SMCA-CNN: Learning a Semantic Mask and Cross-Scale Adaptive Feature for Robust Crowd Counting

SMCA-CNN: Learning a Semantic Mask and Cross-Scale Adaptive Feature for Robust Crowd Counting

Density-based crowd counting methods with deep convolutional neural network (CNN) have achieved the state of the art on the challenging datasets. Experimental results showed that the performance of these methods suffers from two problems: 1) Background interference problem: there are some estimated...

Full description

Bibliographic Details
Main Authors: Guoshuai Wang, Yue Zou, Zirui Li, Dongming Yang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Crowd counting
cross-scale features
background interference
semantic mask
span architecture
Online Access:https://ieeexplore.ieee.org/document/8765698/

Internet

https://ieeexplore.ieee.org/document/8765698/

Similar Items