To make it more interesting I thought it’d be cool to restrict the machine learning model to a single type of item and add support for voice control to change between types. While I was at it I added the audio from the Portal turrets, because why not?
Last night the object detection project, which is using a Raspberry Pi model 3b+ and an Intel / Movidius Neural Compute Stick 2 (NCS2), finally started working as expected. The video feed comes from a Pi cam v2.1. Kudos for Adrian at Pyimagesearch for his very helpful guide on this topic!
After a fresh install of Ubuntu server 20.04 on a Raspberry Pi (3b+ in this case) you may find that the default login (user: “ubuntu” password: “ubuntu”) won’t get you logged in.
After waiting for a few minutes while googling this the Rpi output some cloud-init and SSH-key messages. When trying again the default ubuntu/ubuntu login worked just fine.
So, it turns out that even though the login screen is shown and it looks like the OS has fully booted, it won’t be possible to log in until the cloud-init etc. have finished (which may take 5min or so)!
Playing around with AWS Lambda, Rekognition, Polly, DynamoDB, Lex, S3, etc. to create a system for deploying Docker containers by talking to a Raspberry Pi. The containers are deployed locally on a PC running the “p4docker” service while the other two services (p4security and p4voiceui) are running on the Raspberry Pi.
This was part of a project for an internal Pied Piper course here at Dell Tech earlier this year: https://bigdatadownunder.com/2019/10/11/innovating-ground-up-project-piper/
The code can be found here:
Short demo of EdgeX Foundry using two Raspberry Pi’s. One to generate and send sensor data to EdgeX and another to play the role of an edge device which can receive commands from EdgeX depending on sensor values.
Note: This demo uses the Delhi release since I still haven’t updated the device profile for the “smartVent” Raspberry Pi to work with Edinburgh. I’ll post something cooler once that is working too.