Bingfei Zhang and Zhenhua Zhu
Vision-Based Detection of Falls at Flat Level Surfaces
Abstract: Workers might experience fall accidents even when they are working at flat level surfaces. These accidents plus other types of fall accidents have been reported as one of the major causes for worker-related fatalities and injuries. Currently, it becomes common to set up video cameras to monitor working environments. The video cameras provide an alternative to detect fall accidents. The objective of this paper is to investigate the feasibility of detecting fall accidents of workers with video. The preliminary focus is put on the fall detection under one single monocular camera. A novel fall detection method is proposed. Under the method, workers in the videos captured by the video cameras are first detected and tracked. Their pose and shape related features are then extracted. Given a set of features, an artificial neural network (ANN) classifier is further trained to automatically determine whether a fall happens. The method has been tested and the detection precision and recall were used to evaluate the method. The test results with high detection precision and recall indicated the method effectiveness. Also, the lessons and findings from this research are expected to build a solid foundation to create a vision-based fall detection solution for safety engineers.
Keywords: Fall Detection, Video Processing, Computer Vision, Safety Management
Full text: content.pdf (1,275,832 bytes) (available to registered users only)
Hassanain M A, Froese T M, Vanier D J
Information analysis for roofing systems maintenance management integrated system
Abstract: The Building Envelope Life Cycle Asset Management (BELCAM) project,
lead by the National Research Council Canada (NRCC) and Public Works
and Government Service Canada (PWGSC), is a "proof of concept" project
aimed at helping asset managers to predict the remaining service life of
building envelope components and to maximize the return on their
maintenance expenditure. The BELCAM project focuses on flat or lowslope
conventional roofing systems as a representative domain. This paper
focuses on maintenance management, which is primarily concerned with the
management of all technical and administrative tasks involved in
maintaining a building element in, or restoring it to, a state in which it can
perform its intended function. A framework for the integration of the
process of managing maintenance of roofing systems is proposed. The
framework consists of five sequential steps: (1) Identification of roofing
system components requiring assessment, (2) Identification of roofing
system performance requirements, (3) Identification of performance
assessment methods, (4) Roofing system maintenance planning, (5) Roofing
system maintenance operations management. This paper introduces a
framework for roofing systems maintenance management. It presents a
preliminary analysis of an integrated information system to support
maintenance management. The paper follows the development
methodology adopted by the International Alliance for Interoperability (IAI)
to represent the high-level information within the proposed framework of
maintenance management. IAI projects follow a standard process-oriented
development methodology, involving the following steps: usage scenarios,
process definitions, information analysis and information modeling and
Full text: content.pdf (87,919 bytes) (available to registered users only)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.processing (0.013504)
Sound: read aloud.
Permission to reproduce these papers has been graciously provided by the Research Press of the National Research Council of Canada. The support of the editors, particularly Dr. Dana Vanier, is gratefully appreciated.
FABRICATION OF PARTIALLY DOUBLE-CURVED SURFACES OUT OF FLAT SHEET MATERIAL THROUGH A 3D PUZZLE APPROACH
Abstract: The topic of this paper is the connection of digital modeling with generative programming and rapid prototyping, to produce physical sketch surface models. The physical surface models are assembled out of developable strips connected through a puzzle-like detail. The use of programming as a design approach allows the generation of connection details that corresponds to the rules of flat sheet rapid prototyping techniques of laser cutting and water jet cutting. With numerically controlled cutting, there is no need to keep the joint detail related to manually achievable forms or to apply a standardized dimension. This paper demonstrates the possibilities of programming to generate cutting geometries that adapt to the local surface properties. The larger perspective of the research approach is the question of how to formulate and capture design intention through programming. What influence does the use of generative modeling in combination with rapid prototyping have on the design language of physical objects?
