Crowd Counting with Deep Structured Scale Integration Network

08/23/2019
by   Lingbo Liu, et al.
49

Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people. In this paper, we propose a novel Deep Structured Scale Integration Network (DSSINet) for crowd counting, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization. Unlike conventional methods which directly fuse multiple features with weighted average or concatenation, we first introduce a Structured Feature Enhancement Module based on conditional random fields (CRFs) to refine multiscale features mutually with a message passing mechanism. In this module, each scale-specific feature is considered as a continuous random variable and passes complementary information to refine the features at other scales. Second, we utilize a Dilated Multiscale Structural Similarity loss to enforce our DSSINet to learn the local correlation of people's scales within regions of various size, thus yielding high-quality density maps. Extensive experiments on four challenging benchmarks well demonstrate the effectiveness of our method. Specifically, our DSSINet achieves improvements of 9.5 on UCF-QNRF dataset against the state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 7

research
07/29/2021

Cascaded Residual Density Network for Crowd Counting

Crowd counting is a challenging task due to the issues such as scale var...
research
03/07/2020

Crowd Counting via Hierarchical Scale Recalibration Network

The task of crowd counting is extremely challenging due to complicated d...
research
07/11/2020

Pyramid Scale Network for Crowd Counting

Crowd counting is a challenging task in computer vision due to serious o...
research
09/09/2019

Crowd Counting on Images with Scale Variation and Isolated Clusters

Crowd counting is to estimate the number of objects (e.g., people or veh...
research
07/02/2018

Crowd Counting using Deep Recurrent Spatial-Aware Network

Crowd counting from unconstrained scene images is a crucial task in many...
research
01/31/2020

Hybrid Graph Neural Networks for Crowd Counting

Crowd counting is an important yet challenging task due to the large sca...
research
09/06/2022

Multiscale major factor selections for complex system data with structural dependency and heterogeneity

Based on structured data derived from large complex systems, we computat...

Please sign up or login with your details

Forgot password? Click here to reset