Crowd counting via cross-stage refinement networks

Crowd counting via cross-stage refinement networks

Crowd counting is challenging due to unconstrained imaging factors, e.g., background clutters, non-uniform distribution of people, large scale and perspective variations. Dealing with these problems using deep neural networks requires rich prior knowledge and multi-scale contextual representations....

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Yongtuo, WEN, Qiang, CHEN, Haoxin, LIU, Wenxi, QIN, Jing, HAN, Guoqiang, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Feature extraction
Convolution
Decoding
Clutter
Benchmark testing
Cameras
Network architecture
Crowd counting
recurrent network
image refinement
Information Security
Online Access:https://ink.library.smu.edu.sg/sis_research/7848
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:Crowd counting is challenging due to unconstrained imaging factors, e.g., background clutters, non-uniform distribution of people, large scale and perspective variations. Dealing with these problems using deep neural networks requires rich prior knowledge and multi-scale contextual representations. In this paper, we propose a Cross-stage Refinement Network (CRNet) that can refine predicted density maps progressively based on hierarchical multi-level density priors. In particular, CRNet is composed of several fully convolutional networks. They are stacked together recursively with the previous output as the next input, and each of them serves to utilize previous density output to gradually correct prediction errors of crowd areas and refine the predicted density maps at different stages. Cross-stage multi-level density priors are further exploited in our recurrent framework by the cross-stage skip layers based on ConvLSTM. To cope with different challenges of unconstrained crowd scenes, we explore different crowd-specific data augmentation methods to mimic real-world scenarios and enrich crowd feature representations from different aspects. Extensive experiments show the proposed method achieves superior performances against state-of-the-art methods on four widely-used challenging benchmarks in terms of counting accuracy and density map quality. Code and models are available at this https://github.com/lytgftyf/Crowd-Counting-via-Cross-stage-Refinement-Networks.

Similar Items