Generation of pedestrian pose structures using generative adversarial networks

James Spooner; Madeline Cheah; Vasile Palade; Stratis Kanarachos; Alireza Daneshkhah

doi:10.1109/ICMLA.2019.00269

Generation of pedestrian pose structures using generative adversarial networks

James Spooner, Madeline Cheah, Vasile Palade, Stratis Kanarachos, Alireza Daneshkhah

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited, and furthermore, the available data does not have a fair representation of different scenarios and rare events. This work presents a novel approach for the generation of human pose structures, specifically the type of pose structures that would appear to be in pedestrian scenarios. The results show that the generated pedestrian structures are indistinguishable from the ground truth pose structures when classified using a suitably trained classifier. The paper demonstrates that the Generative Adversarial Network architecture can be used to create realistic new training samples, and, in future, new pedestrian events.

Original language	English
Title of host publication	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Editors	M. Arif Wani, Taghi M. Khoshgoftaar, Dingding Wang, Huanjing Wang, Naeem Seliya
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1644-1650
Number of pages	7
ISBN (Electronic)	9781728145495
DOIs	https://doi.org/10.1109/ICMLA.2019.00269
Publication status	Published - 17 Feb 2020
Event	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 - Boca Raton, United States Duration: 16 Dec 2019 → 19 Dec 2019

Publication series

Name	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Conference

Conference	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Country/Territory	United States
City	Boca Raton
Period	16/12/19 → 19/12/19

Keywords

Autonomous Driving
GANs
Neural Networks
Pedestrians
Pose estimation

ASJC Scopus subject areas

Strategy and Management
Artificial Intelligence
Computer Science Applications
Decision Sciences (miscellaneous)
Signal Processing
Media Technology

Access to Document

10.1109/ICMLA.2019.00269

Cite this

Spooner, J., Cheah, M., Palade, V., Kanarachos, S., & Daneshkhah, A. (2020). Generation of pedestrian pose structures using generative adversarial networks. In M. A. Wani, T. M. Khoshgoftaar, D. Wang, H. Wang, & N. Seliya (Eds.), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 (pp. 1644-1650). Article 8999199 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2019.00269

Generation of pedestrian pose structures using generative adversarial networks. / Spooner, James; Cheah, Madeline; Palade, Vasile et al.
Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. ed. / M. Arif Wani; Taghi M. Khoshgoftaar; Dingding Wang; Huanjing Wang; Naeem Seliya. Institute of Electrical and Electronics Engineers Inc., 2020. p. 1644-1650 8999199 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Spooner, J, Cheah, M, Palade, V, Kanarachos, S & Daneshkhah, A 2020, Generation of pedestrian pose structures using generative adversarial networks. in MA Wani, TM Khoshgoftaar, D Wang, H Wang & N Seliya (eds), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019., 8999199, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1644-1650, 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, Boca Raton, Florida, United States, 16/12/19. https://doi.org/10.1109/ICMLA.2019.00269

Spooner J, Cheah M, Palade V, Kanarachos S, Daneshkhah A. Generation of pedestrian pose structures using generative adversarial networks. In Wani MA, Khoshgoftaar TM, Wang D, Wang H, Seliya N, editors, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1644-1650. 8999199. (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). doi: 10.1109/ICMLA.2019.00269

Spooner, James ; Cheah, Madeline ; Palade, Vasile et al. / Generation of pedestrian pose structures using generative adversarial networks. Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. editor / M. Arif Wani ; Taghi M. Khoshgoftaar ; Dingding Wang ; Huanjing Wang ; Naeem Seliya. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 1644-1650 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

@inproceedings{af25387554ac45a3aa69f8e3a8fc9c2a,

title = "Generation of pedestrian pose structures using generative adversarial networks",

abstract = "The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited, and furthermore, the available data does not have a fair representation of different scenarios and rare events. This work presents a novel approach for the generation of human pose structures, specifically the type of pose structures that would appear to be in pedestrian scenarios. The results show that the generated pedestrian structures are indistinguishable from the ground truth pose structures when classified using a suitably trained classifier. The paper demonstrates that the Generative Adversarial Network architecture can be used to create realistic new training samples, and, in future, new pedestrian events.",

keywords = "Autonomous Driving, GANs, Neural Networks, Pedestrians, Pose estimation",

author = "James Spooner and Madeline Cheah and Vasile Palade and Stratis Kanarachos and Alireza Daneshkhah",

year = "2020",

month = feb,

day = "17",

doi = "10.1109/ICMLA.2019.00269",

language = "English",

series = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1644--1650",

editor = "Wani, {M. Arif} and Khoshgoftaar, {Taghi M.} and Dingding Wang and Huanjing Wang and Naeem Seliya",

booktitle = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

address = "United States",

note = "18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 ; Conference date: 16-12-2019 Through 19-12-2019",

}

TY - GEN

T1 - Generation of pedestrian pose structures using generative adversarial networks

AU - Spooner, James

AU - Cheah, Madeline

AU - Palade, Vasile

AU - Kanarachos, Stratis

AU - Daneshkhah, Alireza

PY - 2020/2/17

Y1 - 2020/2/17

N2 - The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited, and furthermore, the available data does not have a fair representation of different scenarios and rare events. This work presents a novel approach for the generation of human pose structures, specifically the type of pose structures that would appear to be in pedestrian scenarios. The results show that the generated pedestrian structures are indistinguishable from the ground truth pose structures when classified using a suitably trained classifier. The paper demonstrates that the Generative Adversarial Network architecture can be used to create realistic new training samples, and, in future, new pedestrian events.

AB - The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited, and furthermore, the available data does not have a fair representation of different scenarios and rare events. This work presents a novel approach for the generation of human pose structures, specifically the type of pose structures that would appear to be in pedestrian scenarios. The results show that the generated pedestrian structures are indistinguishable from the ground truth pose structures when classified using a suitably trained classifier. The paper demonstrates that the Generative Adversarial Network architecture can be used to create realistic new training samples, and, in future, new pedestrian events.

KW - Autonomous Driving

KW - GANs

KW - Neural Networks

KW - Pedestrians

KW - Pose estimation

UR - http://www.scopus.com/inward/record.url?scp=85080886700&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2019.00269

DO - 10.1109/ICMLA.2019.00269

M3 - Conference proceeding

AN - SCOPUS:85080886700

T3 - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

SP - 1644

EP - 1650

BT - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

A2 - Wani, M. Arif

A2 - Khoshgoftaar, Taghi M.

A2 - Wang, Dingding

A2 - Wang, Huanjing

A2 - Seliya, Naeem

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Y2 - 16 December 2019 through 19 December 2019

ER -

Generation of pedestrian pose structures using generative adversarial networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this