Attentional Neural Fields for Crowd Counting

Crowd counting has recently generated huge popularity in computer vision, and is extremely challenging due to the huge scale variations of objects. In this paper, we propose the Attentional Neural Field (ANF) for crowd counting via density estimation. Within the encoder-decoder network, we introduce...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Anran, Yue, Lei, Shen, Jiayi, Zhu, Fan, Zhen, Xiantong, Cao, Xianbin, Shao, Ling
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Aggregates
Computational modeling
Estimation
Feature extraction
Machine learning
Task analysis
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Crowd counting has recently generated huge popularity in computer vision, and is extremely challenging due to the huge scale variations of objects. In this paper, we propose the Attentional Neural Field (ANF) for crowd counting via density estimation. Within the encoder-decoder network, we introduce conditional random fields (CRFs) to aggregate multi-scale features, which can build more informative representations. To better model pair-wise potentials in CRFs, we incorperate non-local attention mechanism implemented as inter- and intra-layer attentions to expand the receptive field to the entire image respectively within the same layer and across different layers, which captures long-range dependencies to conquer huge scale variations. The CRFs coupled with the attention mechanism are seamlessly integrated into the encoder-decoder network, establishing an ANF that can be optimized end-to-end by back propagation. We conduct extensive experiments on four public datasets, including ShanghaiTech, WorldEXPO 10, UCF-CC-50 and UCF-QNRF. The results show that our ANF achieves high counting performance, surpassing most previous methods.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00581