Figure 4 - uploaded by Philip Greenhalgh
Content may be subject to copyright.
Source publication
We report on a deployment of the DAQRI SMART HELMET ™ (DSH) into an industrial environment. The deployment shows that data that was contextually filtered, categorised and displayed in relevant physical space yielded the greatest benefit. We describe those findings as well as how the embedded Intel ® RealSense ™ camera technology can further refine...
Citations
... By utilizing the Simultaneous Localization And Mapping (SLAM) on object tracking, markerless-based methods have been proposed. Mostly, they use active sensors acquiring a rich information of the target environment, such as a RGBD sensor (Macedo et al., 2013), a 3D rider sensor (Bosche et al., 2010), or a sensor-embedded system (Schall et al. 2009;Martin et al. 2015;Greenhalgh et al. 2016). These sensors are robust to the scale-ambiguity problem (Mur-Artal et al., 2017) commonly encountered in a monocular-based SALM, but it requires a heavy computation for the registration of dense point clouds in real-time application. ...
... Bosche et al. (2010) proposed an offline registration method which merges partial observations from a 3D radar sensor, into a global coordinate. Greenhalgh et al. (2016) developed a HMD-based system which displays a 3D CAD model at the current head position in real-time. These methods can capture a dense 3D information of the target environment but they require a special equipment, and a high performance computing system due to the registration between dense point clouds in the system coordinates and the CAD model. ...
The Mixed Reality (MR) has become a trend in industrial applications such as inspection and maintenance thanks to the benefit of technological advances in computer vision. Simultaneous Localization And Mapping (SLAM) is a key component of the MR system which augments the CAD model of a target object in the live stream. However, the existing SLAM-based systems rely on a manual handling or a marker-based registration between the model coordinate and the global coordinate. In this paper, we present a non-marker based registration method which automatically performs both the target object detection in the live stream and its initial 3D pose estimation. We exploit two Convolutional Neural Networks (CNNs) to align the CAD model in a global map, and to detect the target object in keyframes of the SLAM system. Since manual preparation of training data is very laborious, we also propose a data argumentation method for the industrial application. The data augmentation method generates a synthesized dataset consisting of pairs of the RGB image and the corresponding camera pose using the object's CAD model. Two CNNs for the object detection in keyframes and the initial pose estimation are trained with the synthesized dataset, respectively. Our result shows that this method can robustly find the target object's initial pose without a dense point cloud or other features detected by hand-crafted descriptors.
... For instance: 1) The spatial stream from several airborne lidar sensors must be integrated in real-time and analyzed interactively to manage forest fire, 2) The spatial stream of road traffic must be monitored in an online fashion to manage road traffic and identify speeding vehicles, 3) Citywide people flow must be analyzed in real-time to better manage the city resources, etc. These and other similar applications suffer from the traditional offline processing which cannot handle contin-(a) Road segment (b) Human face [3] (c) Indoor space [4] Fig. 1. Different types of 3D scanning uously arriving spatial stream in real-time. ...
... Nowadays Smart devices allow user to implement AR-based applications with mobility. Others head mounted displays like the Daqri Smart helmet and HoloLens are aiming to provide a mobile solution for the manufacturing and construction industry (Greenhalgh, et al , 2016). ...
Augmented Reality (AR) represents a viable and efficient approach for combining Virtual Reality with the real world. It also augments user’s perception of a real-world entity by inserting relevant digital information into the real environment and creating an environment where computer generated information is superimposed onto the user’s view of a real-world scene. The idea of Pervasive AR (PAR) adds context-awareness and continuity to the typical AR technology, thus providing continued assistance to the users. This paper is aimed at main drivers and barriers for the implementation of PAR within the field of Architecture, Engineering and Construction (AEC). A review of the literature was performed highlighting the main barriers and drivers for the implementation of PAR in the AEC sector, as well as possible applications of this technology. The literature review showed cost of technology, hardware issues and development of applications as the main barriers for implementing PAR. Whereas, error and cost reduction; and continued assistance were the main drivers of implementation. Although there are some barriers to overcome, the future implementation of PAR in the construction sector looks promising with possible applications of this technology in the AEC sector such as visualisation of spatial, drawing or technical information for designers, the jobsite workforce or marketing purposes.
... The ARToolKit was originally developed by ARToolWorks in 1999 and was bought by Daqri in 2015. Daqri [15] have since made the libraries open source giving a wider accessibility to developers. ARToolKit works though eclipse using the Android NDK and SDK. ...
Purpose
Construction cost management is one of the important processes that should be achieved effectively and accurately for successful project delivery. Modern-day construction cost management demands a high level of spatial skills. Augmented reality (AR) can potentially increase the stakeholders’ spatial skills as a supportive technology to traditional cost management tools and techniques. AR is a breakthrough technology that could considerably ease execution in various industries, but AR applicability in cost management has not been studied extensively. Thus, this study aims to explore the use of AR in construction cost management tools and techniques.
Design/methodology/approach
Data were collected using a qualitative approach consisting of two rounds of the Delphi technique. A total of 22 experts in the construction and information technology fields were interviewed using a purposive sampling technique. The manual content analysis helped analyse data.
Findings
The study identified AR features with the potential to increase the usage of cost management tools and techniques. AR can enable spatial skills (abilities, thinking and tasks) in most cost management tools and techniques. However, technical, cultural and technical and cultural barriers obstruct the use of AR in the construction industry.
Originality/value
The usage of AR in construction cost management tools and techniques has not been examined in detail until now. Thus, the study was developed to meet the industry needs and fill the literature gap to investigate the potential use of AR in construction cost management tools and techniques.
IN recent years, virtual-reality (VR) and augmented -reality (AR) technologies have moved from the realms of science fiction and imagination to advanced research in academic laboratories, to product development in the industry, and, finally, into the hands of consumers in the real world. A number of marquee VR devices have been launched, along with compelling immersive applications. A few AR devices and developer kits have been released as well. The pace of progress in both VR and AR technologies has been rapid. So, in line with this fast-emerging trend in the ecosystem, the Society for Information Display (SID) decided to create a special track on AR and VR for Display Week 2016. The rich lineup at Display Week in San Francisco included a short course, a seminar, and a number of invited and contributed presentations in the technical symposium, and demonstrations on the exhibit floor.
