EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Inception Convolution and Feature Fusion for Person Search

Huan Ouyang iD, Jiexian Zeng, Lu Leng

Sensors · 10.02.2023 · 23 (4) · 1984

DOI: 10.3390/s23041984 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.02.2023. Verfasst von Huan Ouyang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Nanchang Hangkong University, Nanchang 330063, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China under Grants, Jiangxi Provincial Key Program Project of Research and Development under Grant, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement of deep learning theory and hardware device computing capacity, computer vision tasks, such as object detection and instance segmentation, have entered a revolutionary phase in recent years. As a result, extremely challenging integrated tasks, such as person search, might develop quickly. The majority of efficient network frameworks, such as Seq-Net, are based on Faster R-CNN. However, because of the parallel structure of Faster R-CNN, the performance of re-ID can be significantly impacted by the single-layer, low resolution, and occasionally overlooked check feature diagrams retrieved during pedestrian detection. To address these issues, this paper proposed a person search methodology based on an inception convolution and feature fusion module (IC-FFM) using Seq-Net (Sequential End-to-end Network) as the benchmark. First, we replaced the general convolution in ResNet-50 with the new inception convolution module (ICM), allowing the convolution operation to effectively and dynamically distribute various channels. Then, to improve the accuracy of information extraction, the feature fusion module (FFM) was created to combine multi-level information using various levels of convolution. Finally, Bounding Box regression was created using convolution and the double-head module (DHM), which considerably enhanced the accuracy of pedestrian retrieval by combining global and fine-grained information. Experiments on CHUK-SYSU and PRW datasets showed that our method has higher accuracy than Seq-Net. In addition, our method is simpler and can be easily integrated into existing two-stage frameworks.

Schlagwörter

Stichwörter der Autor:innen

Faster R-CNNdouble-headefficient learningfeature fusioninception convolutionperson searchregion proposal network (RPN)

Autor:innen und Institutionen

  • School of Software, Nanchang Hangkong University, Nanchang 330063, China.
  • Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang 330063, China.
  • Science and Technology College, Nanchang Hangkong University, Gongqingcheng 332020, China.

ORCID-Profile: Huan Ouyang

Förderung

  • National Natural Science Foundation of China under Grants
  • Jiangxi Provincial Key Program Project of Research and Development under Grant
  • National Natural Science Foundation of China
  • Jiangxi Provincial Key Program Project of Research and Development
  • The technology Innovation Guidance Program Project

Zitieren

APA

Ouyang, H., Zeng, J., & Leng, L. (2023). Inception Convolution and Feature Fusion for Person Search. Sensors, 23(4), 1984. https://doi.org/10.3390/s23041984

Vancouver

Ouyang H, Zeng J, Leng L. Inception Convolution and Feature Fusion for Person Search. Sensors. 2023;23(4):1984. doi:10.3390/s23041984

BibTeX
@article{Ouyang2023,
  author = {Ouyang, Huan and Zeng, Jiexian and Leng, Lu},
  title = {Inception Convolution and Feature Fusion for Person Search},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {4},
  pages = {1984},
  doi = {10.3390/s23041984}
}
Kostenlos starten →