A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automated classification of “cluttered” construction housekeeping images through supervised and self-supervised feature representation learning
Abstract Construction housekeeping is crucial for safety, but frequent manual inspections are difficult to maintain. A computer vision approach to automatically monitor housekeeping can overcome these issues. However, it requires labelling large number of “cluttered” construction housekeeping images that are difficult to label, even by experts. Thus, this paper presents an alternative approach that evaluates the use of self-supervised learning feature extraction to classify “cluttered” construction housekeeping images. The most suitable (84% accuracy) backbone architecture for supervised classification of housekeeping images was found to be Swin-transformer. In addition, the experiments show that self-supervised learning approach can perform better (1–4% improvement in prediction accuracy, precision, and recall) than the supervised learning approach in a non-transfer learning context and when the number of training images is reduced.
Highlights Defined cluttered images as a class of problem that deserves attention Developed models to automatically classify cluttered construction housekeeping images Self-supervised learning is a feasible alternative to supervised learning for classifying cluttered construction images Self-supervised learning can reduce the reliance on labelled image for classifying cluttered construction images
Automated classification of “cluttered” construction housekeeping images through supervised and self-supervised feature representation learning
Abstract Construction housekeeping is crucial for safety, but frequent manual inspections are difficult to maintain. A computer vision approach to automatically monitor housekeeping can overcome these issues. However, it requires labelling large number of “cluttered” construction housekeeping images that are difficult to label, even by experts. Thus, this paper presents an alternative approach that evaluates the use of self-supervised learning feature extraction to classify “cluttered” construction housekeeping images. The most suitable (84% accuracy) backbone architecture for supervised classification of housekeeping images was found to be Swin-transformer. In addition, the experiments show that self-supervised learning approach can perform better (1–4% improvement in prediction accuracy, precision, and recall) than the supervised learning approach in a non-transfer learning context and when the number of training images is reduced.
Highlights Defined cluttered images as a class of problem that deserves attention Developed models to automatically classify cluttered construction housekeeping images Self-supervised learning is a feasible alternative to supervised learning for classifying cluttered construction images Self-supervised learning can reduce the reliance on labelled image for classifying cluttered construction images
Automated classification of “cluttered” construction housekeeping images through supervised and self-supervised feature representation learning
Lim, Yu Guang (author) / Wu, Junxian (author) / Goh, Yang Miang (author) / Tian, Jing (author) / Gan, Vincent (author)
2023-09-14
Article (Journal)
Electronic Resource
English
Self-supervised learning unveils urban change from street-level images
| Elsevier | 2024