Burcu Akinci

A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure

Visual inspection of civil infrastructure is essential for condition assessment.We focus on concrete bridges, tunnels, underground pipes, and asphalt pavements.Accordingly, we review the latest computer vision based defect detection methods.Using computer vision most relevant types of defects can be automatically detected.Automatic defect properties retrieval and assessment has not been achieved yet. To ensure the safety and the serviceability of civil infrastructure it is essential to visually inspect and assess its physical and functional condition. This review paper presents the current state of practice of assessing the visual condition of vertical and horizontal civil infrastructure; in particular of reinforced concrete bridges, precast concrete tunnels, underground concrete pipes, and asphalt pavements. Since the rate of creation and deployment of computer vision methods for civil engineering applications has been exponentially increasing, the main part of the paper presents a comprehensive synthesis of the state of the art in computer vision based defect detection and condition assessment related to concrete and asphalt civil infrastructure. Finally, the current achievements and limitations of existing methods as well as open research challenges are outlined to assist both the civil engineering and the computer science research community in setting an agenda for future research.

Life-cycle data management of engineered-to-order components using radio frequency identification

Management of engineered-to-order (ETO) components and their related information is a challenging task due to the complexity of information and its flow. Different information items are generated, accessed and exchanged between different organizations and they must continually flow through design, production, construction, and operations and maintenance. Current manual and labor-intensive methods are inefficient; as a result, information is frequently incomplete, inaccurate or unavailable during the life-cycle of a facility. This paper provides a vision of intelligent components, which know their identities, locations and history, and communicate this information to their environments. It proposes streamlining information flow through supply chains by utilizing radio frequency identification (RFID) technology. To explore the technical feasibility of intelligent components, component-related information flow patterns in ETO supply chains were identified and analyzed. Requirements analysis and corresponding technology deployment and testing were performed for three types of ETO components through different life-cycle phases. These experiments demonstrated that it is technically feasible to have intelligent components in construction supply chains by using RFID technology; that status information can be collected automatically; and that maintenance information can be stored and retrieved during the service life of a facility.

Characterization of Laser Scanners and Algorithms for Detecting Flatness Defects on Concrete Surfaces

In many construction and infrastructure management projects, it is important to ensure the flatness of concrete surfaces. Inspectors assess the quality of flat surface construction by checking whether a surface deviates from perfectly flat by more than a specified tolerance. Current flatness assessment methods, such as using a straightedge or shape profiler, are limited in the speed or density of their measurements. Laser scanners are general-purpose instruments for densely and accurately measuring three-dimensional shapes. In this paper, we show how laser scanners can be effectively used to assess surface flatness. Specifically, we formalize, implement, and validate three algorithms for processing laser-scanned data to detect surface flatness deviations. Since different scanners and algorithms can perform differently, we define an evaluation framework for objectively evaluating the performance of different algorithms and scanners. Using this framework, we analyze and compare the performance of the three algorithms using data from three laser scanners. The results show that it is possible to detect surface flatness defects as small as 3 cm across and 1 mm thick from a distance of 20 m.

Utilizing Radio-Frequency Identification on Precast Concrete Components - Supplier's Perspective

Precast concrete material suppliers are responsible for the components that they manufacture from casting until up to 25 years after installation. To effectively manage the production and storage at a the production facility, to streamline the construction process and to quickly repair a component should there be a problem, information about components must be readily available and updated throughout the 25 year life cycle. Currently, suppliers use barcodes to track precast components and paper-based documents to store information about them. These approaches are time-consuming and error prone. Suppliers also face the problem of not finding the right information in a timely manner. This paper discusses the utilization of radio frequency identification technology (RFID) for tracking precast concrete components and their historical information from fabrication to post-construction. RFID is an automatic identification technology that uses memory chips attached/embedded to objects to transmit data about them. Our discussion revolves around one use case that we developed describing the current component tracking approach and the proposed approach utilization of RFID technology from a large-scale precast manufacturer/erector’s perspective. We conclude with an assessment of benefits and limitations of the proposed utilization of RFID system for tracking precast concrete materials.

An ontological engineering approach for integrating CAD and GIS in support of infrastructure management

Infrastructure managers rely on capabilities of Computer-Aided Design (CAD) and Geospatial Information Systems (GIS) for making decisions during the implementation of engineering tasks. However, despite the fact that there are domains in which both CAD and GIS are used and despite the overlaps between the data and operations they support, CAD and GIS have been developed independently over many years resulting in platforms that are not easily integrated. Engineers in infrastructure management must gain knowledge and skills in both CAD and GIS to perform infrastructure management tasks. In most cases, they need to manually transfer data queried from one system to another, due to the heterogeneous nature, such as data and operations heterogeneity, of CAD and GIS. Interoperability is seen as a solution to overcome the problems associated with heterogeneous environments and may occur at different levels and for different purposes. In this paper, we discuss the need for semantic interoperability between GIS and CAD and present an ontological engineering methodology as a possible means to enable this interoperability. This methodology uses ontological-based techniques for resolving the semantic differences in queries requiring CAD and GIS data and operations.

