Focal Inverse Distance Transform Maps for Crowd Localization

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.

Accepted by IEEE Transactions on Multimedia (TMM). The code and models are available at https://github.com/dk-liang/FIDTM

References in corpus (6)

• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• TransCrowd: weakly-supervised crowd counting with transformers
• Distribution Matching for Crowd Counting
• A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
• Learning Independent Instance Maps for Crowd Localization
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds

Cited by in corpus (5)

• TransCrowd: weakly-supervised crowd counting with transformers
• DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
• Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher
• Learning Discriminative Features for Crowd Counting
• The Effectiveness of a Simplified Model Structure for Crowd Counting