EUVIMEDEUVIMED entdecken
Crossref

Dilated Convolution-based Feature Refinement Network for Crowd Localization

Xingyu Gao, Jinyang Xie, Zhenyu Chen, An-An Liu, Zhenan Sun, Lei Lyu

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.11.2023 · 19 (6) · 1-16

DOI: 10.1145/3571134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 12.07.2023. Verfasst von Xingyu Gao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Science and Technology Innovation (STI) 2030-Major Projects, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As an emerging computer vision task, crowd localization has received increasing attention due to its ability to produce more accurate spatially predictions. However, continuous scale variations in complex crowd scenes lead to tiny individuals at the edges, so that existing methods cannot achieve precise crowd localization. Aiming at alleviating the above problems, we propose a novel Dilated Convolution-based Feature Refinement Network (DFRNet) to enhance the representation learning capability. Specifically, the DFRNet is built with three branches that can capture the information of each individual in crowd scenes more precisely. More specifically, we introduce a Feature Perception Module to model long-range contextual information at different scales by adopting multiple dilated convolutions, thus providing sufficient feature information to perceive tiny individuals at the edge of images. Afterwards, a Feature Refinement Module is deployed at multiple stages of the three branches to facilitate the mutual refinement of feature information at different scales, thus further improving the expression capability of multi-scale contextual information. By incorporating the above modules, DFRNet can locate individuals in complex scenes more precisely. Extensive experiments on multiple datasets demonstrate that the proposed method has more advanced performance compared to existing methods and can be more accurately adapted to complex crowd scenes.

Förderung

  • Science and Technology Innovation (STI) 2030-Major Projects
  • National Natural Science Foundation of China

Zitieren

APA

Gao, X., Xie, J., Chen, Z., Liu, A., Sun, Z., & Lyu, L. (2023). Dilated Convolution-based Feature Refinement Network for Crowd Localization. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(6), 1-16. https://doi.org/10.1145/3571134

Vancouver

Gao X, Xie J, Chen Z, Liu A, Sun Z, Lyu L. Dilated Convolution-based Feature Refinement Network for Crowd Localization. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(6):1-16. doi:10.1145/3571134

BibTeX
@article{Gao2023,
  author = {Gao, Xingyu and Xie, Jinyang and Chen, Zhenyu and Liu, An-An and Sun, Zhenan and Lyu, Lei},
  title = {Dilated Convolution-based Feature Refinement Network for Crowd Localization},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {6},
  pages = {1--16},
  doi = {10.1145/3571134}
}
Kostenlos starten →