# Crowd Gathering Detection Method Based on Multi-Scale Feature Fusion and Convolutional Attention

## TL;DR

This paper introduces a new method for detecting crowd gatherings using multi-scale features and attention mechanisms to improve accuracy in complex environments.

## Contribution

The novel contribution is the Multi-Scale Convolutional Attention Network (MSCANet) for dynamic crowd detection.

## Key findings

- MSCANet achieves high counting accuracy in dense and occluded environments.
- The method outperforms existing approaches by adapting to varying crowd densities.
- Experiments on public datasets show strong robustness and real-world potential.

## Abstract

With rapid urbanization and growing population inflows into metropolitan areas, crowd gatherings have become increasingly frequent and dense, posing significant challenges to public safety management. Although existing crowd gathering detection methods have achieved notable progress, they still face major limitations: most rely heavily on local texture or density features and lack the capacity to model contextual information, making them ineffective under severe occlusions and complex backgrounds. Additionally, fixed-scale feature extraction strategies struggle to adapt to crowd regions with varying densities and scales, and insufficient attention to densely populated areas hinders the capture of critical local features. To overcome these challenges, we propose a point-supervised framework named Multi-Scale Convolutional Attention Network (MSCANet). MSCANet adopts a context-aware architecture and integrates multi-scale feature extraction modules and convolutional attention mechanisms, enabling it to dynamically adapt to varying crowd densities while focusing on key regions. This enhances feature representation in complex scenes and improves detection performance. Extensive experiments on public datasets demonstrate that MSCANet achieves high counting accuracy and robustness, particularly in dense and occluded environments, showing strong potential for real-world deployment.