A high-resolution RTSP stream connects to a system using OpenCV and YOLO. Frames are queued, resampled, and processed to match objects with specific IDs by coordinates, size, and timestamp, making LLM requests to the Ollama server for object tagging. The system operates with a 640x480 resolution for processing and averages 20ms
Table of contents
UsesHow it worksObject matchingTest EnvironmentPrerequisitesShortcutsProject directionSort: