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
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
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 -