Granular-based dense crowd density estimation
Document Type
Article
Publication Date
1-1-2018
Abstract
Dense crowd density estimation is one of the fundamental tasks in crowd analysis. While tremendous progress has been made to understand crowd scenes along with the rise of Convolutional Neural Networks (CNNs), research work on dense crowd density estimation is still an ongoing process. In this paper, we propose a novel approach to learn discriminative crowd features from granules, that conforms to the outline between crowd and background (i.e. non-crowd) regions, for density estimation. It shows that by studying the inner statistics of granules for density estimation, this approach is adaptive to arbitrary distribution of crowd (i.e. scene independent). Multiple features fusion is proposed to learn discriminative crowd features from granules. This is to be used as description of the crowd where a direct mapping between the features and crowd density is learned. Extensive experiments on public benchmark datasets demonstrate the effectiveness of our novel approach for scene independent dense crowd density estimation.
Keywords
Dense crowd analysis, Density estimation, Texture features, Visual surveillance
Divisions
fsktm
Funders
GGPM grant GGPM-2017-024, from the National University of Malaysia (UKM),Fundamental Research Grant Scheme (FRGS) MoHE Grant FP070-2015A, from the Ministry of Education Malaysia
Publication Title
Multimedia Tools and Applications
Volume
77
Issue
15
Publisher
Springer