Crowd counting with crowd attention convolutional neural network

TL;DR

This paper introduces CAT-CNN, a novel end-to-end deep learning model that improves crowd counting accuracy by adaptively focusing on human heads using a confidence map, effectively handling scene complexity and scale variation.

Contribution

The paper presents a new crowd counting model that uses a confidence map to guide attention, enhancing density map accuracy and reducing errors caused by scene complexity.

Findings

Outperforms state-of-the-art methods on three challenging datasets.

Effectively reduces misjudgements caused by scene complexity.

Provides a refined density map for accurate crowd estimation.

Abstract

Crowd counting is a challenging problem due to the scene complexity and scale variation. Although deep learning has achieved great improvement in crowd counting, scene complexity affects the judgement of these methods and they usually regard some objects as people mistakenly; causing potentially enormous errors in the crowd counting result. To address the problem, we propose a novel end-to-end model called Crowd Attention Convolutional Neural Network (CAT-CNN). Our CAT-CNN can adaptively assess the importance of a human head at each pixel location by automatically encoding a confidence map. With the guidance of the confidence map, the position of human head in estimated density map gets more attention to encode the final density map, which can avoid enormous misjudgements effectively. The crowd count can be obtained by integrating the final density map. To encode a highly refined density map, the total crowd count of each image is classified in a designed classification task and we first explicitly map the prior of the population-level category to feature maps. To verify the efficiency of our proposed method, extensive experiments are conducted on three highly challenging datasets. Results establish the superiority of our method over many state-of-the-art methods.