This project is a proof of concept to demonstrate how easily you can deploy a fleet of edge devices running a tinyML model with object detection capabilities. I have chosen a simple use case of counting cars in a parking lot. You can use similar infrastructure to build any kind of objection detection application such as identifying product defect in real manufacturing workflow, automate car inspection for exterior damages, etc. Parking facilities need to know how many cars are parked in a given facility at any given point of time, to evaluate how many empty parkings available and intake more customers. You also want to keep track of the number of cars that enter and exit your facility during any given time. You can use this information to improve operations, such as adding more parking payment centers, optimizing price, directing cars to different floors etc. Parking center owners typically operate on multiple floor or more than one facility and they want to manage a fleet of devices and aggregate real-time data to take efficient decision on business process.
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/scale-your-fleet-of-tinyml-solutions-using-aws-iot-edge-impulse-and-balena