Information retrieval and automated progress estimation of ongoing construction projects have been an area of interest for researchers in the field of civil engineering. It is done using 3D point cloud asbuilt and as-planned model. Advancements in the field of photogrammetry and computer vision have made 3D reconstruction of buildings easy and affordable. But the high variability of construction sites, in terms of lighting conditions, material appearance, etc. and error-prone data collection techniques tend to make the reconstructed 3D model erroneous and incorrect representation of the actual site. This eventually affects the result of progress estimation step. To overcome these limitations, this paper presents a novel approach for improving the results of 3D reconstruction of a construction site by employing two-step process for the reconstruction as compared to the traditional approach. In the proposed method, the first step is to obtain an as-built 3D model of the construction site using 3D scanning techniques or photogrammetry in the form of point cloud data. In the second step, the model is passed through pre-trained machine learning binary classification model for identifying and removing erroneous data points in the captured point cloud. Erroneous points are removed by identifying the correct building points. This processed as-built model is compared with an as-planned model for progress estimation. Based on the proposed method, experiments are carried out using commercially available stereo vision camera for 3D reconstruction.

Monitoring the progress of a large construction site manually is a challenging task for managers. By collecting visual data of the site, many monitoring tasks can be automated using machine vision techniques. In this work, we study a new method of collecting site data, which is through crane camera images used to create 3D point clouds. The technology is cost-effective and enables automatic capturing and transmission of on-site data. To automatically extract buildings from the as-built point clouds, we present VBUILT, which uses 3D convex hull volumes to identify building clusters. Experimental results on 40 point clouds collected over four months on a large construction site show that the proposed algorithm can identify building clusters with 100% accuracy.

Conventional demolition approaches of razing a building at the end of its life-cycle generate a large amount of mingled debris, which is difficult to reuse and recycle. Compared to demolition, deconstruction involves disassembling a building systematically and it is a more environmentally friendly alternative. Recent research studies have focused on the transition from demolition to deconstruction to minimize the amount of generated waste and maximize the amount of recycling and reusing material. However, due to tight schedule requirements, extra labor cost, and the lack of drawings and design information, it is difficult for an owner to estimate the cost and duration of deconstruction ahead of time. 3D imaging technologies, such as laser scanning and image-based 3D reconstruction, provide an opportunity to obtain data about as-is conditions at a job site and hence can potentially help in identifying quantities of materials that will be recycled. Existing 3D imaging workflows have two primary limitations: visibility and appearance ambiguity. First, 3D imaging can only capture visible objects before a deconstruction process starts. Also, data captured before deconstruction or at different times during deconstruction can only include a subset of all building components. Second, building components with similar appearances can be made from different materials, resulting in misclassification and errors in quantity estimation. Only a few case studies have discussed how visibility and appearance ambiguity can affect the usage of 3D imaging in deconstruction waste management. In this paper, the authors aim to illustrate the application of 3D imaging during a small-scale deconstruction project in Pittsburgh. Specifically, the authors documented the waste generated during deconstruction manually and by using two different 3D imaging technologies: laser scanning and image-based registration. We then quantified the number of invisible objects and objects with ambiguous appearances at different stages of deconstruction. Through the comparison between the quantity takeoffs from 3D imagery and the ground truth, the paper aims at providing insights on the following questions: 1) How accurate are the quantity estimation and documentation of two 3D imaging technologies (laser scanning and imagery) compared to the actual waste generated? 2) Does 3D imaging capture all components of interest during deconstruction?