Journal
IEEE TRANSACTIONS ON MULTIMEDIA
Volume 25, Issue -, Pages 2074-2084Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2022.3142398
Keywords
Tree structure; scale enhancer; multi-level auxiliator; crowd counting
Ask authors/readers for more resources
This paper proposes a novel network called STNet for accurate crowd counting. STNet consists of two key components: Scale-Tree Diversity Enhancer and Multi-level Auxiliator. By enriching scale diversity and exploiting shared characteristics at multiple levels, STNet can significantly improve the accuracy of crowd counting.
State-of-the-art approaches for crowd counting resort to deepneural networks to predict density maps. However, counting people in congested scenes remains a challenging task because the presence of drastic scale variation, density inconsistency, and complex background can seriously degrade their counting accuracy. To battle the ingrained issue of accuracy degradation, in this paper, we propose a novel and powerful network called Scale Tree Network (STNet) for accurate crowd counting. STNet consists of two key components: a Scale-Tree Diversity Enhancer and a Multi-level Auxiliator. Specifically, the Diversity Enhancer is designed to enrich scale diversity, which alleviates limitations of existing methods caused by insufficient level of scales. A novel tree structure is adopted to hierarchically parse coarse-to-fine crowd regions. Furthermore, a simple yet effective Multi-level Auxiliator is presented to aid in exploiting generalisable shared characteristics at multiple levels, allowing more accurate pixel-wise background cognition. The overall STNet is trained in an end-to-end manner, without the needs for manually tuning loss weights between the main and the auxiliary tasks. Extensive experiments on five challenging crowd datasets demonstrate the superiority of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available