Counting Crowds in Bad Weather

TL;DR

This paper introduces a robust crowd counting method that effectively handles adverse weather conditions like haze, rain, and snow by learning weather-aware features and adaptive queries, outperforming existing approaches.

Contribution

A novel single-stage model that learns weather information and crowd features simultaneously, improving accuracy in adverse weather scenarios.

Findings

Effective in various weather conditions on benchmark datasets

Outperforms existing crowd counting methods in adverse weather

Provides publicly available source code and models

Abstract

Crowd counting has recently attracted significant attention in the field of computer vision due to its wide applications to image understanding. Numerous methods have been proposed and achieved state-of-the-art performance for real-world tasks. However, existing approaches do not perform well under adverse weather such as haze, rain, and snow since the visual appearances of crowds in such scenes are drastically different from those images in clear weather of typical datasets. In this paper, we propose a method for robust crowd counting in adverse weather scenarios. Instead of using a two-stage approach that involves image restoration and crowd counting modules, our model learns effective features and adaptive queries to account for large appearance variations. With these weather queries, the proposed model can learn the weather information according to the degradation of the input image and optimize with the crowd counting module simultaneously. Experimental results show that the proposed algorithm is effective in counting crowds under different weather types on benchmark datasets. The source code and trained models will be made available to the public.