Hierarchical Adversarial Network for Human Pose Estimation

Ibrahim Hamed Ismail RADWAN, Nour Moustafa, Byron Keating, Kim-Kwang Raymond Choo, Roland GOECKE

Research output: Contribution to journalArticle

Abstract

This paper presents a novel adversarial deep neural network to estimate human poses from still images, such as those obtained from CCTV and the Internet-of-Things (IoT) devices. Specifically, the proposed adversarial deep neural network exhibits the spatial hierarchy of human body parts considering the fact that predicting the position of some parts is more challenging than others. The generative and the discriminative portions of the proposed adversarial deep neural network are designed to encode the spatial relationship between the parts in the first stage of the hierarchy (parents) and the parts in the second stage of the hierarchy (children). Each of the generator and the discriminator networks is designed as two components, which are sequentially connected together to infer rich appearance potentials and to encode not only the likelihood of the part’s existence but also the relationships between each body part and its parent. The method is evaluated on three different datasets, whose findings suggest that the proposed network achieves comparable results with other competing state-of-the-art approaches.
Original languageEnglish
Pages (from-to)103619-103628
Number of pages10
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 25 Jul 2019

Fingerprint

Closed circuit television systems
Discriminators
Deep neural networks
Internet of things

Cite this

RADWAN, I. H. I., Moustafa, N., Keating, B., Choo, K-K. R., & GOECKE, R. (2019). Hierarchical Adversarial Network for Human Pose Estimation. IEEE Access, 7, 103619-103628. https://doi.org/10.1109/ACCESS.2019.2931050
RADWAN, Ibrahim Hamed Ismail ; Moustafa, Nour ; Keating, Byron ; Choo, Kim-Kwang Raymond ; GOECKE, Roland. / Hierarchical Adversarial Network for Human Pose Estimation. In: IEEE Access. 2019 ; Vol. 7. pp. 103619-103628.
@article{6cb0da89834d4eb2b1fc422375cbdbba,
title = "Hierarchical Adversarial Network for Human Pose Estimation",
abstract = "This paper presents a novel adversarial deep neural network to estimate human poses from still images, such as those obtained from CCTV and the Internet-of-Things (IoT) devices. Specifically, the proposed adversarial deep neural network exhibits the spatial hierarchy of human body parts considering the fact that predicting the position of some parts is more challenging than others. The generative and the discriminative portions of the proposed adversarial deep neural network are designed to encode the spatial relationship between the parts in the first stage of the hierarchy (parents) and the parts in the second stage of the hierarchy (children). Each of the generator and the discriminator networks is designed as two components, which are sequentially connected together to infer rich appearance potentials and to encode not only the likelihood of the part’s existence but also the relationships between each body part and its parent. The method is evaluated on three different datasets, whose findings suggest that the proposed network achieves comparable results with other competing state-of-the-art approaches.",
keywords = "Human pose estimation, Hierarchical Adversarial Network",
author = "RADWAN, {Ibrahim Hamed Ismail} and Nour Moustafa and Byron Keating and Choo, {Kim-Kwang Raymond} and Roland GOECKE",
year = "2019",
month = "7",
day = "25",
doi = "10.1109/ACCESS.2019.2931050",
language = "English",
volume = "7",
pages = "103619--103628",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

RADWAN, IHI, Moustafa, N, Keating, B, Choo, K-KR & GOECKE, R 2019, 'Hierarchical Adversarial Network for Human Pose Estimation', IEEE Access, vol. 7, pp. 103619-103628. https://doi.org/10.1109/ACCESS.2019.2931050

Hierarchical Adversarial Network for Human Pose Estimation. / RADWAN, Ibrahim Hamed Ismail; Moustafa, Nour; Keating, Byron; Choo, Kim-Kwang Raymond; GOECKE, Roland.

In: IEEE Access, Vol. 7, 25.07.2019, p. 103619-103628.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Hierarchical Adversarial Network for Human Pose Estimation

AU - RADWAN, Ibrahim Hamed Ismail

AU - Moustafa, Nour

AU - Keating, Byron

AU - Choo, Kim-Kwang Raymond

AU - GOECKE, Roland

PY - 2019/7/25

Y1 - 2019/7/25

N2 - This paper presents a novel adversarial deep neural network to estimate human poses from still images, such as those obtained from CCTV and the Internet-of-Things (IoT) devices. Specifically, the proposed adversarial deep neural network exhibits the spatial hierarchy of human body parts considering the fact that predicting the position of some parts is more challenging than others. The generative and the discriminative portions of the proposed adversarial deep neural network are designed to encode the spatial relationship between the parts in the first stage of the hierarchy (parents) and the parts in the second stage of the hierarchy (children). Each of the generator and the discriminator networks is designed as two components, which are sequentially connected together to infer rich appearance potentials and to encode not only the likelihood of the part’s existence but also the relationships between each body part and its parent. The method is evaluated on three different datasets, whose findings suggest that the proposed network achieves comparable results with other competing state-of-the-art approaches.

AB - This paper presents a novel adversarial deep neural network to estimate human poses from still images, such as those obtained from CCTV and the Internet-of-Things (IoT) devices. Specifically, the proposed adversarial deep neural network exhibits the spatial hierarchy of human body parts considering the fact that predicting the position of some parts is more challenging than others. The generative and the discriminative portions of the proposed adversarial deep neural network are designed to encode the spatial relationship between the parts in the first stage of the hierarchy (parents) and the parts in the second stage of the hierarchy (children). Each of the generator and the discriminator networks is designed as two components, which are sequentially connected together to infer rich appearance potentials and to encode not only the likelihood of the part’s existence but also the relationships between each body part and its parent. The method is evaluated on three different datasets, whose findings suggest that the proposed network achieves comparable results with other competing state-of-the-art approaches.

KW - Human pose estimation

KW - Hierarchical Adversarial Network

UR - https://ieeexplore.ieee.org/document/8772037?source=authoralert

U2 - 10.1109/ACCESS.2019.2931050

DO - 10.1109/ACCESS.2019.2931050

M3 - Article

VL - 7

SP - 103619

EP - 103628

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -