Real-time spatial modeling to detect and track resources on construction sites
| dc.contributor.advisor | Haas, Carl T. (Carl Thomas) | en |
| dc.contributor.advisor | Caldas, Carlos H. | en |
| dc.creator | Teizer, Jochen | en |
| dc.date.accessioned | 2008-08-28T23:17:27Z | en |
| dc.date.available | 2008-08-28T23:17:27Z | en |
| dc.date.issued | 2006 | en |
| dc.description.abstract | For more than 10 years the U.S. construction industry has experienced over 1,000 fatalities annually. Many fatalities may have been prevented had the individuals and equipment involved been more aware of and alert to the physical state of the environment around them. Awareness may be improved by automatic 3D (three-dimensional) sensing and modeling of the job site environment in real-time. Existing 3D modeling approaches based on range scanning techniques are capable of modeling static objects only, and thus cannot model in real-time dynamic objects in an environment comprised of moving humans, equipment, and materials. Emerging prototype 3D video range cameras offer another alternative by facilitating affordable, wide field of view, automated static and dynamic object detection and tracking at frame rates better than 1Hz (real-time). This dissertation presents an imperical work and methodology to rapidly create a spatial model of construction sites and in particular to detect, model, and track the position, dimension, direction, and velocity of static and moving project resources in real-time, based on range data obtained from a three-dimensional video range camera in a static or moving position. Existing construction site 3D modeling approaches based on optical range sensing technologies (laser scanners, rangefinders, etc.) and 3D modeling approaches (dense, sparse, etc.) that offered potential solutions for this research are reviewed. The choice of an emerging sensing tool and preliminary experiments with this prototype sensing technology are discussed. These findings led to the development of a range data processing algorithm based on three-dimensional occupancy grids which is demonstrated in detail. Testing and validation of the proposed algorithms have been conducted to quantify the performance of sensor and algorithm through extensive experimentation involving static and moving objects. Experiments in indoor laboratory and outdoor construction environments have been conducted with construction resources such as humans, equipment, materials, or structures to verify the accuracy of the occupancy grid modeling approach. Results show that modeling objects and measuring their position, dimension, direction, and speed had an accuracy level compatible to the requirements of active safety features for construction. Results demonstrate that video rate 3D data acquisition and analysis of construction environments can support effective detection, tracking, and convex hull modeling of objects. Exploiting rapidly generated three-dimensional models for improved visualization, communications, and process control has inherent value, broad application, and potential impact, e.g. as-built vs. as-planned comparison, condition assessment, maintenance, operations, and construction activities control. In combination with effective management practices, this sensing approach has the potential to assist equipment operators to avoid incidents that result in reduce human injury, death, or collateral damage on construction sites. | |
| dc.description.department | Civil, Architectural, and Environmental Engineering | en |
| dc.format.medium | electronic | en |
| dc.identifier | b68637767 | en |
| dc.identifier.oclc | 166263913 | en |
| dc.identifier.uri | http://hdl.handle.net/2152/2939 | en |
| dc.language.iso | eng | en |
| dc.rights | Copyright is held by the author. Presentation of this material on the Libraries' web site by University Libraries, The University of Texas at Austin was made possible under a limited license grant from the author who has retained all copyrights in the works. | en |
| dc.subject.lcsh | Building--Accidents | en |
| dc.subject.lcsh | Accidents--Prevention | en |
| dc.title | Real-time spatial modeling to detect and track resources on construction sites | en |
| dc.type.genre | Thesis | en |
| thesis.degree.department | Civil, Architectural, and Environmental Engineering | en |
| thesis.degree.discipline | Civil Engineering | en |
| thesis.degree.grantor | The University of Texas at Austin | en |
| thesis.degree.level | Doctoral | en |
| thesis.degree.name | Doctor of Philosophy | en |