Multi-resolution attention convolutional neural network for crowd counting

NEUROCOMPUTING

卷:329

Article

Zhang, Youmei¹  Zhou, Chunluan²  Chang, Faliang¹  Kot, Alex C.² 

[1] Shandong Univ, Sch Control Sci & Engn, Jinan 250061, Shandong, Peoples R China

[2] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore

关键词: Crowd counting;    Multi-resolution attention (MRA) model;    Convolution neural network (CNN);    Atrous convolution;   

DOI  :  10.1016/j.neucom.2018.10.058

来源: Elsevier

【 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.

【 授权许可】

Free