Computer vision-enabled digital twin for construction management

Abstract

Conventional construction management relies on sampling labour productivity data to monitor project budget and progress, an error-prone process that leads to misjudgement, resource overrun and post-event remedies. The industry is longing for a new management tool for better construction management. In this regard, Prof. Li and his research team have developed a computer vision-enabled digital twin based on far, middle and near surveillance. As such, outdoor activities of workers can be monitored, identified and analysed on a device-free approach, with video input translated into measurable indicators for automatic productivity evaluation. Leveraging on machine learning methodologies, the work progress of indoor trades and the health status of the project can be assessed. These technologies have been put to several trials in Hong Kong, and are anticipated to transform construction management into a human-based, intensive and proactive process that can reduce waste and significantly improve productivity and performance.