Towards real-world monitoring scenarios: An improved point prediction method for crowd counting based on contrastive learning
PLOS One · 2025
DOI: 10.1371/journal.pone.0327397 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Rundong Cao und 3 weiteren Autor:innen. Beteiligte Einrichtung: China Tower Corporation Limited, Beijing, China. Hauptthemen laut MEDLINE: Crowding, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In open environments, complex and variable backgrounds and dense multi-scale targets are two key challenges for crowd counting. Due to the reliance on supervised learning with labeled data, current methods struggle to adapt to crowd detection in complex scenarios when training data is limited; Moreover, detection-based methods may lead to numerous missed detections when dealing with dense, small-scale target groups. This paper proposes a simple yet effective point-based contrastive learning method to alleviate these issues. Initially, we construct contrastive cropped samples and feed them into a convolutional neural network to predict head points of each image patch. Based on the classification and regression loss of these points, we incorporate an auxiliary supervision contrastive learning loss to enhance the model’s ability to differentiate between foreground heads and the background. Additionally, a multi-scale feature fusion module is proposed to obtain high-quality feature maps for detecting targets of different scales. Comparative experimental results on public crowd counting datasets demonstrate that the proposed method achieves state-of-the-art performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- China Tower Corporation Limited, Beijing, China.
ORCID-Profile: Rundong Cao
Zitieren
APA
Cao, R., Yu, J., Liu, Z., & Liang, Q. (2025). Towards real-world monitoring scenarios: An improved point prediction method for crowd counting based on contrastive learning. PLOS One. https://doi.org/10.1371/journal.pone.0327397
Vancouver
Cao R, Yu J, Liu Z, Liang Q. Towards real-world monitoring scenarios: An improved point prediction method for crowd counting based on contrastive learning. PLOS One. 2025. doi:10.1371/journal.pone.0327397
BibTeX
@article{Cao2025,
author = {Cao, Rundong and Yu, Jiazhong and Liu, Ziwei and Liang, Qinghua},
title = {Towards real-world monitoring scenarios: An improved point prediction method for crowd counting based on contrastive learning},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0327397}
}
EUVIMED