HRANet: Hierarchical region-aware network for crowd counting

Aiming to tackle the most intractable problems of scale variation and complex backgrounds in crowd counting, we present an innovative framework called Hierarchical Region-Aware Network (HRANet) for crowd counting in this paper, which can better focus on crowd regions to accurately predict crowd dens...

Full description

Saved in:
Bibliographic Details
Published inApplied intelligence (Dordrecht, Netherlands) Vol. 52; no. 11; pp. 12191 - 12205
Main Authors Xie, Jinyang, Gu, Lingyu, Li, Zhonghui, Lyu, Lei
Format Journal Article
LanguageEnglish
Published New York Springer US 2022
Springer Nature B.V
Subjects
Artificial Intelligence
Computer Science
Density
Experiments
Feature extraction
Feature maps
Intelligence gathering
Machines
Manufacturing
Mechanical Engineering
Methods
Modules
Processes
Attention mechanism
Density map estimation
Crowd counting
Multi-scale feature
Online AccessGet full text

Cover

More Information
Summary:Aiming to tackle the most intractable problems of scale variation and complex backgrounds in crowd counting, we present an innovative framework called Hierarchical Region-Aware Network (HRANet) for crowd counting in this paper, which can better focus on crowd regions to accurately predict crowd density. In our implementation, first, we design a Region-Aware Module (RAM) to capture the internal differences within different regions of the feature map, thus adaptively extracting contextual features within different regions. Furthermore, we propose a Region Recalibration Module (RRM) which adopts a novel region-aware attention mechanism (RAAM) to further recalibrate the feature weights of different regions. By the integration of the above two modules, the influence of background regions can be effectively suppressed. Besides, considering the local correlations within different regions of the crowd density map, a Region Awareness Loss (RAL) is designed to reduce false identification while producing the locally consistent density map. Extensive experiments on five challenging datasets demonstrate that the proposed method significantly outperforms existing methods in terms of counting accuracy and quality of the generated density map. In addition, a series of specific experiments in crowd gathering scenes indicate that our method can be practically applied to crowd localization.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-021-03030-w