A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition

Xingyu Qian; Aximu Yuemaier; Wenchi Yang; Xiaogang Chen; Longfei Liang; Shunfen Li; Weibang Dai; Zhitang Song

doi:10.3390/s23125435

A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition

Xingyu Qian, Aximu Yuemaier, Wenchi Yang, Xiaogang Chen^*, Longfei Liang, Shunfen Li, Weibang Dai, Zhitang Song

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Video behavior recognition often needs to focus on object motion processes. In this work, a self-organizing computational system oriented toward behavioral clustering recognition is proposed, which achieves the extraction of motion change patterns through binary encoding and completes motion pattern summarization using a similarity comparison algorithm. Furthermore, in the face of unknown behavioral video data, a self-organizing structure with layer-by-layer accuracy progression is used to achieve motion law summarization using a multi-layer agent design approach. Finally, the real-time feasibility is verified in the prototype system using real scenes to provide a new feasible solution for unsupervised behavior recognition and space-time scenes.

Original language	English
Article number	5435
Journal	Sensors
Volume	23
Issue number	12
DOIs	https://doi.org/10.3390/s23125435
Publication status	Published - Jun 2023
Externally published	Yes

Keywords

action clustering
field programmable gate array (FPGA)
hardware implementation
real-time system

Access to Document

10.3390/s23125435

Cite this

Qian, X., Yuemaier, A., Yang, W., Chen, X., Liang, L., Li, S., Dai, W., & Song, Z. (2023). A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition. Sensors, 23(12), Article 5435. https://doi.org/10.3390/s23125435

@article{ab9d4559b6be4470a810c8f568df8c3b,

title = "A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition",

abstract = "Video behavior recognition often needs to focus on object motion processes. In this work, a self-organizing computational system oriented toward behavioral clustering recognition is proposed, which achieves the extraction of motion change patterns through binary encoding and completes motion pattern summarization using a similarity comparison algorithm. Furthermore, in the face of unknown behavioral video data, a self-organizing structure with layer-by-layer accuracy progression is used to achieve motion law summarization using a multi-layer agent design approach. Finally, the real-time feasibility is verified in the prototype system using real scenes to provide a new feasible solution for unsupervised behavior recognition and space-time scenes.",

keywords = "action clustering, field programmable gate array (FPGA), hardware implementation, real-time system",

author = "Xingyu Qian and Aximu Yuemaier and Wenchi Yang and Xiaogang Chen and Longfei Liang and Shunfen Li and Weibang Dai and Zhitang Song",

note = "Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = jun,

doi = "10.3390/s23125435",

language = "English",

volume = "23",

journal = "Sensors",

issn = "1424-8220",

publisher = "MDPI (Basel, Switzerland) ",

number = "12",

}

TY - JOUR

T1 - A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition

AU - Qian, Xingyu

AU - Yuemaier, Aximu

AU - Yang, Wenchi

AU - Chen, Xiaogang

AU - Liang, Longfei

AU - Li, Shunfen

AU - Dai, Weibang

AU - Song, Zhitang

PY - 2023/6

Y1 - 2023/6

N2 - Video behavior recognition often needs to focus on object motion processes. In this work, a self-organizing computational system oriented toward behavioral clustering recognition is proposed, which achieves the extraction of motion change patterns through binary encoding and completes motion pattern summarization using a similarity comparison algorithm. Furthermore, in the face of unknown behavioral video data, a self-organizing structure with layer-by-layer accuracy progression is used to achieve motion law summarization using a multi-layer agent design approach. Finally, the real-time feasibility is verified in the prototype system using real scenes to provide a new feasible solution for unsupervised behavior recognition and space-time scenes.

AB - Video behavior recognition often needs to focus on object motion processes. In this work, a self-organizing computational system oriented toward behavioral clustering recognition is proposed, which achieves the extraction of motion change patterns through binary encoding and completes motion pattern summarization using a similarity comparison algorithm. Furthermore, in the face of unknown behavioral video data, a self-organizing structure with layer-by-layer accuracy progression is used to achieve motion law summarization using a multi-layer agent design approach. Finally, the real-time feasibility is verified in the prototype system using real scenes to provide a new feasible solution for unsupervised behavior recognition and space-time scenes.

KW - action clustering

KW - field programmable gate array (FPGA)

KW - hardware implementation

KW - real-time system

UR - http://www.scopus.com/inward/record.url?scp=85163954824&partnerID=8YFLogxK

U2 - 10.3390/s23125435

DO - 10.3390/s23125435

M3 - Article

C2 - 37420602

AN - SCOPUS:85163954824

SN - 1424-8220

VL - 23

JO - Sensors

JF - Sensors

IS - 12

M1 - 5435

ER -

A Self-Organizing Multi-Layer Agent Computing System for Behavioral Clustering Recognition

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this