Recently, the concept of Digital Twin [DT] has pervaded the field of urban planning and city infrastructure management. This paper first affirms that the knowledge created by virtue of DT real-world implementation, through undertaking various DT pilot projects, case studies and proof-of-concept initiatives, comprises the ‘know-how’ and genuine practical experience upon which the DT research and practices can further develop and mature. It then argues that this type of knowledge is poorly captured and mostly left neither realized nor fully utilized. This significantly hinders the rate by which DT practices within the urban and built environments evolve. While acknowledging the benefits of the ongoing work by many DT researchers, including enumeration, categorization and detailing of multiple DT use cases, such endeavours arguably suffer from three profound weaknesses causing the inefficient sharing and transfer of DT ‘know-how’ knowledge amongst DT stakeholders. The three limitations are: (a) lack of DT standard terminology constituting a common DT language; (b) lack of standard and clear methods to enable documenting DT projects and making the ‘know-how’ explicit to the rest of the DT market; and (c) the lack of an established and adequate DT use cases classifications system to guide DT practitioners in searching for and retrieving the previously accomplished DT case studies that are most relevant to their interests and context. Correspondingly, three solutions are proposed constituting a three-pronged DT Uses Classification System [DTUCS]: prong-A (i.e. Standardize-to-Publish); prong-B (i.e. Detail-to-Prove); and prong-C (i.e. Classify-to-Reach). DTUCS is developed using a meta-methodology encapsulating a systematic literature review and three distinct sub-methodologies. The paper concludes with an overview of the implications of DTUCS along with recommendations on how it can be further validated and improved.
Research domain and Problem: HBIM modelling from point cloud data has become a crucial research topic in the last decade since it is potentially considered as the central data model paving the way for the digital heritage practice beyond digitization. Reality Capture technologies such as terrestrial laser scanning, drone-mounted LiDAR sensors and photogrammetry enable the reality capture with a sub-millimetre accurate point cloud file that can be used as a reference file for Heritage Building Information Modelling (HBIM). However, HBIM modelling from the point cloud data of heritage buildings is mainly manual, error-prone, and time-consuming. Furthermore, image processing techniques are insufficient for classification and segmentation of point cloud data to speed up and enhance the current workflow for HBIM modelling. Due to the challenges and bottlenecks in the scan-to-HBIM process, which is commonly criticized as complex with its bespoke requirements, semantic segmentation of point clouds is gaining popularity in the literature. Research Aim and Methodology: Therefore, this paper aims to provide a thorough critical review of Machine Learning and Deep Learning methods for point cloud segmentation, classification, and BIM geometry automation for cultural heritage case study applications. Research findings: This paper files the challenges of HBIM practice and the opportunities for semantic point cloud segmentation found across academic literature in the last decade. Beyond definitions and basic occurrence statistics, this paper discusses the success rates and implementation challenges of machine and deep learning classification methods. Research value and contribution: This paper provides a holistic review of point cloud segmentation and its potential for further development and application in the Cultural Heritage sector. The critical analysis provides insight into the current state-of-the-art methods and advises on their suitability for HBIM projects. The review has identified highly original threads of research, which hold the potential to significantly influence practice and further applied research.