A CV-Based Automatic Method of Acquiring and Processing Operation Data on Construction Site

Hui Li (), Hongling Guo and Zhihui Zhang
Additional contact information
Hui Li: Tsinghua University
Hongling Guo: Tsinghua University
Zhihui Zhang: Tsinghua University

A chapter in Proceedings of the 24th International Symposium on Advancement of Construction Management and Real Estate, 2021, pp 1281-1296 from Springer

Abstract: Abstract Image data of construction site is often of large volume and difficult to handle. This paper introduces a computer-vision-based automatic method of acquiring and processing this kind of data. A deep convolutional neural network along with region proposal network is used for on-site object detection including workers, materials and machines, followed by a light-weighed network to determine the real-time interaction between workers and working objects. A practical implication of the two network models and their experimental results is a scenario-based security and productivity management system and its basic structure is also introduced in this paper.

Keywords: Construction site; Image processing; Convolutional neural network; Deep learning; Safety and productivity management (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-15-8892-1_90

Ordering information: This item can be ordered from
http://www.springer.com/9789811588921

DOI: 10.1007/978-981-15-8892-1_90

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().