Keywords: fabrication, generative design
Full text: content.pdf (2,151,238 bytes) (available to registered users only)
Pilgrim M, Bouchlaghem D, Holmes M, Loveday D
Visualisation in building design and analysis
Abstract: "Research on data visualisation is undergoing major developments in a number of different fields. These developments include investigating ways of applying visualisation techniques and systems for more efficient manipulation, interpretation and presentation of data. Research into applied visualisation has so far taken place in the fields of Computational Fluid Dynamics, Medicine, Social Sciences, and the Environment. In the built environment field however, the potential of new visualisation technologies to enhance the presentation of performance data from simulation programmes (of the type used by engineering design consultants, for example) has remained almost unexplored. Improvements in this area would lead to a better and more efficient use of these simulation programs and would facilitate the interpretation of such output data by construction industry professionals, leading to better, more informed design decisions.
This paper presents an initial study on Data Visualisation and its effective use in the thermal analysis of buildings. Much of the current data visualisation in the engineering and scientific world focuses on very large data sets produced by applications such as FEA, CFD or GIS. As such the tools developed to date are often too expensive or not appropriate for the visualisation of the relatively smaller data sets produced by thermal analysis tools. The objective of the work summarised here was to develop a method of visualising the data produced by the thermal analysis tools which would run on an average desktop PC and be easy to maintain/customise and above all present the data in an intuitive manner.
A workplace observational study of several engineers performing such an analysis revealed each was spending a significant amount of time manipulating the output within commercial spreadsheet packages. Further studies revealed the most common tasks were the inspection of predicted internal conditions, location of glazed elements transmitting significant solar radiation and the identification of high internal surface temperatures. Two applications were therefore proposed. The first is designed to automatically process the output within the spreadsheet environment. The second is designed to display the solution in three dimensions to aid spatial recognition and data navigation. The spreadsheet tools were developed over a period of several months and then released to all users of the analysis tools. The 3D tool was developed over a longer period and has been subjected to small group tests. Each tool was developed using Microsoft Visual Basic making them both easy to maintain and freely available. The 3D tool reads in flat text files produced by the analysis and automatically generates a framed HTML page with an embedded 3D VRML world describing the building and its results.
This study shows that each of the proposed applications significantly improves some of the attributes associated with usability, namely; learnability, efficiency, memorability, errors and satisfaction. The spreadsheet tool increased efficiency and decreased errors but offered no real satisfaction. The 3D tool offers increased satisfaction but at present does not efficiently present all of the data required. Finally, It is possible to develop low cost Data Visualisation tools to improve the overall usability of a thermal analysis tool within a built environment consultantcy."
Full text: content.pdf (404,505 bytes) (available to registered users only)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.social (0.027102)
Sound: read aloud.
Permission to reproduce these documents have been graciously provided by Icelandic Building Research Institute. The assistance of the editor, Mr. Gudni Gudnason, is gratefully appreciated
Rashidi A,Brilakis I,Vela P
Built infrastructure point cloud data cleaning: an overview of gap filling algorithms
Abstract: Video captured from infrastructure scenes can be used to generate point cloud data (PCD) as a potential solution for acquiring spatial information of built infrastructure - however, video based PCD is incomplete and includes gaps, outliers and poor/non-reconstructed areas. This phenomenon has a negative impact on both visualization and measurement practices and is mainly caused by a number of reasons including insufficient coverage of all views while videotaping the scene, lack of sufficient features on uniform surfaces and possible errors in calibration, matching and optimization algorithms. To tackle this issue, researchers suggested various post processing algorithms for reconstructing missing surfaces and filling gaps/holes. This paper provides an overview on these algorithms summarize their properties in terms of efficiency, ability to work in complex geometry settings and running time. As the comparison study, three most common hole filling algorithms: MSL, GG and RFR were implemented and tested on a number of real built infrastructure scenes as the case studies. Number of generated 3D points for filling the gaps, proper distribution of points on covered surfaces and running time are three major comparison metrics has been taken into account. Results indicate that in general PML outperforms other algorithms on both flat and curved surfaces.
Keywords: Built infrastructure,triangulation,gap,Point Cloud Data,surface reconstruction
Full text: content.pdf (1,158,728 bytes) (available to registered users only)