Multisensor data fusion for on-site materials tracking in construction

Automated materials tracking and locating on construction sites can significantly impact construction productivity. The ability to automatically detect the locations and multi-handling of thousands of items can improve the performance of material distribution, and ultimately improve project performance. Deploying a cost-effective, scalable, and easy to implement materials location sensing system in real world construction sites has very recently become technically and economically feasible. However, much opportunity still exists to improve accuracy, precision and robustness. In this study a data fusion model is used on an integrated solution for automated identification, location estimation, and dislocation detection of construction materials. The developed model is a modified functional data fusion model. Particular attention is focused on dislocation detection because it is closely coupled with location estimation, and because it can be used to detect multi-handling of materials. Multi-handling is a key indicator of inefficiency. This study has successfully addressed the challenges of fusing data from different simple sources of information within a very noisy and dynamic environment. The results indicate a potential for the proposed model to improve location estimation and movement detection as well as to automate multi-handling counts.