Crowd Density Estimation by Using Attention Based Capsule Network and Multi-Column CNN

Merve Ayyuce Kizrak, Bulent Bolat

Araştırma sonucu: Dergi katkısıMakalebilirkişi

4 Alıntılar (Scopus)

Özet

We propose a strategy that focuses on estimating the number of people in a crowd, one of the aims of crowd analysis, using static images or video images. While manual feature extraction was not performed with pixel and regression-based methods in the first studies on crowd analysis, recent studies use Convolutional Neural Networks (CNN) based models. However, it is still difficult to extract spatial information such as position, orientation, posture, and angular value for crowd estimation from a density map. This study uses capsule networks and routing by agreement algorithm as an attention module. Our proposed approach consists of both CNN and capsule network-based attention modules in a two-column deep neural network architecture. We evaluate our proposed approach compared with other state-of-the-art methods using three well-known datasets: UCF-QNRF, UCFCC50, UCSD, ShangaiTech Part A, and WorldExpo'10.

Orijinal dilİngilizce
Makale numarası9433545
Sayfa (başlangıç-bitiş)75435-75445
Sayfa sayısı11
DergiIEEE Access
Hacim9
DOI'lar
Yayın durumuYayınlanan - 2021
Harici olarak yayınlandıEvet

Parmak izi

Crowd Density Estimation by Using Attention Based Capsule Network and Multi-Column CNN' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Bundan alıntı yap