Focal Inverse Distance Transform Maps for Crowd Localization

TL;DR

This paper introduces FIDT maps and a local maxima detection strategy to improve crowd localization accuracy, especially in dense scenes, outperforming existing methods across multiple datasets.

Contribution

The paper proposes a novel FIDT map representation and a local maxima detection method, enhancing crowd localization accuracy in dense scenes beyond prior density map regression approaches.

Findings

Achieves state-of-the-art localization performance on six crowd datasets.

Demonstrates robustness in extremely dense and negative scenes.

FIDT maps effectively eliminate overlaps in dense regions.

Abstract

In this paper, we focus on the crowd localization task, a crucial topic of crowd analysis. Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the density map consists of a series of blurry Gaussian blobs, 2) severe overlaps exist in the dense region of the density map. To tackle this issue, we propose a novel Focal Inverse Distance Transform (FIDT) map for the crowd localization task. Compared with the density maps, the FIDT maps accurately describe the persons' locations without overlapping in dense regions. Based on the FIDT maps, a Local-Maxima-Detection-Strategy (LMDS) is derived to effectively extract the center point for each individual. Furthermore, we introduce an Independent SSIM (I-SSIM) loss to make the model tend to learn the local structural information, better recognizing local maxima. Extensive experiments demonstrate that the proposed method reports state-of-the-art localization performance on six crowd datasets and one vehicle dataset. Additionally, we find that the proposed method shows superior robustness on the negative and extremely dense scenes, which further verifies the effectiveness of the FIDT maps. The code and model will be available at https://github.com/dk-liang/FIDTM.