Jochen Teizer

Personnel tracking on construction sites using video cameras

This paper discusses the possibility of- and need for-tracking workforce on construction jobsites using video cameras. An evaluation of algorithms and their associated results is presented. The principal objective of this paper is to test and demonstrate the feasibility of tracking workers from statically placed and dynamically moving cameras. This paper also reviews existing techniques to monitor workforce and describes areas where this work might be useful in engineering applications. The main difficulties associated with tracking on a construction site is the significant amount of visual clutter, the changing photometric visual content throughout the course of a day, and the presence of occluding and moving obstacles. The tracking of workers within the field of view of the camera will involve four tracking techniques, density mean-shift, Bayesian segmentation, active contours, and graph-cuts. Typical construction site video will be processed using the proposed algorithms and analyzed to determine the most appropriate tracking method for the video presented.

Semantics of model views for information exchanges using the industry foundation class schema

The industry foundation classes (IFC) data schema is generic, designed to support the full range of model exchanges needed in the construction industry. For any particular working exchange for some sub-domain of building construction, a set of model view definitions (MVD) is required to specify exactly what information should be exchanged, and in what form and structure the IFC entities are to be used. Defining model view definitions requires principle decisions and workarounds because the IFC itself does not address a number of semantic issues comprehensively. Some of the issues identified and discussed include the typing of objects, instances, geometry, relationships, and rules, which are supported in the IFC schema, and the complexities of exchanging such information accurately between applications. This paper advances the idea of MVD Concepts as an object-oriented and modular mechanism for embedding semantic meaning in model views. We conclude that although the IFC product model schema is richly expressive, it lacks formal definition of its entities, attributes, and relationships. To achieve standardized and re-usable model views, further research towards a modular and logical framework based on formal specification of IFC concepts is recommended. This research is expected to impact the overall interoperability of applications in the building information modeling realm.

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.

Quadrature Amplitude Modulated Backscatter in Passive and Semipassive UHF RFID Systems

Passive and semipassive UHF RF identification (RFID) systems have traditionally been designed using scalar-valued differential radar cross section (DRCS) methods to model the backscattered signal from the tag. This paper argues that scalar-valued DRCS analysis is unnecessarily limiting because of the inherent coherence of the backscatter link and the complex-valued nature of load-dependent antenna-mode scattering from an RFID tag. Considering modulated backscatter in terms of complex-valued scattered fields opens the possibility of quadrature modulation of the backscatter channel. When compared with binary amplitude shift keying (ASK) or phase shift keying (PSK) based RFID systems, which transmit 1 bit of data per symbol period, and thus 1 bit per on-chip clock oscillator period, tags employing vector backscatter modulation can transmit more than 1 bit per symbol period. This increases the data rate for a given on-chip symbol clock rate leading to reduced on-chip power consumption and extended read range. Alternatively, tags employing an M-ary modulator can achieve log2 M higher data throughput at essentially the same dc power consumption as a tag employing binary ASK or PSK. In contrast to the binary ASK or PSK backscatter modulation employed by passive and semipassive UHF RFID tags, such as tags compliant with the widely used ISO18000-6c standard, this paper explores a novel CMOS-compatible method for generating M-ary quadrature amplitude modulated (QAM) backscatter modulation. A new method is presented for designing an inductorless M-ary QAM backscatter modulator using only an array of switched resistances and capacitances. Device-level simulation and measurements of a four-state phase shift keying (4-PSK)/four-state quadrature amplitude modulated (4-QAM) modulator are provided for a semipassive (battery-assisted) tag operating in the 850-950-MHz band. This first prototype modulator transmits 4-PSK/4-QAM at a symbol rate of 200 kHz and a bit rate of 400 kb/s at a static power dissipation of only 115 nW.

Tracking multiple workers on construction sites using video cameras

This paper proposes a tracking scheme for tracking multiple workers on construction sites using video cameras. Prior work has compared several contemporary tracking algorithms on construction sites and identified several difficulties, one of which included the existence of interacting workforce. In order to address the challenge of multiple workers within the cameras field of view, the authors have developed a tracking algorithm based upon machine learning methods. The algorithm requires several sample templates of the tracking target and learns a general model that can be applied to other targets with similar geometry. A parameterized feature bank is proposed to handle the case of variable appearance content. The tracking initialization has been discussed for different types of video cameras. A multiple tracking management module is applied to optimize the system. The principal objective of this paper is to test and demonstrate the feasibility of tracking multiple workers from statically placed and dynamically moving cameras.

Human Factors Analysis Classification System Relating to Human Error Awareness Taxonomy in Construction Safety

In several studies it is widely accepted that human error is the main reason for up to 80% of all incidents and accidents in complex high-risk systems that exist in the aviation, petrochemical, healthcare, construction, mining, and nuclear power industries. The construction industry, greatly impacted by accidents, is accountable for more than 1,000 fatalities in each of the past 14 years. The human factors analysis classification system (HFACS) is a general human error framework originally developed and tested as a tool for investigating and analyzing the human causes of accidents with applications to rail, air, and offshore environments. This paper introduces the concept of HFACS along with the framework of human error awareness training (HEAT) and their potential contribution to the construction industry. Based on the HEAT approach, this paper proposes a new error analysis educational and classification tool for safety within the construction industry. The primary difference between HFACS and HEAT is found in the structure, content, and presentation of the information allowing for higher effectiveness in incident investigation and safety education and training in construction.

Ultrawideband for Automated Real-Time Three-Dimensional Location Sensing for Workforce, Equipment, and Material Positioning and Tracking

Management of construction resources, such as workforce, equipment, and material, is critical to project success. Completion of work tasks on schedule, safely and within the proposed budget requires a coordinated planning effort that allocates adequate availability of project resources. Because this task alone can become a challenging and time-consuming effort for many field personnel, several existing technologies are reviewed for their benefits and limitations in keeping oversight of resource location and status at job sites. To ensure the optimal solution using the right resources, such knowledge becomes even more meaningful when optimizing construction logistics and safety at the same time. This paper introduces an emerging sensing technology called ultrawideband (UWB) that is capable of determining three-dimensional resource location information in object-cluttered construction environments in real time (up to 60 Hz). The use of UWB is explained in a variety of construction applications including simplifying on-site management, improving resource productivity and usage, reducing schedule and cost, and increasing work zone safety. UWB technology and its advantages and limitations are compared with the state of the art in positioning technologies. Results of preliminary UWB experiments in the laboratory and construction environment are presented using developed data processing algorithms and a method to determine the accuracy of UWB position measurements. The paper discusses the feasibility of using ultrawideband as a data collection and decision support tool for robotic (automated) infrastructure construction applications in the areas of real-time three-dimensional material flow and workforce location tracking, optimized machine positioning and automated navigation, and proactive work zone safety.

Rapid Automated Monitoring of Construction Site Activities Using Ultra-Wide Band

Monitoring construction site activities is a critical concern to most stakeholders (owners, contractors, architects, engineers, suppliers, etc.) in a construction project. Successful projects are often determined by the level of awareness of project status or work task performance. Thus, information has inherent value for real-time or near real-time decision making. Good resource procurement and resource allocation of workforce, material, and equipment comes in play when job site conditions can be efficiently and effectively assessed. Semi- or automated technologies in the data collection and assessment process can assist in making fast and confident decisions. This paper introduces an emerging technology called Ultra Wide Band (UWB) for real-time location sensing and resource tracking. The technology, its use as data collection tool, preliminary data processing algorithms, experiments, and results are presented in the context of active work zone safety and material location tracking. Many more application areas exist where UWB might impact the field and project management level to overall benefit the construction industry’s competitiveness.

Data Fusion of Real-Time Location Sensing and Physiological Status Monitoring for Ergonomics Analysis of Construction Workers

AbstractPrevious research and applications in construction resource optimization have focused on tracking the location of material and equipment. There is a lack of studies on remote monitoring for improving safety and health of the construction workforce. This paper presents a new approach for monitoring ergonomically safe and unsafe behavior of construction workers. The study relies on a methodology that utilizes fusion of data from continuous remote monitoring of construction workers’ location and physiological status. To monitor construction workers activities, the authors deployed nonintrusive real-time worker location sensing (RTLS) and physiological status monitoring (PSM) technology. This paper presents the background and need for a data fusion approach, the framework, the test bed environment, and results to some case studies that were used to automatically identify unhealthy work behavior. Results of this study suggest a new approach for automating remote monitoring of construction workers safet...

Vision-Based Tower Crane Tracking for Understanding Construction Activity

AbstractVisual monitoring of construction worksites through the installation of surveillance cameras has become prevalent in the construction industry. These cameras also are useful for automatic observation of construction events and activities. This paper demonstrates the use of a surveillance camera for assessing tower crane activities during the course of a workday. In particular, it seeks to demonstrate that the crane jib trajectory, together with known information regarding the site plans, provides sufficient information to infer the activity states of the crane. The jib angle trajectory is tracked by using two-dimensional to three-dimensional rigid pose tracking algorithms. The site plan information includes a process model for the activities and site layout information. A probabilistic graph model for crane activity is designed to process the track signals and recognize crane activity as belonging to one of two categories: concrete pouring and nonconcrete material movement. The experimental result...