Consistency-Aware Anchor Pyramid Network for Crowd Localization

TL;DR

This paper introduces a consistency-aware anchor pyramid network for crowd localization that adaptively adjusts anchor density and reduces ranking inconsistency, improving accuracy across multiple datasets.

Contribution

It proposes a novel supervision target reassignment strategy and an anchor pyramid scheme to enhance crowd localization performance.

Findings

Outperforms state-of-the-art methods on multiple datasets

Reduces ranking inconsistency between training and testing

Effectively adapts anchor density to local crowd densities

Abstract

Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A\&B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods.