| Autor: |
Abdullah N Alhawsawi, Sultan Daud Khan, Faizan Ur Rehman |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Information, Vol 15, Iss 5, p 275 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2078-2489 |
| DOI: |
10.3390/info15050275 |
| Popis: |
Automated crowd counting is a crucial aspect of surveillance, especially in the context of mass events attended by large populations. Traditional methods of manually counting the people attending an event are error-prone, necessitating the development of automated methods. Accurately estimating crowd counts across diverse scenes is challenging due to high variations in the sizes of human heads. Regression-based crowd-counting methods often overestimate counts in low-density situations, while detection-based models struggle in high-density scenarios to precisely detect the head. In this work, we propose a unified framework that integrates regression and detection models to estimate the crowd count in diverse scenes. Our approach leverages a routing strategy based on crowd density variations within an image. By classifying image patches into density levels and employing a Patch-Routing Module (PRM) for routing, the framework directs patches to either the Detection or Regression Network to estimate the crowd count. The proposed framework demonstrates superior performance across various datasets, showcasing its effectiveness in handling diverse scenes. By effectively integrating regression and detection models, our approach offers a comprehensive solution for accurate crowd counting in scenarios ranging from low-density to high-density situations. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
