Deep learning-based automated building construction progress monitoring for prefabricated prefinished volumetric construction

Abstract

Recently, prefabricated prefinished volumetric construction (PPVC) has become increasingly popular as it improves flexibility in areas such as scheduling and resource management. Given the modular nature of PPVC assembly and the large amounts of visual data amassed throughout a construction project today, PPVC building construction progress monitoring can be conducted by quantifying assembled PPVC modules within images or videos. As manually processing high volumes of visual data can be extremely time-consuming and tedious, building construction progress monitoring can be automated to be more efficient and reliable. However, the complex nature of construction sites and the presence of nearby infrastructure could occlude or distort visual data. Furthermore, imaging constraints can also result in incomplete visual data. Therefore, it is hard to apply existing purely data-driven object detectors to automate building progress monitoring at construction sites. In this thesis, we propose a novel window-based automated visual building construction progress monitoring (WAVBCPM) system that estimates building construction progress of PPVC by mimicking human decision-making during manual progress monitoring. WAVBCPM is segregated into three modules. A detection module first conducts detection of windows on the target building. This is achieved by detecting windows within the input image at two scales by using YOLOv5 as a backbone network for object detection, before using a window detection filtering process to omit irrelevant detections from the surrounding areas. Next, a rectification module is developed to account for missing windows in the mid-section and near-ground regions of the constructed building that may be caused by occlusion and poor detection. Lastly, a progress estimation module checks the processed detections for missing or excess information before performing building construction progress estimation. In addition, a 5G-supported communications framework was proposed to implement WAVBCPM remotely to facilitate the computation requirements of multiple deep learning models using an off-site GPU server. The proposed method is tested on images obtained from actual construction sites and the experimental findings show that WAVBCPM is able to achieve higher accuracy in progress monitoring than purely data-driven object detectors, by mimicking human inference to overcome imperfections within visual data.