Open AccessFeature channel enhancement for crowd counting
Author(s) -
Wu Xingjiao,
Kong Shuchen,
Zheng Yingbin,
Ye Hao,
Yang Jing,
He Liang
Publication year - 2020
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2019.1308
Subject(s) - channel (broadcasting) , computer science , feature (linguistics) , block (permutation group theory) , feature extraction , key (lock) , feature vector , artificial intelligence , pattern recognition (psychology) , data mining , computer vision , computer security , mathematics , computer network , geometry , philosophy , linguistics
Crowd counting, i.e. count the number of people in a crowded visual space, is emerging as an essential research problem with public security. A key in the design of the crowd counting system is to create a stable and accurate robust model, which requires to process on the feature channels of the counting network. In this study, the authors present a featured channel enhancement (FCE) block for crowd counting. First, they use a feature extraction unit to obtain the information of each channel and encodes the information of each channel. Then use a non‐linear variation unit to deal with the encoded channel information, finally, normalise the data and affixed to each channel separately. With the use of the FCE, the positive characteristic channel can be enhanced and weak or negative channel information can be suppressed. The authors successfully incorporate the FCE with two compact networks on the standard benchmarks and prove that the proposed FCE achieves promising results.