Crowd to Cloud: Simplified automatic reconstruction of digital building assets for Facility Management

Abstract

Existing buildings, the 99% are conveniently neglected in the topic of building stock digitalization. The inefficiencies in the operation and maintenance phase of a building are unbelievably high and this directly influences costs. Digital asset creation for existing buildings to capture its current state is evidently proven to be time consuming, expensive and extremely difficult. This research work proposes a novel crowdsourced cloud-based reconstruction of digital building assets. A fully functional smartphone application prototype is developed and tested. The workflow encompasses a complete circle from data capturing to end user application with a simple smartphone. Results demonstrate successful implementation by achieving a realistic 3D model of different typologies, minimal trade off in accuracy and low process costs. It was found that crowdsourcing the images drastically reduces capture time and simultaneously shifts these costs from the operator to the user. Use cases were developed as web applications serving different demanded functionalities. Most significantly, the proposed approach costed one-fifteenth lesser than manual modelling and one-fifth cheaper than locally processed reconstruction algorithms.