Open Access
ARTICLE
Elderly Fall Detection Based on Improved SSD Algorithm
Jiancheng Zou1, Na Zhu1,*, Bailin Ge1, Don Hong2
1 North China University of Technology, Beijing, 100144, China
2 Department of Mathematical Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
* Corresponding Author: Na Zhu. Email:
Journal of New Media 2021, 3(1), 1-10. https://doi.org/10.32604/jnm.2021.017763
Received 10 February 2021; Accepted 02 March 2021; Issue published 15 March 2021
Abstract
We propose an improved a single-shot detector (SSD) algorithm to
detect falls of the elderly. The VGG16 network part of the SSD network is
replaced with the MobilenetV2 network. At the same time, we change the
infrastructure of MobilenetV2 network, the three layers that were not downsampled at the end were removed, which can make the model structure simpler
and faster to detect. The complete Intersection-over-Union (CIoU) loss function
is introduced to get a good regression of the target borders that have different
sizes and different proportions. We use Feature Pyramid Network (FPN) for upsampling, it can fuse low-level feature maps with high resolution and high-level
feature maps with rich semantic information. For sampling results, we use the
Secure Shell (SSH) module to extract different receptive fields, which improves
the detection accuracy. Our model ensures that the accuracy of the elderly fall
detection remains unchanged, but it greatly improves the detection speed that
only takes 10 milliseconds to detect a picture.
Keywords
Cite This Article
APA Style
Zou, J., Zhu, N., Ge, B., Hong, D. (2021). Elderly fall detection based on improved SSD algorithm. Journal of New Media, 3(1), 1-10. https://doi.org/10.32604/jnm.2021.017763
Vancouver Style
Zou J, Zhu N, Ge B, Hong D. Elderly fall detection based on improved SSD algorithm. J New Media . 2021;3(1):1-10 https://doi.org/10.32604/jnm.2021.017763
IEEE Style
J. Zou, N. Zhu, B. Ge, and D. Hong "Elderly Fall Detection Based on Improved SSD Algorithm," J. New Media , vol. 3, no. 1, pp. 1-10. 2021. https://doi.org/10.32604/jnm.2021.017763