A Biomimicry approach to automating visual road surveys
0
Citation
0
Reference
20
Related Paper
Abstract:
Road surveys that quickly and efficiently identify features and assess their condition are keystones of an effective road asset management system. Manual visual surveys are subjective and expensive, but it appears that no software package can be flexible enough to cater to all survey needs. However, nature suggests that a generic system design is possible, a parallel being the way in which animals based on the quadruped design fill a wide range of ecological niches. This paper presents a generic design whose common design components are image acquisition, image processing, feature recognition by artificial neural networks, and condition assessment by expert systems. The system can accept either real time camera feed, or video/DVD recordings made by survey vehicles. Biomimicry principles are outlined to guide the designs application to produce a survey system for a given road feature, such as line-markings and road edges. A road guide post survey is presented as a case study.Keywords:
Feature (linguistics)
Biomimetics
Cite
Inspection is crucial to the management of ageing infrastructure. Visual information on structures is regularly collected but very little work exists on its organised and quantitative analysis, even though image processing can significantly enhance these inspection processes and transfer real financial and safety benefits to the managers, owners and users. Additionally, new opportunities exist in the fast evolving sectors of wind and wave energy to add value to image-based inspection techniques.
This book is a first for structural engineers and inspectors who wish to harness the full potential of cameras as an inspection tool. It is particularly directed to the inspection of offshore and marine structures and the application of image-based methods in underwater inspections. It outlines a set of best practice guidelines for obtaining imagery, then the fundamentals of image processing are covered along with several image processing techniques which can be used to assess multiple damage forms: crack detection, corrosion detection, and depth analysis of marine growth on offshore structures. The book provides benchmark performance measures for these techniques under various visibility conditions using an image repository which will help inspectors to envisage the effectiveness of the techniques when applied. MATLAB® scripts and access to the underwater image repository are included so readers can run these techniques themselves.
Practising engineers and managers of infrastructure assets are guided in image processing based inspection. Researchers can use this book as a primer, and it also suits advanced graduate courses in infrastructure management or on applied image processing.
Cite
Citations (2)
Availability and accuracy of building information is critical for a variety of tasks during the lifecycle of facilities. Currently Building information modelling (BIM) is mostly used for design and construction. When the as-designed BIM is not updated with the construction changes, it can contain inaccurate information. A way to collect the as-is conditions is to capture how a facility is changing over time. Vision-based data capture technologies, namely laser scanners and cameras, are being widely used. However, occluded components and the challenges associated with reverse engineering of complex construction objects can result in incomplete as-built data. This paper presents a case study, in which a laser scanner and a camera were used to capture the construction history and develop a more complete as-built BIM. A progressive approach is followed to mitigate challenges associated with cluttered construction data. Components/features occluded in any captured scans were reconsidered throughout a continuous planning and data capturing process. Other sources such as as-designed documents are supplemented to as-built data for extraction of information items required for the as-built BIM. The discussions include more ample description of the background research and the addressed problem, followed by detailed description of this study's approach. Lessons learned, findings and recommendations for future research are summarized.
Building Information Modeling
Laser Scanning
Information model
Cite
Citations (44)
Development of driver assistance and automation systems relies on domain-specific formats for the
geometrical and logical representation of road networks in simulation environments. The trend to simulate real world
urban environments leads to increasing demands for such data which cannot be derived easily from
cadastral or open source geodata. In contrast, specific surveying directly into these domain-specific formats
quickly becomes time and cost consuming. The DLR in partnership with OEMs developed guidelines for
simplified surveying into an intermediate, discrete geodata format which meets the requirements of both the
governmental and the driving simulation domain. From this intermediate format specific simulation formats can
be derived automatically through the developed processing toolchain. The feasibility and effort of this approach
is examined in an urban use case in Germany covering the dedicated surveying of road sections followed by
automatic processing into OpenDRIVE.
Toolchain
Executable
Theodolite
Cite
Citations (0)
Central to efficient highway management and navigation systems is an accurate inventory of physical road attributes and properties. Development of such an inventory has been simplified by the advent of automated data collection utilizing vehicles equipped with the capability of geographical positioning by satellite and the support of intelligent geographical systems. Experience has shown that in the urban environment, attribute capture by video and post survey processing supported the addition of 7,500 attribute items per day into an adequately referenced highway network management database. The potential information content of the data is extensive, not only to the highway manager, but to driver information system providers, and other data users, assuming adequate flexible extraction, analysis, and exploitation tools are available. These tools should enable the user to query the database both through a geographical user interface and via alphanumeric textual queries to meet differing user requirements. This paper will describe a set of proven tools developed using artificial intelligence methods for extraction and analysis of data for highway management purposes. Examples include tools for management of street lighting and signing installations, pavement condition monitoring, of the integration of these and other highway data management tools, and the future potential of configuring the data for use in traffic telematics.
