This application deploys AI-powered captioning for live RTSP video streams with Deep Learning Streamer (DL Streamer) and OpenVINO™ Vision Language Models (VLMs).
To see the system requirements and other installations, see the following guides:
- System Requirements: Check the hardware and software requirements for deploying the application.
- Get Started: Follow step-by-step instructions to set up the application.
The overall infrastructure involves ingesting an RTSP stream, processing it through a DLStreamer pipeline that samples frames for VLM inference, and delivering the resulting insights to the dashboard.
For more information see How it works