Can AI Agents Actually Build Jetson Video Apps?

Can AI coding agents build computer vision and video applications on NVIDIA Jetson from scratch? In this video, we put an AI agent to the test on an NVIDIA Jetson Orin NX on a Connect Tech Boson carrier board, paired with an Intel RealSense D435i depth camera.

We set up the environment, start with jetson-device-skills, and challenging the agent to build three progressively complex applications - from basic video/depth streaming to real-time object detection. Along the way, we look at how the agent handles hardware discovery, dependency troubleshooting, and where human intervention is still needed.

We explore using GStreamer, the RealSense library, YOLO 11, and DeepStream to implement the applications in increasing levels of complexity.

Hardware & Setup Used:

NVIDIA Jetson Orin NX (16GB)
Connect Tech Boson Carrier Board
Intel RealSense D435i Depth Camera
Python UV / Virtual Environment

Join this channel to get access to perks:
https://www.youtube.com/channel/UCQs0lwV6E4p7LQaGJ6fgy5Q/join

Connect Tech - Embedded Computing Experts: https://connecttech.com

Sample Demo Prompts: https://drive.google.com/file/d/1--lzVEM7iiieFp3xDkT6S6HKh8-k39e5/view?usp=sharing

Chapters:
00:00 Introduction
01:11 Discovering the Camera
05:10 GStreamer
07:27 Point Cloud Application
12:31 Building the AI Pipeline

As an Amazon Associate I earn from qualifying purchases.
Visit the JetsonHacks storefront on Amazon: https://www.amazon.com/shop/jetsonhacks

Visit the website at https://jetsonhacks.com
Sign up for the newsletter! https://newsletter.jetsonhacks.com
Github accounts: https://github.com/jetsonhacks
https://github.com/jetsonhacksnano
Twitter: http://twitter.com/jetsonhacks

Some of these links here are affiliate links. As an Amazon Associate I earn from qualifying purchases at no extra cost to you.