Alphanumeric
Telematics
Interface (matter)
Cite
Citations (0)
Digital road images have many applications for the management of road networks. With the rapid advancements in technology and the wide range of applications of digital images currently available, it is useful to create a set of standard specifications for the collection of digital images. This report reviews some of the current practices of road authorities and provides recommendations for the development of standard specifications.
Digital Imaging
Cite
Citations (0)
Leverage (statistics)
Cite
Citations (252)
Construction site safety
Cite
Citations (8)
Abstract. In this work, it is examined the 2D recognition and 3D modelling of concrete tunnel cracks, through visual cues. At the time being, the structural integrity inspection of large-scale infrastructures is mainly performed through visual observations by human inspectors, who identify structural defects, rate them and, then, categorize their severity. The described approach targets at minimum human intervention, for autonomous inspection of civil infrastructures. The shortfalls of existing approaches in crack assessment are being addressed by proposing a novel detection scheme. Although efforts have been made in the field, synergies among proposed techniques are still missing. The holistic approach of this paper exploits the state of the art techniques of pattern recognition and stereo-matching, in order to build accurate 3D crack models. The innovation lies in the hybrid approach for the CNN detector initialization, and the use of the modified census transformation for stereo matching along with a binary fusion of two state-of-the-art optimization schemes. The described approach manages to deal with images of harsh radiometry, along with severe radiometric differences in the stereo pair. The effectiveness of this workflow is evaluated on a real dataset gathered in highway and railway tunnels. What is promising is that the computer vision workflow described in this work can be transferred, with adaptations of course, to other infrastructure such as pipelines, bridges and large industrial facilities that are in the need of continuous state assessment during their operational life cycle.
Initialization
Cite
Citations (9)
Pavement Condition surveys are carried out periodically to gather information on pavement distresses that will guide decision-making for maintenance and preservation. Traditional methods involve manual pavement inspections which are time-consuming and subjective. In recent times, there has been a move towards automated methods of pavement condition assessment. The automated methods which comprise of acquiring pavement data with cameras and analyzing the images have several shortcomings, especially in the area of image analysis. A major problem is that most of the image processing algorithms are based on assumptions that may not work well under certain conditions. Therefore, there is a need for adaptive image processing methods that are robust under varying conditions. This study focused on the use of multi-resolution information-mining techniques with a computer vision approach to analyze pavement conditions. A vision-system which seeks to fully-automate the pavement condition survey process is also developed. With a user-friendly interface, geographic information system (GIS) integration and a vision system comprised of three main components; image acquisition, image retrieval and the output analysis and visualization component, this system will serve as the foundation for the future of fully-automated pavement distress surveys.
Pavement management
Component (thermodynamics)
Cite
Citations (0)
Tunnel inspection and asset management is typically a labour-intensive process where engineering judgement and experience is heavily relied upon to identify and assess tunnel condition over kilometres of homogeneous structures. Novel work flows and digital applications have been developed by the authors to create various smart image-based inspection and analysis tools that reduce the potential subjectivity and inconsistency of these inspections. This has resulted in significant improvements to existing tunnel inspection practices and structural health assessment. Current advances in image capture technology and computational processing power has enabled high integrity data to be easily captured, visualised and analysed. The work flows and tools developed take advantage of existing low-cost image capture hardware, open-source processing software and couples this with the creation of unique machine learning algorithms and analytics. Core innovations include: (i) use of low-cost photographic equipment for high quality imagery capture (ii) use of automated inspection vehicles for data capture (iii) Deep learning for automatic defect object recognition and defect classification (iv) Creation of immersive dashboards and 3D visualisations. This results in a suite of image based service offerings and deliverables, relevant to specific tunnel engineering issues and asset management aims. Thanks to deep learning, defect detection and asset condition metrics are automatically created, enabling: (i) the tunnel owner to gain greater insights into their asset resilience and operations, (ii) the tunnel engineer to focus on key issues aided by machine learning.
Cite
Citations (2)