Effective crowd counting using multi-resolution context and image quality assessment-guided training

Abstract

Crowd counting is the challenging task in the crowd scene analysis. To tackle the scale variant issue and to calculate the more accurate result in this target task, this paper designs an effective crowd counting method based on multi-resolution context and image quality assessment-guided training. Specially, a multi-resolution context module is designed to extract the multi-scale context adaptively to enhance the final counting performance through learning the imbalance between different scale paths. An image quality assessment-guided training approach is developed to facilitate the crowd counting network to generate high-quality density map and more accurate counting result. Extensive experiments on benchmarks demonstrate the effectiveness of the proposed method on crowd counting task, the generalization of the proposed method, and the generalization of the developed image quality assessment-guided training approach.