Multidimensional Measure Matching for Crowd Counting

Hui Lin

doi:10.1109/TNNLS.2024.3435854

Multidimensional Measure Matching for Crowd Counting

2024-01-01

0

PRE

AI

DOI：10.1109/TNNLS.2024.3435854

Original

Original request for help

Save

Abstract

En 中文

This article addresses the challenge of scale variations in crowd-counting problems from a multidimensional measure-theoretic perspective. We start by formulating crowd counting as a measure-matching problem, based on the assumption that discrete measures can express the scattered ground truth and the predicted density map. In this context, we introduce the Sinkhorn counting loss and extend it to the semi-balanced form, which alleviates the problems including entropic bias, distance destruction, and amount constraints. We then model the measure matching under the multidimensional space, in order to learn the counting from both location and scale. To achieve this, we extend the traditional 2-D coordinate support to 3-D, incorporating an additional axis to represent scale information, where a pyramid-based structure will be leveraged to learn the scale value for the predicted density. Extensive experiments on four challenging crowd-counting datasets, namely, ShanghaiTech A, UCF-QNRF, JHU ++, and NWPU have validated the proposed method. Code is released at https://github.com/LoraLinH/Multidimensional-Measure-Matching-for-Crowd-Counting.

Keywords:

Estimation

Annotations

Transformers

Kernel

Density measurement

Computer vision

Training

Crowd counting

deep learning

multiscale

Sinkhorn divergence

Multidimensional Measure Matching for Crowd Counting

Abstract

Journal

Organization