TRIPLE ATTENTION FOR ROBUST VIDEO CROWD COUNTING

被引：0

作者：

Wu, Qiyao ^{[1
]}

Zhang, Chongyang ^{[1
]}

Kong, Xiyu ^{[1
]}

Zhao, Muming ^{[1
]}

Chen, Yanjun ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200240, Peoples R China

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2020年

关键词：

Crowd counting; Co-attention; Robustness;

D O I：

10.1109/icip40778.2020.9190701

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

Tra.ditional static-image based crowd counting methods work well on public d.atasets. However, due to the complexity and variability of real-world scenarios, their performance tends to drop dramatically in practice. Aiming to solve the robust problem of crowd counting, we propose to use a co-attention mechanism to extract correlation features lying behind adjacent video frames which can enhance the distinguish-ability between background and foreground. Also, we combine co-attention with spatial attention and multi-scale self-attention. Three different and complementary attention-based modules jointly reinforce the robustness of the counting model. Experiments on two widely used video crowd datasets demonstrate the effectiveness of the proposed approach.

引用

页码：1966 / 1970

页数：5