Overview

In this tutorial we'll be demonstrating how to use Smart Capture in conjunction with the OpenCV Luxonis DepthAI Camera, running on an Nvidia Jetson Orin.

We'll be running object detection onboard the camera, processing them and utilizing the Smart Capture SDK on the Orin, and printing out the output of the triggers. We'll also be using the provided Smart Capture On-Device Update Service to retrieve updated trigger definitions from the Smart Capture Web Interface.

The diagram here can help explain what these different components do. For the purpose of simplicity in this tutorial, we'll be omitting the Update Server component, and will be allowing the On-Device Update Service to directly call the Smart Capture Web Server.

Hardware

Compute

We'll be using the Nvidia Jetson Orin as the compute device.

Camera

To remove the complexity of object detection inference in C++ from the tutorial, we'll be using a camera with onboard compute that provides an easy-to-use SDK. Specifically, the Luxonis Oak-D-Lite.

Dependencies

OpenCV

Since we'll be using OpenCV inside C++, we'll need to build it from source. There are some good instructions for doing so on Linux here.

DepthAI

This is the open-source SDK for interfacing with a Luxonis Camera. We'll also need to build this from source. There are good instructions here.