Madhumitha Senthilvel

Bio: Madhumitha Senthilvel is an academic researcher from RWTH Aachen University. The author has contributed to research in topics: SPARQL & Linked data. The author has an hindex of 3, co-authored 9 publications receiving 25 citations. Previous affiliations of Madhumitha Senthilvel include Indian Institute of Technology Madras.

Comparison of Handheld Devices for 3D Reconstruction in Construction

Abstract: Generation and quality of as built models influence the subsequent applications such as progress monitoring, quality control, and deviation detection. The quality of any 3D reconstructed model heavily depends on the raw inputs and the post processing involved. While laser and LiDAR-based scanning are widely prevalent, lower cost equipment and sensors are increasingly becoming adaptable for 3D reconstruction. This study tests the feasibility of using IR-based scanning tablets and passive stereo vision cameras to acquire data from a construction environment based on the type of applications (such as progress monitoring, deviation detection) on a construction site. Two different off the shelf technologies: Tango tablet and ZED camera are tested during this research for developing as-built models using 3D reconstruction. The devices are compared on the basis of metrics such as preparation time for each scan, calibration of the scanner and total scanning time for determining the ease of scanning process, accuracy of generated point clouds. Also, the influence of external factors such as scanning parameters, ambient lighting, and characteristics of the object being scanned, and angle/orientation of scanner with respect to the object are studied.

Querying heterogeneous linked building datasets with context-expanded GraphQL queries

Abstract: Linked Data in the construction industry is a topic gaining serious interest over the last years. However, this interest remains largely academic and has not sparked much adoption of web technologies in the field. To nourish adoption of Linked Data in practice, access to the data has to be made more easy. SPARQL, the recommended RDF query language, has proven very powerful for retrieving and updating RDF datasets. However, due to its verbosity and complexity, it is often considered a threshold for developers to implement in their tools. In this paper, we compare SPARQL with Linked Data querying languages that extend the GraphQL syntax, in context of querying building datasets: HyperGraphQL and GraphQL-LD. Since it went open source in 2015, GraphQL has been adopted by a large community of developers, partly due to its elegance and conciseness. As a use case, the queries are performed on an RDF-based multi-model that relies on the recent ISO standard ICDD (ISO 21597). ICDD interlinks information on a sub-document identifier level, based on OWL. It is aimed at the industry in that it adds a layer of Linked Data to documentation formats that are still widely used in practice: IFC, spreadsheets, imagery etc. Therefore, it is considered a tuned use case for comparing these different RDF query languages.

Automatic Reassembly of Fragments for Restoration of Heritage Site Structures

Abstract: A major bottleneck activity in the process of restoration of Heritage Structures is the reassembly of its fragments. Computer-aided reassembly could assist in finding the relation between them thereby reducing time, manpower and potential degradation to fragile fragments. Using geometric compatibility between the adjacent fragments as the central idea, a reassembly framework for a three-dimensional shell is proposed as a logical extension of the twodimensional framework. Edges are extracted as polygons and relevant features are computed at each of its vertices. Sequences of the match for two fragments in the feature space are found using a modified version of Smith-Waterman Algorithm. Each match is assessed using a connectivity score. The final choice of best match is left to the user by displaying the resultant assembled fragments of prospective candidates along with the score. After pairwise matching, the global reassembly is done through a clustering-based method. This framework can handle fragments even with curved edges which can be reasonably approximated by a set of edges. We verify the methodology using a simulated dataset for both 2D pieces and a shattered 3D

Semantic query languages for knowledge-based web services in a construction context

Abstract: Since the early 2000s, different frameworks were set up to enable web-based collaboration in building projects. Unfortunately, none of these initiatives was granted a long life. Recently, however, the use of web technologies in the building industry has been gaining momentum again, considered some promising technologies for reaching a more interoperable BIM practice. Specifically, this relates to (1) Linked Data and Semantic Web technologies, and (2) cloud-based applications. In order to combine these into a network of interlinked applications and datastores, an agreed-upon mechanism for automatic communication and data retrieval needs to be used. Apart from the W3C standard SPARQL, often considered too high a threshold for developers to implement, there are some recent GraphQL-based solutions that simplify the querying process and its implementation into web services. In this paper, we review two recent open source technologies based on GraphQL, that enable to query Linked Data on the web: GraphQL-LD and HyperGraphQL.

A Systematic Review of Digital Technology Adoption in Off-Site Construction: Current Status and Future Direction towards Industry 4.0

Abstract: Off-site construction (OSC) is known as an efficient construction method that could save time and cost, reduce waste of resources, and improve the overall productivity of projects. Coupled with digital technologies associated with the Industry 4.0 concept, OSC can offer a higher rate of productivity and safety. While there is a rich literature focusing on both OSC and Industry 4.0, the implementation of associated digital technologies in the OSC context has not been fully evaluated. This paper intends to evaluate the current literature of digital technology applications in OSC. Scientometric analyses and a systematic review were carried out evaluating fifteen typical digital technologies adopted by OSC projects, including building information modelling (BIM), radio frequency identification devices (RFID), global positioning systems (GPS), the Internet of Things (IoT), geographic information systems (GIS), sensors, augmented reality (AR), virtual reality (VR), photogrammetry, laser scanning, artificial intelligence (AI), 3D printing, robotics, big data, and blockchain. This review formulates a clear picture of the current practice of these digital technologies and summarizes the main area of application and limitations of each technology when utilized in OSC. The review also points out their potential and how they can be better adopted to improve OSC practice in the future.

