Face Mask and Social Distance Recognition using Deep Learning
Keywords:
Abstract
As the COVID-19 pandemic has caused a great despair in a variety of industries all over the ecosphere. The World Health Organization (WHO) certifies wearing a face mask and the practice of corporeal distances in order to reduce the virus's blowout. In this development, a workstation vision arrangement is developed for the automatic recognition of the violation of a mask to wear, and the corporeal distance among employees in the organization. For the face recognition, the broadside is collected and remarked on for over 1000 illustrations; set of data is obtained as an input, maximum up to 1853 photos. Then, it is trained and tested with a multi-Tensor Flow using state-of-the-art object recognition replicas on the aspect concealment to the set of data, and opt for the Nearer R-CNN Inception, ResNetV-2 to a system, which is supplied with an accuracy of up to 99.8%. The Euclidean distance is used to calculate remoteness among various objects under study. A barrier of six feet was kept as a safe distance between the objects. The corporeal distance between two or more than two objects is recognized using the R-CNN network. A real- time video of students entering the campus was shot in SECAB engineering campus and data is fed for learning and training of the proposed model. The proposed system is developed to monitor and improve safety measures by providing information about working masses in the organization by distinguishing them for wearing masks and having social distancing.
References
- M. Afkhamiaghda and E. Elwakil, “Preliminary modeling of Coronavirus (COVID-19) spread in construction industry,” J. Emerg. Manag., vol. 18, no. 7, pp. 9–17, Jul. 2020, doi: 10.5055/JEM.2020.0481.
- M. Kamari and Y. Ham, “Automated Filtering Big Visual Data from Drones for Enhanced Visual Analytics in Construction,” in Construction Research Congress 2018, Mar. 2018, vol. 2018- April, pp. 398–409, doi: 10.1061/9780784481264.039.
- M. Kamari and Y. Ham, “Analyzing Potential Risk of Wind-Induced Damage in Construction Sites and Neighboring Communities Using Large-Scale Visual Data from Drones,” in Construction Research Congress 2020: Computer Applications - Selected Papers from the Construction Research Congress 2020, 2020, pp. 915–923, doi: 10.1061/9780784482865.097.
- Y. Ham and M. Kamari, “Automated content-based filtering for enhanced vision-based documentation in construction toward exploiting big visual data from drones,” Autom. Constr., vol. 105, p. 102831, Sep. 2019, doi: 10.1016/j.autcon.2019.102831.
- L. Liu et al., “Deep Learning for Generic Object Recognition: A Survey,” Int. J. Comput. Vis., vol. 128, no. 2, pp. 261–318, Feb. 2020, doi: 10.1007/s11263-019-01247-4.
- Z. Q. Zhao, P. Zheng, S. T. Xu, and X. Wu, “Object Recognition with Deep Learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11. Institute of Electrical and Electronics Engineers Inc., pp. 3212–3232, Nov. 01, 2019, doi: 10.1109/TNNLS.2018.2876865.
- L. Jiao et al., “A survey of deep learning-based object recognition,” IEEE Access, vol. 7, pp. 128837– 128868, 2019, doi: 10.1109/ACCESS.2019.2939201.
- R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object recognition and semantic segmentation,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Sep. 2014, pp. 580–587, doi: 10.1109/CVPR.2014.81.
- Z. Zou, Z. Shi, Y. Guo, and J. Ye, “Object Recognition in 20 Years: A Survey,” 2019, Accessed: Aug. 02, 2020. [Online]. Available: http://arxiv.org/abs/1905.05055.
- R. Girshick, “Fast R-CNN,” 2015. Accessed: Aug. 03, 2020. [Online].Available: https://github.com/rbgirshick/.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.