American Society of Civil Engineers


Multimodal Image Retrieval from Construction Databases and Model-Based Systems


by Ioannis Brilakis, (corresponding author), A.M.ASCE, (Asst. Prof., Dept. of Civ. and Envir. Engrg., Univ. of Michigan—Ann Arbor, 2356 G. G. Brown Bldg., Ann Arbor, MI 48109 E-mail: brilakis@umich.edu) and Lucio Soibelman, M.ASCE, (Assoc. Prof., Dept. of Civ. and Envir. Engrg., Carnegie Mellon Univ., 118N Porter Hall, Pittsburgh, PA 15213. E-mail: lucio@andrew.cmu.edu)

Journal of Construction Engineering and Management, Vol. 132, No. 7, July 2006, pp. 777-785, (doi:  http://dx.doi.org/10.1061/(ASCE)0733-9364(2006)132:7(777))

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Journal Paper
Abstract: In the modern and dynamic construction environment it is important to access information in a fast and efficient manner in order to improve the decision making processes for construction managers. This capability is, in most cases, straightforward with today’s technologies for data types with an inherent structure that resides primarily on established database structures like estimating and scheduling software. However, previous research has demonstrated that a significant percentage of construction data is stored in semi-structured or unstructured data formats (text, images, etc.) and that manually locating and identifying such data is a very hard and time-consuming task. This paper focuses on construction site image data and presents a novel image retrieval model that interfaces with established construction data management structures. This model is designed to retrieve images from related objects in project models or construction databases using location, date, and material information (extracted from the image content with pattern recognition techniques).


ASCE Subject Headings:
Construction management
Data analysis
Databases
Imaging techniques
Information management
Information technology (IT)