Explore chapters and articles related to this topic
BIM registration methods for mobile augmented reality-based inspection
Published in Symeon E. Christodoulou, Raimar Scherer, eWork and eBusiness in Architecture, Engineering and Construction, 2017
As described, currently, there are no efficient mobile AR solutions for on-site inspections. Similar systems in literature present limitations as they either use markers, or they restrict the user to operate from specific locations. Other methods for marker-less AR have been introduced in computer vision literature but have not yet been tested with and/or on construction sites. This paper presents an evaluation of the different methods that could be, potentially, used for a marker-less BIM based mobile AR solution for on-site inspections. The methods evaluated can be divided into three groups; first the group that uses only 2D data, second the group that uses monocular SLAM methods, in which they process 2D data and extract 3D and motion data and finally, the group that uses RGBD devices. Experiments have shown that neither the first group nor the second group of methods could efficiently provide a robust AR solution for on-site inspections. However, the use of RGBD devices shows significant potential for AR applications in the construction arena. Compared to the Kinect sensor, Project Tango offers a more robust motion tracking and although the 3D reconstruction is noisier than Kinect, it can capture larger scenes and operates more quickly, providing real time advantages for AR inspection implementations required on busy construction sites.
Participatory sensing for community engagement with HBIM
Published in Yusuf Arayici, John Counsell, Lamine Mahdjoubi, Gehan Nagy, Soheir Hawas, Khaled Dewidar, Heritage Building Information Modelling, 2017
Deeming environmental factors, such as pollution, there is a need to capture the detailed 3D data that defines the geometry and can then be used for 3D georeferencing, and to create visualisable 3D models (an analytic process that can add semantic data to the geometry). The challenges of the 3D model are discussed in Chapter 3, but the 3D model does offer opportunities for wider virtual interaction, and so may form a key ingredient of community and citizen engagement, particularly asynchronous or off-site. Google supply their Project Tango, currently an Android tablet, to developers with the intent of achieving real-time sensing of 3D environments via future smartphones (Tango 2016). This is one of a number of emerging low-cost 3D scanning technologies. The Structure Sensor (Structure 2016) is a 3D scanner attachment for smartphones and tablets. Quanergy (Spar 3D 2016) have launched a prototype solid-state low-cost Lidar attachment.
Enhancing smart shop floor management with ubiquitous augmented reality
Published in International Journal of Production Research, 2019
X. Wang, A.W.W. Yew, S.K. Ong, A.Y.C. Nee
An Android application has been developed for the tablet to display and interact with the AR interfaces in the shop floor. It uses the Project Tango (Marder-Eppstein 2016) software platform to perform simultaneous localisation and mapping (SLAM), which tracks the pose of the viewing device by building up a 3D map of the physical features of the environment as they are detected by the camera on the device and simultaneously estimating the pose of the device with respect to these features. In addition, fiducial marker tracking (Fiala 2005) is used to anchor the 3D map of the physical features to pre-determined locations in the shop floor. This allows the pose estimated by the SLAM algorithm to be expressed with respect to a fiducial marker, and key locations in the shop floor, such as the locations of machining resources and inventory bins, to be expressed in six degrees-of-freedom with respect to the fiducial markers. Thus, the device can track its location with respect to a fixed shop floor coordinate system. Continuous tracking with respect to the shop floor is achieved, even when a fiducial marker is not detected, through the SLAM algorithm as long as the pose of the device with the shop floor has been previously established by tracking a fiducial marker.
A novel method of combined interval analysis and homotopy continuation in indoor building reconstruction
Published in Engineering Optimization, 2019
Ali Jamali, Francesc Antón Castro, Darka Mioc
A growing interest in indoor building surveying has been observed in the GIS and BIM research communities (Isikdag and Underwood 2010). There are five approaches that seem to be suitable for indoor surveying: One approach is laser scanning, which is expensive and time consuming, and requires a considerable modelling effort to fit sections of the surveyed point clouds to basic features such as walls. This results in extensive manual work after data collection and there is no easy way to integrate individual scan results with the model of a complete complex building.Traditional surveying with a total station or equivalent is also possible, but the conversion of captured data points into a building model is complex.The third approach, using a light rangefinder which integrates azimuth (from a digital compass) and inclination, appears to be the most feasible for surveying an indoor building environment, although it has a lower level of accuracy than total station and laser scanner-based surveying approaches (Jamali et al. 2017).A fourth approach, based on a photogrammetric technique, uses non-calibrated, non-metric cameras to extract 3D information from photographs. For indoor surveying, it is as simple as taking pictures. In addition, images can be used for texture extraction: textures can be attached to walls, floors and ceilings in the model, which increases the realism of visualization. 3D reconstruction based on photogrammetry is not used, as it is outside the scope of this research.A fifth approach, project Tango, introduced by Google, integrates a motion-tracking camera with an infrared 3D depth sensor. One of the limitations of this method is that it has problems with data collection in dark, reflective and shiny environments (Diakité and Zlatanova 2016). However, any measurement device must be calibrated to control the uncertainties. The formal definition of calibration by the International Bureau of Weights and Measures (BIPM) is:Operation that, under specified conditions, in a first step, establishes a relation between the quantity values with measurement uncertainties provided by measurement standards and corresponding indications with associated measurement uncertainties (of the calibrated instrument or secondary standard) and, in a second step, uses this information to establish a relation for obtaining a measurement result from an indication. (Clifford 1985)