Conference Agenda

This paper presents an efficient approach to the accessibility assessment of tram transport based on a simulation within a digital twin environment. We propose a novel framework that integrates several advanced data acquisition and processing steps: mobile mapping of the tram routes, detection of rail tracks and tram stops, and the final assessment of tram accessibility by simulating the MAL deployment in the digital twin. Our experimental evaluation demonstrates that the digital twin provides a practical and reliable tool for assessing tram accessibility.

As-built Building Information Models (BIMs) are crucial for building digitalisation, structural analysis, and life cycle management. Despite recent advances, automated reconstruction of structural elements from point clouds remains a challenging task, particularly in ensuring geometric accuracy and topological consistency within a storey and across consecutive storeys. This paper proposes an automated method for refining topological inconsistency between columns, beams, and slabs, ensuring consistent as-built BIMs. The method places Constructive Solid Geometry (CSG) at the core of the refinement process, driven by fundamental structural principles. The method starts by creating solid rectangular prisms from labelled point clouds. Beams are then aligned both vertically and horizontally within each storey. Columns are vertically aligned across consecutive storeys. Topology relationships between the elements are retrieved and encoded in graphs. These graphs, together with a set of Boolean operations, are used to resolve gaps and trim overlaps between the connected elements. The refined elements are represented in accordance with the IFC standards. The proposed method was validated on two multi-storey case studies representing frame and flat-slab building structures. Both qualitative and quantitative evaluations confirmed the effectiveness of the approach, achieving significant geometric accuracy and topological consistency. In addition, the method exhibits efficient runtime performance, indicating its promise for scalable Scan-to-BIM automation.

Bridge infrastructure plays a critical role in transportation networks, requiring reliable and efficient methods to detect missing bolts to ensure structural integrity and prevent failures. This study proposed a novel methodology integrating point cloud-based Digital Twins (DTs) with Topological Data Analysis (TDA), specifically using Persistent Homology (PH), for robust and accurate missing bolt detection. The framework combines 3D photogrammetric reconstruction to generate point cloud-based DTs, Convolutional Neural Networks (CNNs) for precise bolt localization, and PH to identify and quantify missing bolts. Through parameter evaluations and a real-world bridge case study, the proposed approach demonstrated high detection accuracy, effectively identifying missing bolts with a false positive rate below 10%. These findings confirm the reliability and effectiveness of integrating DTs with TDA as an advanced data-driven approach for automated structural inspection and bridge health monitoring.

Semantic segmentation of indoor point clouds is a fundamental task in 3D scene understanding, supporting applications such as virtual reality, indoor navigation, and building management. Point-based transformer models achieve high accuracy but require substantial computational resources, while superpoint-based methods are more efficient yet often less precise. To address this trade-off, we propose LGFormer, a lightweight framework that integrates Graph Convolutional Networks (GCN) and transformers to jointly capture local and global contextual features. The method constructs a superpoint-based topology graph, where local features are extracted using GCN and global dependencies are modeled through transformer layers. Experiments on the S3DIS and ScanNet++ datasets demonstrate that LGFormer achieves 90.7% and 88.5% segmentation accuracy, respectively, while reducing inference time by more than 99% compared with point-based transformers. By effectively leveraging superpoints and local-global feature fusion, LGFormer dlivers competitive accuracy with significantly lower computational cost, making it suitable for large-scale indoor scene analysis.

Corroding reinforcement leads to cross section loss and reduced structural capacity of concrete bridges. Detecting exposed rebars

(ER) is crucial during bridge inspection to plan countermeasures early and prevent further corrosion. With advancements in deep

learning, several public datasets derived from inspection imagery have been released to identify ER and other concrete damage

automatically. At the same time, Uncrewed Aerial Systems (UAS) have become more capable of navigating even underneath the

bridge deck. This combination holds promise to improve efficiency of bridge inspection methods, but obtained imagery differs

from available datasets, featuring very small damages and complex backgrounds. To address this mismatch, this work reviews

publicly available ER datasets, presents a UAS-based bridge inspection dataset for evaluating ER damage (UBID-ER-val), and

quantifies similarities and differences between them. We train several YOLOv8 models on conventional inspection documentation

images and benchmark the reviewed datasets, scoring F2 = 0.229 at S2DS, F2 = 0.430 at CODEBRIM, F2 = 0.584 at Dacl10k,

compared to F2 = 0.505 at UBID-ER-val. We analyse factors influencing performance and find that tiled inference raises Recall

(+0.166) but drastically reduces Precision (−0.309), while matching training and validation image resolution underperforms across

all datasets (−0.061 to −0.129). The differences in best-performing combinations underscore the underlying domain shift that

complicates practical deployment. As a practical outcome of this work, UBID-ER-val is made publicly available to enable objective

benchmarking of ER detection models and to assess their reliability under field conditions.

Detecting visible electrical utilities is a prerequisite for developing advanced reasoning strategies to reconstruct hidden in-wall networks. This paper investigates the detection of visible power-related utilities using a domain-adaptive deep learning-based vision pipeline based on the YOLOv11-L, object detection model. Four publicly available datasets containing power sockets, power strips, and light switches were curated, relabeled, and merged into a unified training dataset of 3,459 images. The resulting model achieved a mean average precision (mAP) of 0.74 for power sockets and strips and 0.98 for light switches, demonstrating strong detection performance. Real-time evaluation on a low-cost smartphone via the Ultralytics HUB App indicates reliable detection in small-scale real-world environments and detected utilities could be integrated automatically into semantic indoor models using a marker-less referencing approach. The work further highlights broader applications, including Augmented Reality-based visualization to reduce cognitive load for project managers and inspectors or construction workers and electricians, and its potential use as input for existing and future reasoning methods for hidden-utility reconstruction. The prepared dataset, trained model and source code is available at: https://github.com/hcu-cml/indoor-electrical-facility-detection