Although efforts have been made for automated monitoring of construction sites, comprehensive understanding of a whole image remains to be a difficult task. Conventional vision-based monitoring methods have shortcomings in obtaining semantic information regarding an entire image because these methods are not scalable to the number of recognizable objects and training data. Most methods use a parametric model to recognize objects, involving cumbersome parameter tuning. This study presents the data-driven scene parsing method to recognize various objects in a construction site image. For identifying object information of a query image, the monitoring system retrieves the most relevant images to a query image using nearest neighbors and scale invariant feature transform flow matching and transfers relevant image labels to a query image. This study demonstrated the reasonable system performance in construction site images, recording 81.48% of average pixel-wise recognition rate with a small amount of similar images. The scene parsing method would enrich the raw information of a construction site image, thereby facilitating information use for various management applications.
Bibliographical noteFunding Information:
We would like to thank the anonymous reviewers for their valuable comments that helped improve the paper. This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP; Ministry of Science, ICT and Future Planning ) ( NRF-2014R1A2A1A11052499 and No. 2011-0030040 ). The authors would like to thank Yonsei University for granting access to the construction site of the Baekyang-ro renovation project.
© 2016 Elsevier B.V.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Civil and Structural Engineering
- Building and Construction