• Journal of Internet Computing and Services
    ISSN 2287 - 1136 (Online) / ISSN 1598 - 0170 (Print)
    https://jics.or.kr/

Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation


Beanbonyka Rim, Junseob Kim, Yoo-Joo Choi, Min Hong, Journal of Internet Computing and Services, Vol. 21, No. 5, pp. 21-29, Oct. 2020
10.7472/jksii.2020.21.5.21, Full Text:
Keywords: Deep Learning, Human Pose Estimation, CNN, VGG, ResNet

Abstract

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Rim, B., Kim, J., Choi, Y., & Hong, M. (2020). Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation. Journal of Internet Computing and Services, 21(5), 21-29. DOI: 10.7472/jksii.2020.21.5.21.

[IEEE Style]
B. Rim, J. Kim, Y. Choi, M. Hong, "Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation," Journal of Internet Computing and Services, vol. 21, no. 5, pp. 21-29, 2020. DOI: 10.7472/jksii.2020.21.5.21.

[ACM Style]
Beanbonyka Rim, Junseob Kim, Yoo-Joo Choi, and Min Hong. 2020. Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation. Journal of Internet Computing and Services, 21, 5, (2020), 21-29. DOI: 10.7472/jksii.2020.21.5.21.