标题：Multi-resolution attention convolutional neural network for crowd counting
作者：Zhang, Youmei; Zhou, Chunluan; Chang, Faliang; Kot, Alex C.
作者机构：[Zhang, Youmei; Chang, Faliang] Shandong Univ, Sch Control Sci & Engn, Jinan 250061, Shandong, Peoples R China.; [Zhou, Chunluan; Kot, Alex C.] Nany 更多
通讯作者：Chang, Faliang;Chang, FL
通讯作者地址：[Chang, FL]Shandong Univ, Sch Control Sci & Engn, Jinan 250061, Shandong, Peoples R China.
关键词：Crowd counting; Multi-resolution attention (MRA) model; Convolution; neural network (CNN); Atrous convolution
摘要：Estimating crowd counts remains a challenging task due to the problems of scale variations, non-uniform distribution and complex backgrounds. In this paper, we propose a multi-resolution attention convolutional neural network (MRA-CNN) to address this challenging task. Except for the counting task, we exploit an additional density-level classification task during training and combine features learned for the two tasks, thus forming multi-scale, multi-contextual features to cope with the scale variation and non-uniform distribution. Besides, we utilize a multi-resolution attention (MRA) model to generate score maps, where head locations are with higher scores to guide the network to focus on head regions and suppress non-head regions regardless of the complex backgrounds. During the generation of score maps, atrous convolution layers are used to expand the receptive field with fewer parameters, thus getting higher-level features and providing the MRA model more comprehensive information. Experiments on ShanghaiTech, WorldExpo'10 and UCF datasets demonstrate the effectiveness of our method. (C) 2018 Elsevier B.V. All rights reserved.