The main goal of the project is: to share video, screen, camera and audio with an RTSP stream through Lan or Wan supporting CUDA computations in a High Performance embedded environment (Nvidia Jetson Nano), applying real-time AI techiques of Intrusion Detection with bounding boxes localization and frames manipulations.
The Nano was capable to capture frames, apply filters, encode, make inference and stream them at 5 to 10 fps, enough to detect someone passing in front of the camera.
For detection it was used a model based on the coco ssd mobilenet v2.
Nvidia DevTalk post: https://devtalk.nvidia.com/default/topic/1065923/jetson-projects/multimedia-sharing-tool-a-jetson-nano-project/
Jetson Projects board: https://developer.nvidia.com/embedded/community/jetson-projects#multimedia_sharing
Here is a video demonstration of the application.
Comments