Iterative Crowd Counting

TL;DR

This paper introduces a two-branch CNN architecture with a multi-stage extension for high-resolution crowd density map estimation, significantly improving accuracy on benchmark datasets.

Contribution

The paper proposes a novel multi-stage, two-branch CNN approach for crowd counting that enhances density map resolution and accuracy over previous methods.

Findings

Achieves lowest mean absolute error on Shanghaitech dataset

Outperforms previous methods on WorldExpo'10 and UCF datasets

Demonstrates effectiveness of multi-stage density estimation

Abstract

In this work, we tackle the problem of crowd counting in images. We present a Convolutional Neural Network (CNN) based density estimation approach to solve this problem. Predicting a high resolution density map in one go is a challenging task. Hence, we present a two branch CNN architecture for generating high resolution density maps, where the first branch generates a low resolution density map, and the second branch incorporates the low resolution prediction and feature maps from the first branch to generate a high resolution density map. We also propose a multi-stage extension of our approach where each stage in the pipeline utilizes the predictions from all the previous stages. Empirical comparison with the previous state-of-the-art crowd counting methods shows that our method achieves the lowest mean absolute error on three challenging crowd counting benchmarks: Shanghaitech, WorldExpo'10, and UCF datasets.