Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose EstimationEmpirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation
- Other Titles
- Empirical Comparison of Deep Learning Networks on Backbone Method of Human Pose Estimation
- Authors
- 림빈보니카; 김준섭; 최유주; 홍민
- Issue Date
- 2020
- Publisher
- 한국인터넷정보학회
- Keywords
- Deep learning; human pose estimation; CNN; VGG; Resnet
- Citation
- 인터넷정보학회논문지, v.21, no.5, pp.21 - 29
- Journal Title
- 인터넷정보학회논문지
- Volume
- 21
- Number
- 5
- Start Page
- 21
- End Page
- 29
- URI
- https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/3388
- DOI
- 10.7472/jksii.2020.21.5.21
- ISSN
- 1598-0170
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Department of Computer Software Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.