Toward automated generation of parametric BIMs based on hybrid video and laser scanning data

Only very few constructed facilities today have a complete record of as-built information. Despite the growing use of Building Information Modelling and the improvement in as-built records, several more years will be required before guidelines that require as-built data modelling will be implemented for the majority of constructed facilities, and this will still not address the stock of existing buildings. A technical solution for scanning buildings and compiling Building Information Models is needed. However, this is a multidisciplinary problem, requiring expertise in scanning, computer vision and videogrammetry, machine learning, and parametric object modelling. This paper outlines the technical approach proposed by a consortium of researchers that has gathered to tackle the ambitious goal of automating as-built modelling as far as possible. The top level framework of the proposed solution is presented, and each process, input and output is explained, along with the steps needed to validate them. Preliminary experiments on the earlier stages (i.e. processes) of the framework proposed are conducted and results are shown; the work toward implementation of the remainder is ongoing.

Visual pattern recognition models for remote sensing of civil infrastructure

As-built models have been proven useful in many project-related applications, such as progress monitoring and quality control. However, they are not widely produced in most projects because a lot of effort is still necessary to manually convert remote sensing data from photogrammetry or laser scanning to an as-built model. In order to automate the generation of as-built models, the first and fundamental step is to automatically recognize infrastructure-related elements from the remote sensing data. This paper outlines a framework for creating visual pattern recognition models that can automate the recognition of infrastructure-related elements based on their visual features. The framework starts with identifying the visual characteristics of infrastructure element types and numerically representing them using image analysis tools. The derived representations, along with their relative topology, are then used to form element visual pattern recognition (VPR) models. So far, the VPR models of four infrastructure-related elements have been created using the framework. The high recognition performance of these models validates the effectiveness of the framework in recognizing infrastructure-related elements.

Visual Pattern Recognition Models for Remote Sensing of Civil Infrastructure

As-built models have been proven useful in many project-related applications, such as progress monitoring and quality control. However, they are not widely produced in most projects because a lot of effort is still necessary to manually convert remote sensing data from photogrammetry or laser scanning to an as-built model. In order to automate the generation of as-built models, the first and fundamental step is to automatically recognize infrastructure-related elements from the remote sensing data. This paper outlines a framework for creating visual pattern recognition models that can automate the recognition of infrastructure-related elements based on their visual features. The framework starts with identifying the visual characteristics of infrastructure element types and numerically representing them using image analysis tools. The derived representations, along with their relative topology, are then used to form element visual pattern recognition (VPR) models. So far, the VPR models of four infrastructure-related elements have been created using the framework. The high recognition performance of these models validates the effectiveness of the framework in recognizing infrastructure-related elements.

Innovative Stereo Vision-Based Approach to Generate Dense Depth Map of Transportation Infrastructure

Three-dimensional (3-D) spatial data of a transportation infrastructure contain useful information for civil engineering applications, including as-built documentation, on-site safety enhancements, and progress monitoring. Several techniques have been developed for acquiring 3-D point coordinates of infrastructure, such as laser scanning. Although the method yields accurate results, the high device costs and human effort required render the process infeasible for generic applications in the construction industry. A quick and reliable approach, which is based on the principles of stereo vision, is proposed for generating a depth map of an infrastructure. Initially, two images are captured by two similar stereo cameras at the scene of the infrastructure. A Harris feature detector is used to extract feature points from the first view, and an innovative adaptive window-matching technique is used to compute feature point correspondences in the second view. A robust algorithm computes the nonfeature point correspondences. Thus, the correspondences of all the points in the scene are obtained. After all correspondences have been obtained, the geometric principles of stereo vision are used to generate a dense depth map of the scene. The proposed algorithm has been tested on several data sets, and results illustrate its potential for stereo correspondence and depth map generation.

Comparison of Image-Based and Time-of-Flight-Based Technologies for 3D Reconstruction of Infrastructure

Image-based (i.e., photo/videogrammetry) and time-of-flight-based (i.e., laser scanning) technologies are typically used to collect spatial data of infrastructure. In order to help architecture, engineering, and construction (AEC) industries make cost-effective decisions in selecting between these two technologies with respect to their settings, this paper makes an attempt to measure the accuracy, quality, time efficiency, and cost of applying image-based and time-of-flight-based technologies to conduct as-built 3D reconstruction of infrastructure. In this paper, a novel comparison method is proposed, and preliminary experiments are conducted. The results reveal that if the accuracy and quality level desired for a particular application is not high (i.e., error < 10 cm, and completeness rate > 80%), image-based technologies constitute a good alternative for time-of-flight-based technologies and significantly reduce the time and cost needed for collecting the data on site.

Comparison of Image-Based and Time-of-Flight-Based Technologies for Three-Dimensional Reconstruction of Infrastructure

Image-based (i.e., photo/videogrammetry) and time-of-flight-based (i.e., laser scanning) technologies are typically used to collect spatial data of infrastructure. In order to help architecture, engineering, and construction (AEC) industries make cost-effective decisions in selecting between these two technologies with respect to their settings, this paper makes an attempt to measure the accuracy, quality, time efficiency, and cost of applying image-based and time-of-flight-based technologies to conduct as-built 3D reconstruction of infrastructure. In this paper, a novel comparison method is proposed, and preliminary experiments are conducted. The results reveal that if the accuracy and quality level desired for a particular application is not high (i.e., error < 10 cm, and completeness rate > 80%), image-based technologies constitute a good alternative for time-of-flight-based technologies and significantly reduce the time and cost needed for collecting the data on site.

