The quality and efficiency of road maintenance greatly impact on transportation performance. There is an urgent need to automate the process of decision-making for road maintenance, especially for reactive maintenance. However, automating this process is challenging because (1) the expert knowledge required in this process is implicit and difficult to formalize and (2) the defect reports from frontline inspectors are in unstructured human language. This paper proposes a method based on natural language processing (NLP) and knowledge graph reasoning. This method combines the semantic understanding capability of NLP with the structural reasoning capability of the knowledge graph, enabling nuanced and logically rigorous road maintenance decisions. Real-world highway defect reports are used for validation. The experimental results demonstrate a significant improvement of the proposed model over baseline models, with up to 13.5% higher accuracy on the prediction of key tasks. This approach enables a traceable decision-making process, avoiding a black-box model.

The use of graph-based asset information is growing in the Architecture, Engineering, Construction, and Operation (AECO) domain. However, there has been no comprehensive investigation into its internal structure, which hinders the efficiency of information querying and knowledge discovery. This study aims to reveal the internal structure of graph-based IFC (Industry Foundation Classes) information, referred to as IFC-Graph, and to assess the impact of graph structure on the efficiency of information querying and knowledge discovery. First, through a close examination of the IFC standard, five levels of detail were identified and proposed for IFC-Graph. Second, methods for generating graphs at each level were developed. Lastly, the impact of graph structure on information querying and knowledge discovery was assessed. The results show that: (1) relations constitute the main framework of graph-based IFC information and are key to efficiently extracting relational information from IFC-Graph; and (2) the proposed five-level framework makes graph-based asset information more practical to use, by increasing flexibility in graph generation and improving the efficiency of graph queries and knowledge discovery.

• KG querying, reasoning, and enhancement in maintenance decision-making are discussed. • Examine KG use in fault diagnosis, action identification and maintenance organization. • Highlight major gaps and future directions of KGs in maintenance decision making. Operational-level maintenance is essential to ensuring the normal functions of systems and equipment in the industry. The current practice for decision-making for operational maintenance is still expert-led and heavily relies on experts’ implicit knowledge from their experience. This leads to the urgent need for better knowledge management, which can facilitate more efficient and effective operational maintenance. To fulfill this need, knowledge graphs (KGs) have been proposed by previous studies, due to their ability to digitize knowledge and their structural and semantic features to facilitate various decision-making approaches. Although multiple KG-based methods have been proposed and implemented, several questions about maintenance-related knowledge graphs remain unclear, including 1) What methods are employed to exploit the capabilities of KGs in maintenance decision-making, 2) In which scenarios KGs are applied, and how they are utilized, and 3) What are the challenges and opportunities of implementing KGs in practice. To address these questions, this study made a comprehensive systematic review. A total of 270 papers were retrieved from Scopus, and 76 papers were closely examined. The review finds that 1) KG-based querying, reasoning, and enhancement of other algorithms are common methods in decision-making problems; 2) most KGs are applied in fault diagnosis, but KGs also contribute to maintenance action identification and organization; and 3) most applications of KGs in industrial maintenance decision-making are limited to simple tasks and more exploration of efficiently using and sharing KGs is needed. This study summarizes the state-of-the-art works in knowledge graphs for operational maintenance, which can facilitate further research.

All-in-focus(AIF) images, which contain comprehensive scene information with global sharpness, play a crucial role in high-precision light field (LF) measurement and computational imaging. However, generating AIF images from LF data typically requires accurate depth priors, which are often unavailable or unreliable in practice. To overcome this limitation, directly fusing a series of LF refocused images provides an effective alternative that eliminates the dependency on explicit depth estimation. Nevertheless, existing multi-focus image fusion(MFIF) methods are primarily designed for fusing image pairs with complementary focus, performing poorly when applied to stacks due to the error accumulation that occurs during iterative fusion. To this end, we propose a Frequency-Decoupled Stack Fusion Network (FDSNet) for high-precision depth-free LF AIF image generation. FDSNet incorporates a spatial-frequency joint feature extraction module that captures multi-scale spatial details while decoupling high- and low- frequency components to model textures and contextual information separately, thereby alleviating edge blurring caused by subtle focal variations and weak textures in transition regions. Moreover, a dual-stage cross-attention fusion module, following a coarse-to-fine strategy, suppresses artifacts, enhances edge fidelity, and enables simultaneous fusion of arbitrary numbers of refocused images, thereby avoiding error accumulation and computational redundancy. Extensive experiments on both synthetic and real LF datasets demonstrate that FDSNet achieves superior visual quality and quantitative performance. Additional experiments further demonstrate that FDSNet performs robustly under varying low-light and noisy conditions. These results validate that FDSNet delivers excellent fusion capability in terms of image clarity, detail preservation, noise resistance, and generalization, outperforming existing state-of-the-art methods.

