Abstract
Mobile phones and drones are widely used to record images of construction sites in various stages of progress. Although site images can be used a lot during the construction period, they are mostly used only for recording simple construction results. If objects in a photographic image are recognized by a component of construction structure, the image could serve as a valuable tool in construction schedule management. In this study, authors present a framework for automatically recognizing objects for each component of a structure in a photographic image. To this end, after collecting and training a large amount of photographic images from the railroad bridge structures, an object detection method that can automatically recognize the construction components of the bridge structure based on deep learning model was introduced. Images are procured through web crawling, and the collected images are pre-treated for supervised training. The results of the deep learning model showed high performance in the pier and coping classes, and the slab showed a rather low accuracy, and it was confirmed that the degree of utilization of the detection results was significantly affected by the angle of shooting the image.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bunrit S, Kerdprasop N (2019) Evaluating on the transfer learning of CNN architectures to a construction material image classification task. International Journal of Machine Learning and Computing 9:201–207, DOI: https://doi.org/10.18178/ijmlc.2019.9.2.787
Cheng H, He Z, Shi B, Zhong T (2019) Research on recognition method of electrical components based on YOLO V3. IEEE Access 7:157818–157829, DOI: https://doi.org/10.1109/ACCESS.2019.2950053
Cheng JCP, Wang M (2018) Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques. Automation in Construction 95:155–171, DOI: https://doi.org/10.1016/j.autcon.2018.08.006
Choi SH (2019) Development of road asset management system based on artificial intelligence using visual information. DS Thesis, Hanbat University, Daejeon, Korea (in Korean)
Dung CV, Ahn LD (2019) Autonomous concrete crack detection using deep fully convolutional neural network. Automation in Construction 99:52–58, DOI: https://doi.org/10.1016/j.autcon.2018.11.028
Engi’s CONPAPER (2021) Engi’s CONPAPER. Retrieved August 21, 2021, https://conpaper.tistory.com/49147
Kim JU (2019) A study on the classification of risk factors for image recognition technology application in construction. MSc Thesis, Chungang University, Seoul, Korea (in Korean)
Kim HT, Kim YS (2020) Object and environment recognition for a small mobile robot applying artificial intelligence. Journal of the Digital Contents Society 21(4):811–816, DOI: https://doi.org/10.9728/dcs.2020.21.4.811
Kumar SS, Wang MZ, Abraham DM, Mohammad RJ (2018) Deep learning—based automated detection of sewer defects in CCTV videos. Journal of Computing in Civil Engineering 34(1), DOI: https://doi.org/10.1061/(ASCE)CP.1943-5487.0000866
Lee SY, Huynh TC, Park JH, Kim JT (2019) Bolt-loosening detection using vision-based deep learning algorithm and image processing method. Computational Structural Engineering Institute of Korea 32(4):265–272, DOI: https://doi.org/10.7734/COSEIK.2019.32.4.265
Lee YH, Kim YS (2020) Comparison of CNN and YOLO for object detection. Journal of the Semiconductor & Display Technology 19(1):85–92
Lee HJ, Lee WS, Choi IH, Lee CH (2020a) Detection model of fruit epidermal defects using YOLOv3: A case of peach. Information Systems Review 22(1):113–117, DOI: https://doi.org/10.14329/isr.2020.22.1.113
Lee JH, Park JJ, Yoon HC (2020b) Automatic classification of bridge component based on deep learning. Journal of the Korean Society of Civil Engineers 40(2):239–245, DOI: https://doi.org/10.12652/Ksce.2020.40.2.0239
Lin JJ, Han KK, Golparvar-Fard M (2015) A framework for model-driven acquisition and analytics of visual data using UAVs for automated construction progress monitoring. Computing in Civil Engineering 2015:156–164, DOI: https://doi.org/10.1061/9780784479247.020
Rho JH, Park MS, Lee HS (2020) Automated construction progress management using computer vision-based CNN model and BIM. Korean Journal of Construction Engineering and Management 21(5):11–19, DOI: https://doi.org/10.6106/KJCEM.2020.21.5.011
Swetha MS, Veena MS, Muneshwara MS, Thungamani M (2018) Survey of object detection using deep neural networks. International Journal of Advanced Research in Computer and Communication Engineering 7(11), DOI: https://doi.org/10.17148/IJARCCE.2018.71104
Tang S, Roberts D, Mani G-F (2020) Human-object interaction recognition for automatic construction site safety inspection. Automation in Construction 120, DOI: https://doi.org/10.1016/j.autcon.2020.103356
Xiao B, Kang SC (2021) Development of an image data set of construction machines for deep learning object detection. Journal of Computing in Civil Engineering 35(2), DOI: https://doi.org/10.1061/(ASCE)CP.1943-5487.0000945
Zhao Y, Deng X, Lai H (2020) A YOLO-based method to recognize structural components from 2D drawings. Construction Research Congress 2020, DOI: https://doi.org/10.1061/9780784482865.080
Acknowledgments
This study was funded by the Korea Agency for Infrastructure Technology Advancement as part of its research funding support project (22RBIM-C158178-0361382116530003).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Park, S.M., Lee, J.H. & Kang, L.S. A Framework for Improving Object Recognition of Structural Components in Construction Site Photos Using Deep Learning Approaches. KSCE J Civ Eng 27, 1–12 (2023). https://doi.org/10.1007/s12205-022-2318-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-022-2318-0