine-tuning (freezing the backbone, adapting small heads on a 50-class subset), while SUES-200→University-1652 shows expected asymmetry tied to the smaller source diversity of SUES-200. Subset studies on SUES-200 (dense/sparse buildings, water scenes, natural landscapes) further indicate that SURFNet exploits general surface saliency—not only the four SSAA categories—to generalize across scene types. Overall, surface-aware augmentation plus structure-guided aggregation yields features that are both accurate and adaptable for real-world CVGL.
Forecasting pedestrian trajectories is crucial for autonomous driving systems but remains challenging due to complex spatial and temporal interactions. Most existing methods model these interactions separately; for example, they capture temporal features and then pass this information to a spatial interaction model. These sequential methods hinder communication between the two dimensions, reducing forecasting accuracy. To address this limitation, we propose a novel method called CAM (Cross-Dimensional Attention Mechanism for Pedestrian Trajectory Forecasting). CAM independently captures temporal and spatial features and facilitates effective communication between them. Specifically, we utilize graph attention networks to capture spatial features and transformers to capture temporal features. The cross-dimensional attention mechanism enables features encoded in one dimension to query and retrieve relevant information from the other dimension. This mechanism allows features in both dimensions to interact effectively, making pedestrian trajectory forecasting easier. We evaluated our method on two well-known public datasets, ETH and UCY. The results show that our method improves forecasting accuracy, with the average displacement error (ADE) of 0.21 and final displacement error (FDE) of 0.41, improving the ADE and FDE by 16.0% and 6.8%, respectively.