After setting up the NVIDIA Jetson Orin Nano Super in the last blog post, it’s time to dive into the first AI experiments.
Realtime object detection
The NanoOWL tutorial is a great starting point and an impressive demo application. It showcases Open-Vocabulary Object Detection using Vision Transformers. The model can process one or multiple text queries to search for and detect target objects described in natural language within a video stream in real-time.
The full results of my experiments are presented in the video below.
Smart Driveway Monitor & run local LLM
The linked video tutorial from Dave’s Garage shows, among other things, how to build a smart driveway application with AI-based vehicle detection and how to run Llama 3.2 locally.
