People detection and facial Blur

  • Description
    A simple pipeline that uses a standard Nvidia PeopleNet model to detect persons and their faces in the video. The faces are matched versus bodies and blurred with the integrated OpenCV CUDA functionality. There is also a simple, unreliable tracker that helps reduce the flickering of boxes.
  • Key Features
    — Body and facial detection with PeopleNet
    — Facial blur with OpenCV CUDA
    — People tracking with Nvidia Tracker
    — Embedded analytical dashboard
  • End-To-End Performance
    — 116 FPS on Nvidia A4000
    — 30 FPS on Jetson NX