MCNet: A crowd denstity estimation network based on integrating multiscale attention module

TL;DR

This paper introduces MCNet, a novel crowd density estimation network that combines a multiscale attention module with a lightweight feature extractor, optimized for real-time metro surveillance with limited hardware.

Contribution

The paper proposes the IMA module for enhanced semantic feature extraction and a lightweight network for efficient crowd density estimation, suitable for embedded systems.

Findings

Effective crowd texture feature extraction demonstrated on multiple datasets.

Improved accuracy in high-density, occluded, and perspective-distorted scenes.

Faster processing speed with fewer parameters suitable for embedded deployment.

Abstract

Aiming at the metro video surveillance system has not been able to effectively solve the metro crowd density estimation problem, a Metro Crowd density estimation Network (called MCNet) is proposed to automatically classify crowd density level of passengers. Firstly, an Integrating Multi-scale Attention (IMA) module is proposed to enhance the ability of the plain classifiers to extract semantic crowd texture features to accommodate to the characteristics of the crowd texture feature. The innovation of the IMA module is to fuse the dilation convolution, multiscale feature extraction and attention mechanism to obtain multi-scale crowd feature activation from a larger receptive field with lower computational cost, and to strengthen the crowds activation state of convolutional features in top layers. Secondly, a novel lightweight crowd texture feature extraction network is proposed, which can directly process video frames and automatically extract texture features for crowd density estimation, while its faster image processing speed and fewer network parameters make it flexible to be deployed on embedded platforms with limited hardware resources. Finally, this paper integrates IMA module and the lightweight crowd texture feature extraction network to construct the MCNet, and validate the feasibility of this network on image classification dataset: Cifar10 and four crowd density datasets: PETS2009, Mall, QUT and SH_METRO to validate the MCNet whether can be a suitable solution for crowd density estimation in metro video surveillance where there are image processing challenges such as high density, high occlusion, perspective distortion and limited hardware resources.