How to Run a Real-time Object Detector Starter App in Minutes

In this tutorial, we will show you the steps needed to get a real-time object detector starter app up and running quickly and easily on an edge device or local machine.

 

Installing and running the real-time object detector starter app on the alwaysAI platform

This blog describes the six simple steps to getting a real-time object detector app up and running on an edge or embedded device in a just few minutes . In this particular demo, our Senior Software Engineer, Eric VanBuhler, is running Ubuntu 18.04 on his development computer and he has already installed the alwaysAI CLI. You can also run alwaysAI on Mac and Windows.

For his edge device, he has a Raspberry Pi 3 B+ that he has set up with Raspbian Buster, and is utilizing the pi's ribbon camera for real-time video. Check out other current supported devices and cameras.

1. Log into the alwaysAI Platform

If you haven't already signed up for an account, do so now! You can sign up for a free account here.

2. Install alwaysAI

If you have not already done so,  set up your development computer and install alwaysAI. For more information on system requirements and supported boards, check out our Docs.

3. Download the Starter Applications

After logging into alwaysAI on both the Dashboard and CLI, download the starter applications via the CLI. Using these starter applications will show you how to perform computer vision tasks with the alwaysAI EdgeIQ Library.

Screen Shot 2021-02-01 at 6.20.02 PM

 

4. Access the Real-time Object Detector App

Open the starter application directory in your file browser. Open the “realtime_object_detector” folder. 

Screenshot of the real-time object detector from alwaysAI

Open a Terminal window in the application directory.

5. Install Your Object Detection App

Once you have a Terminal window open in your application directory, you can get the real-time object detector app running with a few simple commands.

First, setup the app target directory using the alwaysai app configure command. This will prompt you to either choose a Project name, or create a new Project. For more details on Projects, read our documentation. If you haven't previously created a project, you can simply create a new one now. 

create_new_project

You can then select to run the application on your local device or a remote device.

local_or_remote

If you select a remote device but haven't set up the desired edge device, you can choose to set up a new device.

 

choose_destination

In Eric's case, he chose to deploy the app to his Raspberry Pi 3 B+.

Next, run the command aai app install. If you chose to install your app on an edge device, choose the default option when prompted about where to install the app. After running this command, your computer vision models will be installed and a Docker image will be built for your app. 

Next, start the app using the Terminal command aai app start. This will run the app on your device and start detecting objects through your camera.

Screenshot of  the app start from alwaysAI
 
 

6. View Your App in a Web Browser

The application will bring up a web interface link you can visit in your browser to see what the device is seeing.

Screenshot of the interface link from alwaysAI

And that is all it takes to get a real-time object detector application up and running on an edge device using the alwaysAI platform!

Get started now

We are providing professional developers with a simple and easy-to-use platform to build and deploy computer vision applications on edge devices. 

Sign Up for Free