Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection

Redesigned Skip-Network for Crowd Counting with Dilated Convolution and Backward Connection

Crowd counting is a challenging task dealing with the variation of an object scale and a crowd density. Existing works have emphasized on skip connections by integrating shallower layers with deeper layers, where each layer extracts features in a different object scale and crowd density. However, on...

Full description

Bibliographic Details
Main Authors: Sorn Sooksatra, Toshiaki Kondo, Pished Bunnun, Atsuo Yoshitaka
Format: Article
Language:English
Published: MDPI AG 2020-05-01
Series:Journal of Imaging
Subjects:
surveillance system
crowd counting
regression-based approach
skip connection
dilated convolution
Online Access:https://www.mdpi.com/2313-433X/6/5/28

Similar Items

Similar Items