Precast supply chain management in off-site construction: A critical literature review

Abstract: Off-site construction is a rising topic in both academic research and industrial applications because of its potential to bring about high-level of industrialization, environmental benefits, and sustainability in the built environment. Precast supply chain, as a vital connection between construction sites and off-site plants, is the focus of many recent studies. While these studies have greatly advanced precast supply chain management (PSCM), a critical analysis to summarize the recent research, to identify research gaps, and to inform future research needs is largely missing in the field of precast supply chain management. The overarching goal of this paper is to create a taxonomy to properly classify existing studies in precast supply chain management so as to reveal research gaps and suggest future research opportunities. The specific tasks in this review project include: (1) conducting bibliographic categorizations with regard to journals, years and geographic distributions of publications; (2) identifying the citation correlations and formulating the keyword connection networks; (3) classifying the literature based on research topics and highlighting the state of the art pertaining to each subtopic. The in-depth analysis shows that the studies on precast production are dominant in the PSCM domain. The major research approaches used in existing studies include the genetic algorithm, simulation, RFID (Radio Frequency Identification), and BIM (Building Information Modeling). At last, the possible future research focuses are highlighted, such as dynamic disturbances management, smart precast supply chain, coordination among participants, simultaneously optimizing scheduling and resource allocation.

Dynamic transportation planning for prefabricated component supply chain

Abstract: Prefabricated construction concerns off-site production, multi-mode transportation and on-site installation of the prefabricated components, which are interdependent and dynamically interactive, so coordination among the multiple stages along the prefabricated component supply chain (PCSC) is indispensable. This study aims to solve the dynamic transportation planning problem for the PCSC by addressing the interdependency, dynamic interaction and coordination among the multiple stages and different objectives of the stakeholders.,The PCSC is analyzed and then the formulation for the dynamic transportation planning problem is developed based on the just-in-time (JIT) strategy. The particle swarm optimization (PSO) algorithm is applied to solve the dynamic optimization problem.,The proposed dynamic transportation planning method for the PCSC regarding component supplier selection, transportation planning for means, routes and schedule, site layout planning and transportation plan adjustment is able to facilitate coordination among the multiple stages by addressing their interdependencies and dynamic interactions, as well as different economic objectives of the stakeholders such as suppliers or the contractor.,The study helps to achieve the advantages of prefabricated construction by prompting coordination among multiple stages of the PCSC by realizing different benefits of the stakeholders. In addition, it provides the stakeholders with the competitive bidding prices and the evaluation data for the bids quote. Meanwhile, it contributes to the domain knowledge of the PCSC management with regard to the viewpoint of coordination and integration of multiple stages rather than only one stage as well as the dynamic optimization model based on the JIT strategy and the PSO algorithm.

Comparative geometrical accuracy investigations of hand-held 3d scanning systems – an update

Abstract: . Hand-held 3D scanning systems are increasingly available on the market from several system manufacturers. These systems are deployed for 3D recording of objects with different size in diverse applications, such as industrial reverse engineering, and documentation of museum exhibits etc. Typical measurement distances range from 0.5 m to 4.5 m. Although they are often easy-to-use, the geometric performance of these systems, especially the precision and accuracy, are not well known to many users. First geometrical investigations of a variety of diverse hand-held 3D scanning systems were already carried out by the Photogrammetry & Laser Scanning Lab of the HafenCity University Hamburg (HCU Hamburg) in cooperation with two other universities in 2016. To obtain more information about the accuracy behaviour of the latest generation of hand-held 3D scanning systems, HCU Hamburg conducted further comparative geometrical investigations using structured light systems with speckle pattern (Artec Spider, Mantis Vision PocketScan 3D, Mantis Vision F5-SR, Mantis Vision F5-B, and Mantis Vision F6), and photogrammetric systems (Creaform HandySCAN 700 and Shining FreeScan X7). In the framework of these comparative investigations geometrically stable reference bodies were used. The appropriate reference data was acquired by measurements with two structured light projection systems (AICON smartSCAN and GOM ATOS I 2M). The comprehensive test results of the different test scenarios are presented and critically discussed in this contribution.

Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimization

Abstract: We tackle the image reassembly problem with wide space between the fragments, in such a way that the patterns and colors continuity is mostly unusable. The spacing emulates the erosion of which the archaeological fragments suffer. We crop-square the fragments borders to compel our algorithm to learn from the content of the fragments. We also complicate the image reassembly by removing fragments and adding pieces from other sources. We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions. In this paper, we notably investigate the effect of branch-cut in the graph of reassemblies. We also provide a comparison with the literature, solve complex images reassemblies, explore at length the dataset, and propose a new metric that suits its specificities. Keywords: image reassembly, jigsaw puzzle, deep learning, graph, branch-cut, cultural heritage