Crowd Counting Method Based on Improved CSRnet

DOI
  • Zhao Huailin
    School of electrical and Electronic Engineering, Shanghai Institute of Technology
  • Lu Shengyang
    School of electrical and Electronic Engineering, Shanghai Institute of Technology
  • Wang Li
    School of electrical and Electronic Engineering, Shanghai Institute of Technology
  • Nie Zhen
    School of electrical and Electronic Engineering, Shanghai Institute of Technology
  • Li Yaoyao
    School of electrical and Electronic Engineering, Shanghai Institute of Technology

説明

Aiming at the problem of population counting, the research is getting deeper and deeper, CSRnet proposed a method of expanding convolution instead of convolution layer and pooling layer. This paper mainly proposes a multi-scale expansive convolutional neural network, which uses a method similar to the inception-ResNet module to calculate the population density of dense crowds with large scale changes and severe occlusion. And apply this method to ShanghaiTech dataset. The experimental results show that compared with CSRnet, the accuracy of this method has been improved, and the speed of feature extraction has also been improved.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390846609806887936
  • DOI
    10.5954/icarob.2020.os11-15
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