A Comparative Analysis of Depth-Discontinuity and Mixed-Pixel Detection Algorithms

Laser scanner measurements are corrupted by noise and artifacts that can undermine the performance of registration, segmentation, surface reconstruction, recognition, and other algorithms operating on the data. While much research has addressed laser scanner noise models, comparatively little is known about other artifacts, such as the mixed pixel effect, color-dependent range biases, and specular reflection effects. This paper focuses on the mixed pixel effect and the related challenge of detecting depth discontinuities in 3D data. While a number of algorithms have been proposed for detecting mixed pixels and depth discontinuities, there is no consensus on how well such algorithms perform or which algorithm performs best. This paper presents a comparative analysis of five mixed-pixel/discontinuity detection algorithms on real data sets. We find that an algorithm based on the surface normal angle has the best overall performance, but that no algorithm performs exceptionally well. Factors influencing algorithm performance are also discussed.

Using laser scanners for modeling and analysis in architecture, engineering, and construction

Laser scanners are rapidly gaining acceptance as a tool for three dimensional (3D) modeling and analysis in the architecture, engineering, and construction (AEC) domain. Since 2001, our cross-disciplinary research team has been developing new methods for analyzing and modeling laser scanner data, with an emphasis on applications in the AEC domain. This paper provides an overview of our groups recent research efforts. Our work includes improving our understanding of the low-level aspects of laser scanner data, using comparison methods to analyze laser scanner data and derived models, and developing modeling and recognition algorithms to support the automatic creation of building models from laser scan data.

An Overview of Approaches for Utilizing RFID in Construction Industry

Construction industry has dynamic and uncontrolled environments, where tracking components/materials and accessing related information are challenging tasks. Failure in effectively tracking components/materials and in accessing the related information on demand results in schedule delays and additional labor costs. Due to long read ranges, radio frequency identification (RFID) technology holds the potential for enabling automated tracking of components/materials in dynamic and uncontrolled environments. Also, on-board storage capacity of RFID allows for making information related to a component of a bulk of material readily available to the persons who are handling components and materials. This paper provides an overview of possible applications for RFID use and describes the field tests conducted in several research studies on utilization of RFID in construction industry. The field tests described were performed for tracking pipe spools and precast components during delivery and receipt, tracking precast components in a manufacturers storage yard, tracking tools, locating materials and transferring material information to construction site. The results of those tests demonstrated that despite some limitations of the current technology, active UHF RFID meets the needs for the selected cases provided that some reasoning mechanisms are developed and implemented for data cleaning and processing purposes.

Sensing and Field Data Capture for Construction and Facility Operations

Collection of accurate, complete, and reliable field data is not only essential for active management of construction projects involving various tasks, such as material tracking, progress monitoring, and quality assurance, but also for facility and infrastructure management during the service lives of facilities and infrastructure systems. Limitations of current manual data collection approaches in terms of speed, completeness, and accuracy render these approaches ineffective for decision support in highly dynamic environments, such as construction and facility operations. Hence, a need exists to leverage the advancements in automated field data capture technologies to support decisions during construction and facility operations. These technologies can be used not only for acquiring data about the various operations being carried out at construction and facility sites but also for gathering information about the context surrounding these operations and monitoring the workflow of activities during these o...

Efficient and Effective Quality Assessment of As-Is Building Information Models and 3D Laser-Scanned Data

Documenting as-is conditions of buildings using 3D laser scanning and Building Information Modeling (BIM) technology is being adopted as a practice for enhancing effective management of facilities. Many service providers generate as-is BIMs based on laser-scanned data. It is necessary to conduct timely and comprehensive assessments of the quality of the laser-scanned data and the as-is BIM generated from the data before using them for making decisions about facilities. This paper presents the data and as-is BIM QA requirements of civil engineers and demonstrates that the required QA information can be derived by analyzing the patterns in the deviations between the data and the as-is BIMs. We formalized this idea as a deviation analysis method for efficient and effective QA of the data and as-is BIMs. A preliminary evaluation of the results obtained through this approach show the potential of this method for achieving timely, detailed, comprehensive, and quantitative assessment of various types of data/model quality issues.