Multiscale Crowd Counting and Localization By Multitask Point Supervision

TL;DR

This paper introduces a multitask framework for crowd counting and localization that leverages multiscale representations and point supervision, outperforming density-based methods on popular datasets.

Contribution

It presents a novel multiscale, multitask approach that jointly addresses crowd counting and localization using point supervision, with demonstrated superior performance.

Findings

Achieves MSE of 110.7 and 15.0 on ShanghaiTech A and B for counting.

Attains AP of 0.71 and 0.75 on ShanghaiTech A and B for localization.

Shows the effectiveness of multiscale fusion and ablation studies.

Abstract

We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them. In contrast to the relatively more popular density-based methods, our model uses point supervision to allow for crowd locations to be accurately identified. We test our model on two popular crowd counting datasets, ShanghaiTech A and B, and demonstrate that our method achieves strong results on both counting and localization tasks, with MSE measures of 110.7 and 15.0 for crowd counting and AP measures of 0.71 and 0.75 for localization, on ShanghaiTech A and B respectively. Our detailed ablation experiments show the impact of our multiscale approach as well as the effectiveness of the fusion module embedded in our network. Our code is available at: https://github.com/RCVLab-AiimLab/crowd_counting.