Dilated Convolution to Capture Scale Invariant Context in Crowd Density Estimation
43rd Conference of the South African Institute of Computer Scientists and Information Technologists, SAICSIT 2022
; 85:89-103, 2022.
Article
in English
| Scopus | ID: covidwho-2026411
ABSTRACT
Crowd Density Estimation (CDE) can be used ensure safety of crowds by preventing stampedes or reducing spread of disease which was made urgent with the rise of Covid-19. CDE a challenging problem due to problems such as occlusion and massive scale variations. This research looks to create, evaluate and compare different approaches to crowd counting focusing on the ability for dilated convolution to extract scale-invariant contextual information. In this work we build and train three different model architectures a Convolutional Neural Network (CNN) without dilation, a CNN with dilation to capture context and a CNN with an Atrous Spatial Pyramid Pooling (ASPP) layer to capture scale-invariant contextual features. We train each architecture multiple times to ensure statistical significance and evaluate them using the Mean Squared Error (MSE), Mean Average Error (MAE) and Grid Average Mean Absolute Error (GAME) on the Shang-haiTech and UCF CC 50 datasets. Comparing the results between approaches we find that applying dilated convolution to more sparse crowd images with little scale variations does not make a significant difference but, on highly congested crowd images, dilated convolutions are more resilient to occlusion and perform better. Furthermore, we find that adding an ASPP layer improves performance in the case when there are significant differences in the scale of objects within the crowds. The code for this research is available at https//github.com/ThishenP/crowd-density. © 2022, EasyChair. All rights reserved.
Computer vision; Convolutional neural networks; Errors; Mean square error; Multilayer neural networks; Network architecture; Contextual feature; Contextual information; Convolutional neural network; Crowd density; Density estimation; Modeling architecture; Scale-invariant; Spatial pyramids; Spread of disease; Statistical significance; Convolution
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
43rd Conference of the South African Institute of Computer Scientists and Information Technologists, SAICSIT 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS