期刊
NEURAL NETWORKS
卷 148, 期 -, 页码 219-231出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2022.01.015
关键词
Crowd counting; Top-Down visual perception mechanism; Priority map; Global context information
资金
- National Natural Science Foundation of China [62073257, 62141223, 61971343]
- Natural Science Basic Research Plan in Shaanxi Province of China [2020JM-012]
In this paper, a novel feedback network with Region-Aware block (RANet) is proposed to tackle the common problems of background noise and scale variation in crowd counting. The RANet incorporates human's Top-Down visual perception mechanism by generating priority maps and adaptively encoding contextual information. Experimental results demonstrate that our method outperforms state-of-the-art approaches on multiple public datasets.
Background noise and scale variation are common problems that have been long recognized in crowd counting. Humans glance at a crowd image and instantly know the approximate number of human and where they are through attention the crowd regions and the congestion degree of crowd regions with a global receptive field. Hence, in this paper, we propose a novel feedback network with Region-Aware block called RANet by modeling human's Top-Down visual perception mechanism. Firstly, we introduce a feedback architecture to generate priority maps that provide prior about candidate crowd regions in input images. The prior enables the RANet pay more attention to crowd regions. Then we design Region-Aware block that could adaptively encode the contextual information into input images through global receptive field. More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity. The relevance matrix obtained would be utilized to build global relationships between pixels. Our method outperforms state-of-the-art crowd counting methods on several public datasets. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据