EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Height reverse perspective transformation for crowd counting

Xiaomei Zhao, Honggang Li, Zhan Zhao, Shuo Li

Frontiers in Imaging · 2023

DOI: 10.3389/fimag.2023.1271885 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Imaging, 2023. Verfasst von Xiaomei Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Crowd counting plays a critical role in the intelligent video surveillance of public areas. A significant challenge to this task is the perspective effect on human heads, which causes serious scale variations. Height reverse perspective transformation (HRPT) alleviates this problem by narrowing the height gap among human heads.

Methods

It employs depth maps to calculate the rescaling factors of image rows, and then it performs image transformation accordingly. HRPT enlarges small human heads in far areas to make them more noticeable and shrinks large human heads in closer areas to reduce redundant information. Then, convolutional neural networks can be used for crowd counting. Previous crowd-counting methods mainly solve the scale variation problem by designing specific networks, such as multi-scale or perspective-aware networks. These networks cannot be conveniently employed by other methods. In contrast, HRPT solves the scale variation problem through image transformation. It can be used as a preprocessing step and easily employed by other crowd-counting methods without changing their original structures. Results and discussion Experimental results show that HRPT successfully narrows the height gap among human heads and achieves state-of-the-art performance on a large crowd-counting RGB-D dataset.

Förderung

  • Natural Science Foundation of Shandong Province

Zitieren

APA

Zhao, X., Li, H., Zhao, Z., & Li, S. (2023). Height reverse perspective transformation for crowd counting. Frontiers in Imaging. https://doi.org/10.3389/fimag.2023.1271885

Vancouver

Zhao X, Li H, Zhao Z, Li S. Height reverse perspective transformation for crowd counting. Frontiers in Imaging. 2023. doi:10.3389/fimag.2023.1271885

BibTeX
@article{Zhao2023,
  author = {Zhao, Xiaomei and Li, Honggang and Zhao, Zhan and Li, Shuo},
  title = {Height reverse perspective transformation for crowd counting},
  journal = {Frontiers in Imaging},
  year = {2023},
  doi = {10.3389/fimag.2023.1271885}
}
Kostenlos starten →