Multi-resolution attention convolutional neural network for crowd counting

• Main Authors: Zhang, Youmei, Zhou, Chunluan, Chang, Faliang, Kot, Alex Chichung
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Crowd Counting; Multi-resolution Attention (MRA) Model
• Online Access: https://hdl.handle.net/10356/144965
• Institution: Nanyang Technological University

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.