| In the modern, distributed and dynamic construction environment it is important to exchange information from different sources and in different data formats in order to improve the processes supported by these systems. Previous research has demonstrated that: (i) a significant percentage of construction data is stored in semi-structured or unstructured data formats; (ii) locating and identifying such data that are needed for the important decision making processes is a very hard and time-consuming task; (iii) there is no automated method for associating visual data with their related project objects; and (iv) construction visual data and specifically images are a significant part of construction documentation with thousands stored in site photographs logs of large scale projects. Therefore, methods for managing such types of data and especially construction images are important for construction information management.; In this dissertation, an automated methodology for the retrieval, classification, and integration of construction images in AEC/FM model based systems will be presented. Specifically, a combination of techniques from the areas of image processing, computer vision, and content-based image retrieval have been deployed to develop a method that can retrieve related construction site image data from components of a project model. This method is able to automatically classify, store, integrate and retrieve image data files in inter-organizational systems so as to allow their usage in project management related tasks like project monitoring and productivity measuring systems, processes visualization across time and inventory monitoring as well as evidence retrieval for litigation and other purposes. |
