SRNet: Scale-Aware Representation Learning Network for Dense Crowd Counting

Liangjun Huang

doi:10.1109/ACCESS.2021.3115963

2021-01-01

DOI：10.1109/ACCESS.2021.3115963

原文链接

原文求助

摘要

En 中文

Huge variations in the scales of people in images create an extremely challenging problem in the task of crowd counting. Currently, many researchers apply multi-column structures to solve the scale variation problem. However, multi-column structures usually have complex structures with large numbers of parameters and are difficult to optimize. To this end, we propose a scale-aware representation learning network (SRNet) that uses a commonly used encoder-decoder framework. An image is converted into deep features by the first ten layers of VGG16 in the encoder. Then, the features are regressed to a crowd density map via the decoder. The decoder mainly consists of two modules: the scale-aware feature learning module (SAM) and the pixel-aware upsampling module (PAM). SAM models the multi-scale features of a crowd at each level with different sizes of receptive fields, and PAM enlarges the spatial resolution and enhances the pixel-level semantic information, thereby improving the overall counting accuracy. We conduct extensive crowd counting experiments on ShanghaiTech Part_A, UCF-QNRF, and UCF_CC_50 datasets. Furthermore, to obtain the locations of each person, we conduct crowd localization experiments on UCF-QNRF and NWPU-Crowd datasets. The qualitative and quantitative results prove the effectiveness of the SRNet in dense crowd counting and crowd localization tasks.

Keyword:

Feature extraction

Task analysis

Convolution

Estimation

Decoding

Semantics

Location awareness

Dense crowd counting

multi-scale feature learning

deep learning

convolution neural network

期刊

IEEE Access

IF:

3.6

论文数:

9.8W

被引数:

29.4W

机构

university of hamburg

学者数:

3.7W

论文数: 2.9W

被引数: 30

shanghai institute of technology

学者数:

5.8K

论文数: 3.7K

被引数: 1

引用论文

Significance of Effects of High Pressure on Kinetics of Electrode Reactions: I . Applications to Transition States in Hydrogen Evolution Reaction Mechanisms

Journal of The Electrochemical Society

IF0

2019-12-09

PREAI

B. E. Conway; J. C. Currie

The profiles of cat and dog tutors participating in a pet neutering campaign 参与宠物绝育活动的猫和狗导师的档案

Acta Veterinaria Brasilica

IF0

2017-12-22

OAAI

Filipi Alexandre do Nascimento Silva; Ana Maria Quessada; Dayanne Anunciação Silva Dantas Lima; Wagner Costa Lima; Jeferson Da Cruz Silva; Jaqueline Lustosa Rodrigues Camapum

Comparative analysis of occlusion methods for artificial sphincters 人工括约肌闭塞方法的比较分析

Artificial Organs

IF0

2020-04-07

PREAI

Leonardo Marziale; Gioia Lucarini; Tommaso Mazzocchi; Leonardo Ricotti; Arianna Menciassi

Scale-Aware Fast R-CNN for Pedestrian Detection 基于尺度感知的快速r-cnn行人检测

IEEE TRANSACTIONS ON MULTIMEDIA

IF9.7

2017-01-01

587

OAAI