Crowd Counting in Harsh Weather using Image Denoising with Pix2Pix GANs

TL;DR

This paper introduces a method that employs Pix2Pix GANs to denoise images affected by harsh weather conditions, thereby improving the accuracy of crowd counting models in challenging environments.

Contribution

The paper presents a novel application of Pix2Pix GANs for denoising crowd images before counting, enhancing performance in adverse weather conditions.

Findings

Improved crowd counting accuracy in fog, dust, and low light conditions.

Effective denoising of synthetic noisy images using Pix2Pix GANs.

Enhanced reliability of crowd density estimates in challenging environments.

Abstract

Visual crowd counting estimates the density of the crowd using deep learning models such as convolution neural networks (CNNs). The performance of the model heavily relies on the quality of the training data that constitutes crowd images. In harsh weather such as fog, dust, and low light conditions, the inference performance may severely degrade on the noisy and blur images. In this paper, we propose the use of Pix2Pix generative adversarial network (GAN) to first denoise the crowd images prior to passing them to the counting model. A Pix2Pix network is trained using synthetic noisy images generated from original crowd images and then the pretrained generator is then used in the inference engine to estimate the crowd density in unseen, noisy crowd images. The performance is tested on JHU-Crowd dataset to validate the significance of the proposed method particularly when high reliability and accuracy are required.