Monitoring of construction performance using daily progress photograph logs and 4d as-planned models

Early detection of actual or potential schedule delay in field construction activities is vital to project management. This entails project managers to design, implement, and maintain a systematic approach for construction progress monitoring to identify, process and communicate discrepancies between actual and as-planned performances as soon as possible. To achieve this goal, this research focuses on exploring application of unordered daily progress photograph logs - available on any construction site - as a data collection technique. Our approach is based on computing- from the images themselves- the photographer's locations and orientations, along with a sparse 3D geometric representation of the as-built site using daily progress photographs and superimposition of the reconstructed scene over as-planned 4D models. Within such an environment, progress photographs are registered in the virtual as-planned environment allowing a large unstructured collection of daily construction images to be sorted, interactively browsed and explored. In addition, sparse reconstructed scenes superimposed over 4D models allow site images to be geo-registered with the as-planned components and consequently, location-based image processing technique to be implemented and progress data to be extracted automatically. The results of progress comparison between as-planned and as-built performances are visualized in a 4D Augmented Reality environment (D⁴AR) using a traffic light metaphor. We present our results on two ongoing construction projects and discuss implementation and future potential enhancement of this new technology in construction.