Advertisement
Published in:
2022 | OriginalPaper | Chapter
An Automatic Classification and Storage Method of Construction Images Based on YOLOv5
Authors : Songchun Chen, Hongling Guo
Published in: Proceedings of the 26th International Symposium on Advancement of Construction Management and Real Estate
Publisher: Springer Nature Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Computer vision has a wide range of application prospects in the construction industry, which can improve the management efficiency of the construction site to a large extent. However, the application of machine vision has relatively high requirements for images, and currently there is no good way to obtain images. Most researchers need to build their own databases when conducting research, which hinders the applications of computer vision in construction to a certain extent.
A large number of image resources are generated on the construction site every day, but the image information is relatively complicated and messy, and difficult to be used effectively. Therefore, this paper proposes an automatic classification and storage method for construction images, which can effectively automatically classify and format large-scale images. The results show that the classification accuracy for helmets, workers, and excavators is about 70%, which can meet the needs of image classification and storage, and has good application prospects.