Pi: A Smart Construction Quality Management System
The discontinuous, dispersed, diverse and distinct nature of construction sites can easily overwhelm quality inspectors/managers who often need to pay daily visits to multiple sites. Quality inspections are time-consuming and labor-intensive; and resultant quality records/documentations are often inappropriate. Quality management appears to be post-event remedies. In some cases, inspection procedures were completely ignored, and forms were duly signed without conducting actual inspections. The practice of multi-tier subcontracting system intensifies the situation as subcontractors may use lower standards in executing tasks. In addition, quality deviations can cause significant cost overruns and project delays; and even become threats to public health and well-being.
LSCM has worked together with The Hong Kong Polytechnic University developed a system named Pi. Project Eye (Pi) is a vision-based system, which integrates computer vision with deep learning to improve the current manual quality management process. Pi takes site surveillance videos as input, detects construction-related objects, recognizes activities of workers on foot and construction plants, and determines if there are any quality deviations and defects produced in these activities.
Pi is non-intrusive and requires little additional costs in its implementation since surveillance cameras are commonly used on construction sites. Pi has the potential to liberate human inspectors from tedious site inspections and manual documentation. Also, Pi can be easily extended to improve construction safety management.
Pi: A Smart Construction Quality Management System has won Gold Medal at the 47th International Exhibition of Inventions Geneva in 2019.