3D Data Augmented Person Re-identification and Edge-based Implementation

Ziyang Bian; Liang Ma; Jianan Li; Tingfa Xu

doi:10.1007/978-981-99-1256-8_37

3D Data Augmented Person Re-identification and Edge-based Implementation

Ziyang Bian, Liang Ma, Jianan Li^*, Tingfa Xu

^*Corresponding author for this work

School of Optics and Photonics

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

Abstract

In recent years, artificial intelligence technology has made breakthrough progress. It is widely used in person re-identification(Re-ID), but its accuracy still needs to be improved. This paper proposes a person re-identification(Re-ID) model based on 3D data augmentation and designs and implements edge computing deployment. The 3D human body model is put into the 3D scene and take automatic virtual photography to obtain the simulation image data. The neural network model is trained through the expanded data set of 3D simulation, and its improvement is significant. Based on this, an onboard scheme of artificial intelligence edge computing based on the Rock chips 3588 was designed to meet the practical needs of person re-identification(Re-ID) applications. This scheme is widely compatible with standard IP cameras based on RTSP/RTMP streams, supports person re-identification of visible and infrared video streams, can control the PTZ through the network interface, and can be updated and iterated remotely through the network.

Original language	English
Title of host publication	Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China
Editors	Qilian Liang, Wei Wang, Jiasong Mu, Xin Liu, Zhenyu Na
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	312-319
Number of pages	8
ISBN (Print)	9789819912551
DOIs	https://doi.org/10.1007/978-981-99-1256-8_37
Publication status	Published - 2023
Event	4th International Conference on Artificial Intelligence in China, AIC 2022 - Changbaishan, China Duration: 22 Oct 2022 → 23 Oct 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	871 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	4th International Conference on Artificial Intelligence in China, AIC 2022
Country/Territory	China
City	Changbaishan
Period	22/10/22 → 23/10/22

Keywords

3D Data Augmentation
Edge Computing
Person Re-identification
Rock chips 3588

Access to Document

10.1007/978-981-99-1256-8_37

Cite this

Bian, Z., Ma, L., Li, J., & Xu, T. (2023). 3D Data Augmented Person Re-identification and Edge-based Implementation. In Q. Liang, W. Wang, J. Mu, X. Liu, & Z. Na (Eds.), Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China (pp. 312-319). (Lecture Notes in Electrical Engineering; Vol. 871 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-1256-8_37

Bian, Ziyang ; Ma, Liang ; Li, Jianan et al. / 3D Data Augmented Person Re-identification and Edge-based Implementation. Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China. editor / Qilian Liang ; Wei Wang ; Jiasong Mu ; Xin Liu ; Zhenyu Na. Springer Science and Business Media Deutschland GmbH, 2023. pp. 312-319 (Lecture Notes in Electrical Engineering).

@inproceedings{6ad68ffd394b4ec283151d3a77287b69,

title = "3D Data Augmented Person Re-identification and Edge-based Implementation",

abstract = "In recent years, artificial intelligence technology has made breakthrough progress. It is widely used in person re-identification(Re-ID), but its accuracy still needs to be improved. This paper proposes a person re-identification(Re-ID) model based on 3D data augmentation and designs and implements edge computing deployment. The 3D human body model is put into the 3D scene and take automatic virtual photography to obtain the simulation image data. The neural network model is trained through the expanded data set of 3D simulation, and its improvement is significant. Based on this, an onboard scheme of artificial intelligence edge computing based on the Rock chips 3588 was designed to meet the practical needs of person re-identification(Re-ID) applications. This scheme is widely compatible with standard IP cameras based on RTSP/RTMP streams, supports person re-identification of visible and infrared video streams, can control the PTZ through the network interface, and can be updated and iterated remotely through the network.",

keywords = "3D Data Augmentation, Edge Computing, Person Re-identification, Rock chips 3588",

author = "Ziyang Bian and Liang Ma and Jianan Li and Tingfa Xu",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 4th International Conference on Artificial Intelligence in China, AIC 2022 ; Conference date: 22-10-2022 Through 23-10-2022",

year = "2023",

doi = "10.1007/978-981-99-1256-8_37",

language = "English",

isbn = "9789819912551",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "312--319",

editor = "Qilian Liang and Wei Wang and Jiasong Mu and Xin Liu and Zhenyu Na",

booktitle = "Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China",

address = "Germany",

}

Bian, Z, Ma, L, Li, J & Xu, T 2023, 3D Data Augmented Person Re-identification and Edge-based Implementation. in Q Liang, W Wang, J Mu, X Liu & Z Na (eds), Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China. Lecture Notes in Electrical Engineering, vol. 871 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 312-319, 4th International Conference on Artificial Intelligence in China, AIC 2022, Changbaishan, China, 22/10/22. https://doi.org/10.1007/978-981-99-1256-8_37

3D Data Augmented Person Re-identification and Edge-based Implementation. / Bian, Ziyang; Ma, Liang; Li, Jianan et al.
Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China. ed. / Qilian Liang; Wei Wang; Jiasong Mu; Xin Liu; Zhenyu Na. Springer Science and Business Media Deutschland GmbH, 2023. p. 312-319 (Lecture Notes in Electrical Engineering; Vol. 871 LNEE).

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

TY - GEN

T1 - 3D Data Augmented Person Re-identification and Edge-based Implementation

AU - Bian, Ziyang

AU - Ma, Liang

AU - Li, Jianan

AU - Xu, Tingfa

PY - 2023

Y1 - 2023

N2 - In recent years, artificial intelligence technology has made breakthrough progress. It is widely used in person re-identification(Re-ID), but its accuracy still needs to be improved. This paper proposes a person re-identification(Re-ID) model based on 3D data augmentation and designs and implements edge computing deployment. The 3D human body model is put into the 3D scene and take automatic virtual photography to obtain the simulation image data. The neural network model is trained through the expanded data set of 3D simulation, and its improvement is significant. Based on this, an onboard scheme of artificial intelligence edge computing based on the Rock chips 3588 was designed to meet the practical needs of person re-identification(Re-ID) applications. This scheme is widely compatible with standard IP cameras based on RTSP/RTMP streams, supports person re-identification of visible and infrared video streams, can control the PTZ through the network interface, and can be updated and iterated remotely through the network.

AB - In recent years, artificial intelligence technology has made breakthrough progress. It is widely used in person re-identification(Re-ID), but its accuracy still needs to be improved. This paper proposes a person re-identification(Re-ID) model based on 3D data augmentation and designs and implements edge computing deployment. The 3D human body model is put into the 3D scene and take automatic virtual photography to obtain the simulation image data. The neural network model is trained through the expanded data set of 3D simulation, and its improvement is significant. Based on this, an onboard scheme of artificial intelligence edge computing based on the Rock chips 3588 was designed to meet the practical needs of person re-identification(Re-ID) applications. This scheme is widely compatible with standard IP cameras based on RTSP/RTMP streams, supports person re-identification of visible and infrared video streams, can control the PTZ through the network interface, and can be updated and iterated remotely through the network.

KW - 3D Data Augmentation

KW - Edge Computing

KW - Person Re-identification

KW - Rock chips 3588

UR - http://www.scopus.com/inward/record.url?scp=85152586741&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-1256-8_37

DO - 10.1007/978-981-99-1256-8_37

M3 - Conference contribution

AN - SCOPUS:85152586741

SN - 9789819912551

T3 - Lecture Notes in Electrical Engineering

SP - 312

EP - 319

BT - Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China

A2 - Liang, Qilian

A2 - Wang, Wei

A2 - Mu, Jiasong

A2 - Liu, Xin

A2 - Na, Zhenyu

PB - Springer Science and Business Media Deutschland GmbH

T2 - 4th International Conference on Artificial Intelligence in China, AIC 2022

Y2 - 22 October 2022 through 23 October 2022

ER -

Bian Z, Ma L, Li J , Xu T. 3D Data Augmented Person Re-identification and Edge-based Implementation. In Liang Q, Wang W, Mu J, Liu X, Na Z, editors, Artificial Intelligence in China - Proceedings of the 4th International Conference on Artificial Intelligence in China. Springer Science and Business Media Deutschland GmbH. 2023. p. 312-319. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-99-1256-8_37