Stacked dense-hourglass networks for human pose estimation

Convolutional Neural Networks (CNNs) are driving major advances in many computer vision tasks, including the problem of 2D single-person pose estimation. For this task, the Stacked Hourglass Networks (Stack-HgNets) is one of the state-of-the-art architecture that uses residual modules extensively as the basic building block. The residual modules are well recognized for creating shortcut connections, skipping one or more layers which allows information and gradients to flow more effectively through a deep network without vanishing. In this work, we build on the Stack-HgNets and introduce the Stacked Dense-Hourglass Networks (Stack-DenseHgNets). They use dense blocks instead of the residual modules as the basic building block. The dense blocks create more direct connections between each layer and its subsequent successors, granting later filters the access to all the preceding feature-maps inside the same block. Therefore, dense blocks serve as the upgraded substitution for the residual modules. We evaluate the Stack-DenseHgNets on the popular human pose estimation benchmark dataset and compare its performance to the original Stack-HgNets. Using fewer parameters, the Stack-DenseHgNets obtains a performance competitive to the state-of-the-art results on the MPII Human Pose Dataset.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2018

Author dc:creator

• Wang, Dongbo

Contributors dc:contributor

• Schwing, Alexander

• Stacked Hourglass Networks
• DenseNets
• Pose Estimation

Statement dc:rights

• Copyright 2018 Dongbo Wang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/101155

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/101155