This paper presents a new image-based approach for 3D mapping the locations of the rebar and embedded components in a railway bridge deck prior to placement of concrete. Our approach enables practitioners to quickly and automatically identify where the rebar and other underlying components are within the bridge decks, locate safe and unsafe drilling area, and creates a valuable documentation for future retrofit or rehabilitation of the concrete bridge decks. In the proposed method, digital images collected along the rebar cage prior to placement of concrete, are processed to automatically generate a 3D point cloud. Using a set of control points, the reconstructed point cloud is transformed into the site coordinate system. Next, a pattern recognition algorithm identifies the rebar locations. A cell-based map of the underlying structure is generated and the occupancies of the cells are automatically detected and visualized using a traffic light color spectrum. Impact of the number of images and control points on the accuracy and density of the image-based 3D reconstruction, registration, and automated recognition of the rebar locations and safe/unsafe cells are studied in detail. Results of our experiments show the promise on applicability of this low-cost approach in practice.
Proceedings Title: Proceedings of the 2012 Construction Research Congress
Conference Dates: May 21-23, 2012
Conference Location: West Lafayette, IN
Conference Title: Construction Research Congress 2012
Pub Type: Conferences
Railway, Rebar mapping, image-based 3D reconstruction, Concrete Placement