EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Person Re-Identification through Attention-Driven Global Features and Angular Loss Optimization

Yihan Bi, Rong Wang, Qianli Zhou, Ronghui Lin, Mingjie Wang

Entropy · 21.05.2024 · 26 (6) · 436

DOI: 10.3390/e26060436 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 21.05.2024. Verfasst von Yihan Bi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Double First-Class Innovation Research Project for People's Public Security University of China, Double First-Class Innovation Research Project for the People’s Public Security University of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address challenges related to the inadequate representation and inaccurate discrimination of pedestrian attributes, we propose a novel method for person re-identification, which leverages global feature learning and classification optimization. Specifically, this approach integrates a Normalization-based Channel Attention Module into the fundamental ResNet50 backbone, utilizing a scaling factor to prioritize and enhance key pedestrian feature information. Furthermore, dynamic activation functions are employed to adaptively modulate the parameters of ReLU based on the input convolutional feature maps, thereby bolstering the nonlinear expression capabilities of the network model. By incorporating Arcface loss into the cross-entropy loss, the supervised model is trained to learn pedestrian features that exhibit significant inter-class variance while maintaining tight intra-class coherence. The evaluation of the enhanced model on two popular datasets, Market1501 and DukeMTMC-ReID, reveals improvements in Rank-1 accuracy by 1.28% and 1.4%, respectively, along with corresponding gains in the mean average precision (mAP) of 1.93% and 1.84%. These findings indicate that the proposed model is capable of extracting more robust pedestrian features, enhancing feature discriminability, and ultimately achieving superior recognition accuracy.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismclassification loss optimizationglobal feature learningperson re-identification

Autor:innen und Institutionen

  • School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China.
  • Key Laboratory of Security Prevention Technology and Risk Assessment of Ministry of Public Security, Beijing 100038, China.
  • Beijing Public Security Bureau, Beijing 100038, China.

Förderung

  • Double First-Class Innovation Research Project for People's Public Security University of China
  • Double First-Class Innovation Research Project for the People’s Public Security University of China

Zitieren

APA

Bi, Y., Wang, R., Zhou, Q., Lin, R., & Wang, M. (2024). Enhancing Person Re-Identification through Attention-Driven Global Features and Angular Loss Optimization. Entropy, 26(6), 436. https://doi.org/10.3390/e26060436

Vancouver

Bi Y, Wang R, Zhou Q, Lin R, Wang M. Enhancing Person Re-Identification through Attention-Driven Global Features and Angular Loss Optimization. Entropy. 2024;26(6):436. doi:10.3390/e26060436

BibTeX
@article{Bi2024,
  author = {Bi, Yihan and Wang, Rong and Zhou, Qianli and Lin, Ronghui and Wang, Mingjie},
  title = {Enhancing Person Re-Identification through Attention-Driven Global Features and Angular Loss Optimization},
  journal = {Entropy},
  year = {2024},
  volume = {26},
  number = {6},
  pages = {436},
  doi = {10.3390/e26060436}
}
Kostenlos starten →