期刊
2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
卷 -, 期 -, 页码 1498-1503出版社
IEEE
DOI: 10.1109/ICME.2019.00259
关键词
Crowd Counting; Multi-Scale Feature; Input View; Feature View; Criterion View
类别
资金
- National Key Research and Development Program of China [2018YFC0830103]
- National Science Foundation of China [U1811463, 61602533, 61702565]
- Fundamental Research Funds for the Central Universities [18lgpy63]
Crowd counting, aiming at estimating the total number of people in unconstrained crowded scenes, has increasingly received attention. But it is greatly challenged by the huge variation in people scale. In this paper, we propose a novel Multi-View Scale Aggregation Network (MVSAN), which handle the scale variation from feature, input and criterion view comprehensively. Firstly, we design a simple but effective Multi-Scale Feature Encoder, which exploits dilated convolution layers with various dilation rates to improve the representation ability and scale diversity of features. Secondly, we feed multiple scales of input images into networks to generate high-quality density maps in a coarse-to-fine manner. Finally, we propose a Multi-Scale Structural Similarity loss to force our networks to learn the local correlation of density maps. Extensive experiments on two standard benchmarks show that the proposed method can generate high-quality crowd density map and accurate count estimation, outperforming the state-of-the-art methods with a large margin.
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