期刊
NEUROCOMPUTING
卷 450, 期 -, 页码 14-24出版社
ELSEVIER
DOI: 10.1016/j.neucom.2021.03.128
关键词
Crowd counting; Adversarial learning; Hybrid dilated convolution; Feature fusion; Sub-pixel convolution layer; Convolutional neural network
Crowd counting faces challenges of scale variations and limited annotated data, while having similarities with object detection in attention areas. Existing methods often overlook these similarities and specialties. The proposed ASANet tackles these challenges with three branches and demonstrates outstanding performance on public datasets.
Crowd counting aims to count the number of pedestrians in an image or a video. Currently, scale variations in crowd counting are inevitable and challenging in practice. Besides, for the crowd counting task, there is only a small amount of annotated data available. It can be seen from previous methods of crowd counting and object detection that the two tasks have similar attention areas. However, existing methods in crowd counting generally ignore the similarities and specialties between the crowd counting task and the object detection task. In this paper, in order to solve the above challenges, we propose an adversarial scale-adaptive neural network (ASANet), consisting of three branches. First, a private branch for the crowd counting task concentrates on generating high-quality density maps. Second, another private branch for the object detection task aims to correctly detect and recognize objects. Third, we design a common branch to learn the similar attention area of the two tasks and assist crowd counting. Experimental results demonstrate an outstanding performance of the ASANet over state-of-the-art methods on three public datasets (ShanghaiTech, UCF_CC_50, and UCF_QNRF). (c) 2021 Elsevier B.V. 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