Construction Research Congress 2020
Construction Worker Posture Estimation Using OpenPose
Publication: Construction Research Congress 2020: Safety, Workforce, and Education
ABSTRACT
Visual field observations are critical in construction project management. Cost reduction and increases in data usability have made RGB cameras more prevalent on construction sites, expanding capabilities of the modern construction manager. The eyes of a construction manager are irreplaceable tools which monitor and subjectively evaluate construction activities. The variety of “right” and “wrong” ways to complete a construction task make the automation of visual field operations a difficult task. Existing vision-based methods are limited to RGB-depth cameras which are rarely used on construction sites. This paper presents a method for using deep learning techniques to aid the automatic recognition of construction worker activities from RGB camera footage and to what extent can computer vision accurately detect construction worker activity. OpenPose human estimation algorithm was used to create 2D human pose samples of construction activities using RGB cameras. The samples are used to train and test a time distributed feed forward neural network with LSTM Keras model classifier. The results of this work in progress set the stage for improving the usefulness of visual data for project management in a variety of construction scenarios and other labor-intensive sectors. Monitoring the safety and productivity of construction workers will become more efficient allowing much-needed increases in our capacity to develop and maintain infrastructure.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Bls.gov (2018). "Databases, Tables & Calculators by Subject." <https://www.bls.gov/data/#injuries>. (12/01/2018, 2018).
Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., and Sheikh, Y. J. a. p. a. (2018). "OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields."
Cao, Z., Simon, T., Wei, S.-E., and Sheikh, Y. "Realtime multi-person 2d pose estimation using part affinity fields." Proc., Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7291-7299.
Chen, C., Jafari, R., and Kehtarnavaz, N. J. I. T. o. H.-M. S. (2014). "Improving human action recognition using fusion of depth camera and inertial sensors." 45(1), 51-61.
Dubois, A., and Charpillet, F. "Human activities recognition with RGB-Depth camera using HMM." Proc., 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 4666-4669.
Escorcia, V., Dávila, M. A., Golparvar-Fard, M., and Niebles, J. C. "Automated vision-based recognition of construction worker actions for building interior construction operations using RGBD cameras." Proc., Construction Research Congress 2012: Construction Challenges in a Flat World, 879-888.
Gong, J., and Caldas, C. H. J. J. o. C. i. C. E. (2009). "Computer vision-based video interpretation model for automated productivity analysis of construction operations." 24(3), 252-263.
Hochreiter, S., and Schmidhuber, J. J. N. c. (1997). "Long short-term memory." 9(8), 1735-1780.
Jones, S. R. G. (1992). "Was There a Hawthorne Effect?", 98(3), 451-468.
Kepski, M., and Kwolek, B. "Fall detection using ceiling-mounted 3d depth camera." Proc., 2014 International conference on computer vision theory and applications (VISAPP), IEEE, 640-647.
Khosrowpour, A., Niebles, J. C., and Golparvar-Fard, M. J. A. i. C. (2014). "Vision-based workface assessment using depth images for activity analysis of interior construction operations." 48, 74-87.
Rafibakhsh, N., Gong, J., Siddiqui, M. K., Gordon, C., and Lee, H. F. "Analysis of xbox kinect sensor data for use on construction sites: depth accuracy and sensor interference assessment." Proc., Construction research congress, 848-857.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). "Learning representations by back-propagating errors." Nature, 323(6088), 533-536.
Shehata, M. E., and El-Gohary, K. M. (2011). "Towards improving construction labor productivity and projects’ performance." Alexandria Engineering Journal, 50(4), 321-330.
Sung, J., Ponce, C., Selman, B., and Saxena, A. "Human activity detection from RGBD images." Proc., Workshops at the twenty-fifth AAAI conference on artificial intelligence.
Weerasinghe, I. T., Ruwanpura, J. Y., Boyd, J. E., and Habib, A. F. "Application of Microsoft Kinect sensor for tracking construction workers." Proc., Construction Research Congress, 858-867.
Yang, J., Shi, Z., and Wu, Z. (2016). "Vision-based action recognition of construction workers using dense trajectories." Advanced Engineering Informatics, 30(3), 327-336.
Yilmaz, A., Javed, O., and Shah, M. (2006). "Object tracking: A survey." ACM Comput. Surv., 38(4), 13.
Zhang, C., and Tian, Y. (2012). "RGB-D camera-based daily living activity recognition." Journal of Computer Vision and Image Processing, 2(4), 12.
Zhang, H., Yan, X., and Li, H. J. A. i. C. (2018). "Ergonomic posture recognition using 3D view-invariant features from single ordinary camera." 94, 1-10.
Information & Authors
Information
Published In
Construction Research Congress 2020: Safety, Workforce, and Education
Pages: 556 - 564
Editors: Mounir El Asmar, Ph.D., Arizona State University, David Grau, Ph.D., Arizona State University, and Pingbo Tang, Ph.D., Arizona State University
ISBN (Online): 978-0-7844-8287-2
Copyright
© 2020 American Society of Civil Engineers.
History
Published online: Nov 9, 2020
Published in print: Nov 9, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.