Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework

TL;DR

This paper introduces a novel point-based framework for crowd counting and localization, emphasizing direct point prediction and a new evaluation metric, leading to improved accuracy over existing methods.

Contribution

It proposes a purely point-based approach with a new metric and a direct prediction network, simplifying the process and enhancing performance in crowd analysis.

Findings

Outperforms state-of-the-art methods on counting benchmarks

Achieves promising localization accuracy

Introduces a new evaluation metric, density nAP

Abstract

Localizing individuals in crowds is more in accordance with the practical demands of subsequent high-level crowd analysis tasks than simply counting. However, existing localization based methods relying on intermediate representations (\textit{i.e.}, density maps or pseudo boxes) serving as learning targets are counter-intuitive and error-prone. In this paper, we propose a purely point-based framework for joint crowd counting and individual localization. For this framework, instead of merely reporting the absolute counting error at image level, we propose a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation. Moreover, we design an intuitive solution under this framework, which is called Point to Point Network (P2PNet). P2PNet discards superfluous steps and directly predicts a set of point proposals to represent heads in an image, being consistent with the human annotation results. By thorough analysis, we reveal the key step towards implementing such a novel idea is to assign optimal learning targets for these proposals. Therefore, we propose to conduct this crucial association in an one-to-one matching manner using the Hungarian algorithm. The P2PNet not only significantly surpasses state-of-the-art methods on popular counting benchmarks, but also achieves promising localization accuracy. The codes will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet.