SmartCamera: Realtime Video Stream-Oriented Action Recognition Platform in Edge Environment


Abstract:

This paper designs a real-time video stream-oriented action recognition platform, namely SmartCamera. It aims to detect target actions in real-time in a resource-constrained edge environment. The SmartCamera adopts 3D convolutional network-based sliding window as the classification model of actions, and introduces a flexible sliding window localization method to reduce the computational complexity of action recognition without harming behavioral consistency. The prototype of SmartCamera mainly includes five modules: Real-time Video Stream Collection, Video Stream Preprocessing, Action Recognition, Sliding Window Localization, User Interface. The preliminary evaluation shows that the system can detect target actions with an acceptable accuracy and latency.

Año de publicación:

2021

Keywords:

  • action recognition
  • Real-time video stream
  • edge environment

Fuente:

scopusscopus

Tipo de documento:

Conference Object

Estado:

Acceso restringido

Áreas de conocimiento:

  • Visión por computadora
  • Ciencias de la computación

Áreas temáticas:

  • Métodos informáticos especiales
  • Ciencias de la computación
  • Funcionamiento de bibliotecas y archivos