Innovative Stereo Vision-Based Approach to Generate Dense Depth Map of Transportation Infrastructure

Three-dimensional (3-D) spatial data of a transportation infrastructure contain useful information for civil engineering applications, including as-built documentation, on-site safety enhancements, and progress monitoring. Several techniques have been developed for acquiring 3-D point coordinates of infrastructure, such as laser scanning. Although the method yields accurate results, the high device costs and human effort required render the process infeasible for generic applications in the construction industry. A quick and reliable approach, which is based on the principles of stereo vision, is proposed for generating a depth map of an infrastructure. Initially, two images are captured by two similar stereo cameras at the scene of the infrastructure. A Harris feature detector is used to extract feature points from the first view, and an innovative adaptive window-matching technique is used to compute feature point correspondences in the second view. A robust algorithm computes the nonfeature point correspondences. Thus, the correspondences of all the points in the scene are obtained. After all correspondences have been obtained, the geometric principles of stereo vision are used to generate a dense depth map of the scene. The proposed algorithm has been tested on several data sets, and results illustrate its potential for stereo correspondence and depth map generation.

Methods of monitoring of metro lining in Prague

There are several reasons for monitoring of underground structures and they have already been discussed many times, e.g. from the view of ageing or state after accidental event like flooding of Prague metro in 2002. Monitoring of Prague metro is realized in the framework of international research project sponsored by ESF-S3T. The monitoring methods used in Prague are either classical one or new or developing one. The reason for different monitoring methods is the different precision of each method and also for cross-checking between them and their evaluation. Namely we use convergence, tiltmetres, crackmetres, geophysical methods, laser scanning, computer vision and finally installation of MEMS monitoring devices. In the paper more details of each method and obtained results will be presented. The monitoring methods are complemented by wireless data collection and transfer for real-time monitoring. © 2012 Taylor & Francis Group.

The development of a scanning strategy for the manufacture of porous biomaterials by selective laser melting.

Porous structures are used in orthopaedics to promote biological fixation between metal implant and host bone. In order to achieve rapid and high volumes of bone ingrowth the structures must be manufactured from a biocompatible material and possess high interconnected porosities, pore sizes between 100 and 700 microm and mechanical strengths that withstand the anticipated biomechanical loads. The challenge is to develop a manufacturing process that can cost effectively produce structures that meet these requirements. The research presented in this paper describes the development of a 'beam overlap' technique for manufacturing porous structures in commercially pure titanium using the Selective Laser Melting (SLM) rapid manufacturing technique. A candidate bone ingrowth structure (71% porosity, 440 microm mean pore diameter and 70 MPa compression strength) was produced and used to manufacture a final shape orthopaedic component. These results suggest that SLM beam overlap is a promising technique for manufacturing final shape functional bone ingrowth materials.

Laser microstructuring of Si surfaces for low-threshold field-electron emission

Dense arrays of high aspect ratio Si micro-pyramids have been formed by cumulative high intensity laser irradiation of doped Si wafers in an SF6 environment. A comparative study using nanosecond (XeCl, 308 nm) and femtosecond (Ti: Sapphire, 800 nm and KrF, 248 nm) laser pulses has been performed in this work. The influence of pulse duration and ambient gas pressure (SF6) is also presented. Scanning electron microscopy has shown that upon laser irradiation conical features appear on the Si surface in a rather homogenous distribution and with a spontaneous self alignment into arrays. Their lowest tip diameter is 800 nm; while their height reaches up to 90 mum. Secondary tip decoration appears on the surface of the formed spikes. Areas of 2 X 2 mm(2) covered with Si cones have been tested as cold cathode field emitters. After several conditioning cycles, the field emission threshold for the studied Si tips is as low as 2 V/mum, with an emission current of 10(-3) A/cm(2) at 4 V/mum. Even though these structures have smaller aspect ratios than good quality carbon nanotubes, their field emission properties are similar. The simple and direct formation of field emission Si arrays over small pre-selected areas by laser irradiation could lead to a novel approach for the development of electron sources. (C) 2003 Elsevier B.V. All rights reserved.

On the percussion drilling of SI using a 20W MOPA based YB fiber laser

A study on the nanosecond fiber laser interaction with silicon was performed experimentally for the generation of percussion drilled holes. Single pulse ablation experiments were carried out on mono crystalline 650μm thick Si wafers. Changes of the mass removal mechanism were investigated by varying laser fluence up to 68 J/cm2 and pulse duration from 50 ns to 200 ns. Hole width and depth were measured and surface morphology were studied using scanning electron microscopy (SEM) and optical interferometric profilometry (Veeco NT3300). High speed photography was also used to examine laser generated plasma expansion rates. The material removal rate was found to be influenced by the pulse energy, full pulse duration and pulse peak power. Single pulse ablation depth of 4.42 μm was achieved using a 200 ns pulse of 13.3 J/cm 2, giving a maximum machining efficiency of 31.86 μm per mJ. Holes drilled with an increased fluence but fixed pulse length were deeper, exhibited low recast, but were less efficient than those produced at a lower fluence. The increased peak power in this case led to high levels of plasma and vapour production. The expansion of which, results in a strong driving recoil force, an increase in the rate and volume of melt ejection, and cleaner hole formation. The experimental findings show that for efficient drilling at a given energy, a longer, lower peak power pulse is more desirable than a high peak power short pulse.