Building information modelling (BIM) has been adopted in the construction industry. The success of BIM implementation relies on the accurate building information stored in BIM models. However, building information in BIM models can be inaccurate, out-of-date, or missing in real-world projects. 3D laser scanning has been leveraged to capture the accurate as-is conditions of buildings and create as-is BIM models of buildings; this is known as the scan-to-BIM process. Although industry practitioners and researchers have implemented and studied the scan-to-BIM process, there is no framework that systematically defines and discusses the key steps and considerations in the process. This study proposes an application-oriented framework for scan-to-BIM, which describes the four major steps of a scan-to-BIM process and their relationships. The framework is oriented towards the specific BIM application to be implemented using the created as-is BIM, and includes four steps: (1) identification of information requirements, (2) determination of required scan data quality, (3) scan data acquisition, and (4) as-is BIM reconstruction. Two illustrative examples are provided to demonstrate the feasibility of the proposed scan-to-BIM framework. Furthermore, future research directions within the scan-to-BIM framework are suggested.
Developing a classifier to identify the defects from façade images using deep learning requires abundant labeled images. However, it is time‐consuming and uneconomical to label the collected images. Hence, it is desired to train an accurate classifier with only a small amount of labeled data. Therefore, this study proposes a semi‐supervised learning algorithm that uses only a small amount of labeled data for training, but still achieves high classification accuracy. In addition, based on the mean teacher algorithm, this study develops a novel uncertainty filter to select reliable unlabeled data for initial training epochs to further improve the classification accuracy. Validation experiments demonstrate that the proposed method can improve the model accuracy from 79.26% to 84.36% compared to the traditional supervised learning algorithm with 10% of labeled data in a dataset. From another perspective, compared to supervised learning algorithm, the proposed technique can help reduce the time and cost for preparing the labeled data.
Façade inspection is a regular but necessary maintenance task to ensure the safety, functioning, and aesthetics of a building. Traditional visual identification of façade defects is dangerous, time-consuming, and insufficient. Based on an image dataset and deep learning algorithms, an automatic façade defects classification technique is developed in this research. A layer-based categorization rule is proposed to categorize façade defects. To handle the problem of imbalanced data size among defect classes, a meta learning-based method is applied, which reassigns weights to the training data. Experiments demonstrated that the proposed method had a stronger capacity to deal with the imbalanced dataset problem comparing with previous methods by improving the classification accuracy from 71.43% of a basic convolutional neural network (CNN) model to 82.86% of a meta learning-based CNN model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.