In annotating real-life large, noisy and domain-specific images for digitising infrastructure, substantial human effort persists despite past advancements. This research provides practical and interpretable scores for human annotators, enabling flexible annotation strategies, improving automation and reducing the effort required to create and correct image labels. The authors present the CRAAC solution: Consistency Regularised Active learning and Automatic Corrections, which builds on Mask R-CNN with three additional modules: consistency regularisation, scoring modules for active learning and automatic corrections. Experiments on our pavement image dataset, recorded with a low silhouette score of 0.146 and qualitative annotation inconsistencies, reduce the human effort of mouse clicks by 5-11% and improve the quality metrics of mAP and AR by approx. 40% from the original Mask R-CNN. The automatic correction further reduces the performance variation.

Proactive road maintenance extends asset lifespan, enhances safety and reduces downtime. However, costly reactive maintenance becomes necessary without up-to-date and well-structured data. While Geometric Digital Twins (GDT) offer digital replicas of physical structures that can be used to automate maintenance activities, no automated tools are currently available for GDT’s upkeep. This paper addresses this issue and proposes a method with a multi-step pipeline for detecting changes, matching instances, identifying newly added objects and applying these changes to the GDT 3D model using point clouds. Our methods, namely Iterative Change Refinement using a single labelled scan and Dual Instance Aware Change Retrieval using two scans, achieve a 0.89-0.97 F1 score in change detection, and our holistic pipeline results in less than 0.1° rotation angle and 0.01 m translation mean squared errors. This pipeline automates the process of GDT maintenance, making such digital twins viable and practically applicable to the industries.

Building permitting is essential for ensuring the safety, sustainability, and societal alignment of construction projects. Despite interest from both practitioners and researchers, the process remains largely manual and fragmented. Ontologies offer a promising solution by managing complexity and enabling automation through semantic information, though current ontologies in the building permit domain are limited to specific aspects like building code checking. On the process level, the OntoBPR framework integrates multiple domain-specific ontologies for a seamless digital permitting process and provides a workflow to automate the lifecycle of the permit review. Therefore, it suggests integrating the submitted building application using standardized information containers. The paper explores how digital applications can be submitted, reviewed, verified for completeness, and forwarded to authorities, and how permit review results can be gathered to support decision-making and automate notification issuance, and it provides a demonstration in a case study. In conclusion, OntoBPR formalizes a multi-layered ontology that advances and aligns the partitioned building permit process and provides an adaptable framework to harmonize diverse legal, informatics, and procedural aspects.

Road maintenance involves manually classifying a large volume of textual data necessary for downstream applications such as raising a maintenance job order. Automation can not only bring significant time and cost savings, but it can also facilitate digitalization efforts like the Road Digital Twin (DT). However, as is the case with many Architecture, Engineering and Construction (AEC) applications, annotated data availability is low, which demands exploration of specialized techniques for resource-constrained settings that have not been focused on in engineering. This work bridges this gap by proposing a data-efficient similarity-based text classifier that aims at effectively utilizing existing domain knowledge and pre-training knowledge of Large Language Models (LLMs) to enable rapid domain adaptation. It reformulates text classification as a similarity comparison task, using semantics directly as a classification criterion. Through a case study on classifying road inspection comments, the proposed classifier outperformed both traditionally fine-tuned and few-shot learning approaches. It attained an f 1 score of 0.46 with just one example per class, equivalent to the value for Sentence Transformer Fine-Tuning (SetFit) with 4 examples and Llama3 with 10. Additionally, it is able to keep up with traditional fine-tuning methods when trained with more than 300,000 total examples, achieving an a c c u r a c y of more than 95% and f 1 of around 0.9. These results indicate that the proposal is competitive against traditionally fine-tuned and few-shot models across all levels of data availability. This versatility significantly elevates the feasibility of deploying an automated text classification pipeline in a complex engineering field like road maintenance.

