Super-Resolution Information Enhancement For Crowd Counting

TL;DR

This paper introduces MSSRM, a plug-in module that enhances crowd counting accuracy on low-resolution images by improving detail features without increasing inference time, supported by a new SR-Crowd dataset.

Contribution

The paper proposes MSSRM, a novel plug-in module for crowd counting that improves detail recovery in low-resolution images without additional inference cost, and introduces the SR-Crowd dataset.

Findings

MSSRM significantly improves crowd counting accuracy on LR images.

The method outperforms existing approaches on three datasets.

The SR-Crowd dataset supports training and evaluation of SR-based crowd counting models.

Abstract

Crowd counting is a challenging task due to the heavy occlusions, scales, and density variations. Existing methods handle these challenges effectively while ignoring low-resolution (LR) circumstances. The LR circumstances weaken the counting performance deeply for two crucial reasons: 1) limited detail information; 2) overlapping head regions accumulate in density maps and result in extreme ground-truth values. An intuitive solution is to employ super-resolution (SR) pre-processes for the input LR images. However, it complicates the inference steps and thus limits application potentials when requiring real-time. We propose a more elegant method termed Multi-Scale Super-Resolution Module (MSSRM). It guides the network to estimate the lost de tails and enhances the detailed information in the feature space. Noteworthy that the MSSRM is plug-in plug-out and deals with the LR problems with no inference cost. As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd). Extensive experiments on three datasets demonstrate the superiority of our method. The code will be available at https://github.com/PRIS-CV/MSSRM.git.