With the growing attention toward developing a multimodal transport system to enhance urban mobility, there is an increasing need construct new infrastructures, rebuild or expand existing ones, accommodate current and newly generated travel demand. Therefore, this study develops bi-level model that simultaneously determines location capacity of transfer infrastructure be built considering elastic demand in network. The upper-level problem formulated as mixed-integer linear programming...

In this paper, a novel fusion network for infrared and visible images is proposed, named Image Pair Learning Fusion Network (IPLF). At present, most of the released deep learning-based models are trained using unsupervised learning. This learning method lacks ground truth cannot guide model in targeted manner. First, we propose use supervised to training The generated image pairs used as truth. Second, strategy paired images. enhances complementary constraints so that final fused possesses...

Accurate individual tree reconstruction based on laser point clouds is vital for precise biomass estimation, virtual geographic environment modeling, and simulation. However, mobile 3D scanning systems often capture obscured by leaves, resulting in missing or incomplete branch data, posing significant challenges to detailed reconstruction. In this paper, a novel method fine-grained model from proposed. This approach addresses the structural of trees, tackling two main problems:...

Graph theory effectively explains urban structures via street–street connectivity. However, systematic comparisons of street across cities remain challenging. This study employs graph convolutional networks (GCNs) to analyze network structures. A two-branch GCN was used as the backbone extract comparable features among networks. The proposed approach examine different road in a case polycentricity prediction 298 Chinese cities. model transformed approximately 4.5-million segments into...

With the accelerating urbanization process, population increasingly concentrates in urban areas. In view of huge China and a series problems process rapid urbanization, there are no unified measures for characterizing pattern. This study explores distribution pattern Chinese proposes spatial structure using GIS (Geographic Information System) analysis. The main findings as follows: (1) 2015, density presents high southeast low northwest based on county-level administrative regions. lives “Hu...

Abstract This article presents a new method to illustrate the feasibility of 3D topology creation. We base construction process on testing real cases implementation parcels in cadastral system. With utilization and development dense urban space, true geometric volume primitives are needed represent with adjacency incidence relationship. present an effective straightforward approach identifying constructing valid volumetric object from given faces, build topological relationships among...

As an essential part of point cloud processing, autonomous classification is conventionally used in various multifaceted scenes and non-regular distributions. State-of-the-art methods mostly process raw clouds, using a single as the basic unit calculating features by searching local neighbors via k-neighborhood method. Such tend to be computationally inefficient have difficulty obtaining accurate feature descriptions due inappropriate neighborhood selection. In this paper, we propose robust...

This paper presents a novel fully automated approach for generating structured 3D synthetic tree models, addressing the limitations of existing datasets used in applications like digital twin construction, carbon stock calculation, and environmental assessments. The method allows creation large-scale dataset containing 13,000 models ten common species, each featuring detailed point cloud with hierarchical structures, precise parameters, separate branch leaf information. includes both...

ABSTRACT Traditional localization methods based on sensors such as Bluetooth and Wi‐Fi struggle to achieve the required accuracy for fine‐grained applications like AR navigation or robot localization. Accurate global position estimation seamless in dynamic indoor environments can significantly enhance intelligence of scene applications. This paper proposes an as‐built BIM‐based using End‐to‐End visual ARCore. First, pre‐captured RGB image sequences, a sparse point cloud space be constructed...

In high-density crowds, close proximity between pedestrians makes the steady state highly vulnerable to disruption by pushing behaviours, potentially leading serious accidents. However, scarcity of experimental data has hindered systematic studies its mechanisms and accurate modelling. Using behavioural from bottleneck experiments, we investigate pedestrian heterogeneity in tendencies, showing that tend push under high-motivation wider corridors. We introduce a spatial discretization method...

The accuracy of on-grid frequency estimation methods suffers from the quantization error discrete grids. In this article, a deep unfolded network for off-grid is proposed, dubbed OGFreq. OGFreq, there exist two kinds variables. One batch-oriented dictionary frequency-domain transform, and other one instance-specific bias. As required to be universally applicable among all observed signals, layers are designed weights updated approximate transform bases in data-driven way. Besides,...

ABSTRACT The factor flow network of the rural areal system (RAS) provides an important perspective for understanding its internal synergistic development. Traditional synergy assessment is usually based on space places, a concept focusing size (capacity), rather than flows, connections (flows). In this study, we developed multilayer model describing flows factors such as people, land, and industry in RAS using concept, big data, complex theory, then quantitatively characterized three metrics...

ABSTRACT Labels are widely used in maps to convey verbal information for symbols and play a crucial role aiding users' navigation understanding of spatial context. Traditional labeling approaches mainly focus on ensuring label readability by placing them overlap‐free while maintaining visual coherence. However, these methods often fall short Point Interest (POI) labeling, particularly the context Chinese labels, due growing demand detailed informative with long or descriptive POI names. To...