The CAMHighways dataset is presented, built from mobile mapping data that surveyed over 40 km of UK Highways. The dataset consists of textured meshes for road assets (including the pavement, traffic signs, and road furniture), segmented and classified point clouds, orthomosaics generated from pavement images, defect label annotations and shapefiles, and ground penetrating radar point clouds. All modalities are georeferenced and can be integrated into game engines and/or GIS software. The main aim of this work is to facilitate and automate the building of a Digital Twin (DT), a digital representation of the highway, in order to streamline inspection and maintenance through virtual reality, robotics simulation, and DT- and AI-driven data analysis. It also serves as a valuable source for other applications, such as training semantic scene understanding and defect detection algorithms. This paper introduces the dataset and outlines the data preparation process, including novel automation methods developed for this purpose, as well as integration guidelines and possible applications. • The new CAMHighways dataset is presented, spanning 42.8 km of UK highways. • Mobile mapping data is prepared for building a road DT for inspection & maintenance. • 3D meshes, point clouds, pavement orthomosaics, labels, and GPR data are included. • Several aspects of the DT generation process are automated. • The dataset is integrated into game engines and GIS software.

Significant funds have been allocated to maintain road networks each year in developed countries. Performance prediction is crucial for pavement management systems to adjust working plans and budget allocation. As a Bayesian nonparametric method, Gaussian process regression (GPR) is powerful in predicting nonlinear time series and quantifying uncertainty. However, it remains computationally intensive and fails to adapt to the time-varying characteristics. To address such issues, a dynamic GPR model is proposed for probabilistic prediction of the International Roughness Index (IRI) for flexible pavements. A moving window strategy is developed to substantially shrink the size of training data, which effectively alleviates computational cost and thus leads to a dynamic GPR. A genetic algorithm is then adopted to determine the optimal window size by considering the trade-off between computational efficiency and accuracy. A dataset acquired from Long-Term Pavement Performance (LTPP) is used to demonstrate the feasibility of the dynamic GPR. Its performance is compared to traditional GPR as well as dynamic and static Bayesian linear regression (BLR) models. The comparison results indicate that the proposed dynamic GPR can increase the accuracy by 0.86, 1.52, and 2.27 times for dynamic BLR, static GPR, and static BLR, respectively. It exhibits the best results in terms of accuracy and uncertainty metrics due to its nonlinear modelling and time-varying ability.

In this paper, we propose a method for semantic parsing the 3D point cloud of an entire building using a hierarchical approach: first, the raw data is parsed into semantically meaningful spaces (e.g. rooms, etc) that are aligned into a canonical reference coordinate system. Second, the spaces are parsed into their structural and building elements (e.g. walls, columns, etc). Performing these with a strong notation of global 3D space is the backbone of our method. The alignment in the first step injects strong 3D priors from the canonical coordinate system into the second step for discovering elements. This allows diverse challenging scenarios as man-made indoor spaces often show recurrent geometric patterns while the appearance features can change drastically. We also argue that identification of structural elements in indoor spaces is essentially a detection problem, rather than segmentation which is commonly used. We evaluated our method on a new dataset of several buildings with a covered area of over 6, 000m2and over 215 million points, demonstrating robust results readily useful for practical applications.

Building Information Models (BIMs) are becoming the official standard in the construction industry for encoding, reusing, and exchanging information about structural assets. Automatically generating such representations for existing assets stirs up the interest of various industrial, academic, and governmental parties, as it is expected to have a high economic impact. The purpose of this paper is to provide a general overview of the as-built modelling process, with focus on the geometric modelling side. Relevant works from the Computer Vision, Geometry Processing, and Civil Engineering communities are presented and compared in terms of their potential to lead to automatic as-built modelling.