Automatic Counting of People in Crowded Scenes, with Drones That Were Applied in Internal Defense Operations on October 20, 2019 in Ecuador


Abstract:

Eleven days of public protests, unrest and chaos happened in October 2019 in Ecuador. The national security forces acted immediately implementing internal defense operations. In this changing and highly uncertain context the automatic crowd counting based on the Gaussian density estimation combined with the multi-scale convolutional neural networks is used to generate electronic intelligence. This solution is set in a real scene obtaining excellent results and reducing the training time without being the performance affected. In this way, with the information obtained in real-time about the quantities of forces and dispositive. The national security forces reaction is immediate guaranteeing the control, the resupply and reorganization of themselves.

Año de publicación:

2020

Keywords:

  • Gaussian density
  • Real scenarios
  • Crowd counting
  • cnn
  • Security operations

Fuente:

scopusscopus

Tipo de documento:

Conference Object

Estado:

Acceso restringido

Áreas de conocimiento:

  • Visión por computadora
  • Simulación por computadora

Áreas temáticas:

  • Métodos informáticos especiales
  • Física aplicada
  • Otros problemas y servicios sociales