Deploying a computer vision service to detect car obstacles using OpenCV, TensorFlow Lite, and scikit-learn
In this section, we are going to explore how to configure the object detection system that runs at the edge with all its components. This section also shows how to configure the public web application running in the cloud that stores and shows information about all detected objects at the edge. Let’s start by first configuring our Raspberry Pi device in the next section.
Preparing your Raspberry Pi to run the computer vision application
Before installing our software, we have to prepare our device to run it. For this, let’s start to configure our Raspberry Pi 4B following the next steps:
- Install Raspbian Pi OS (32 bit) using Debian Bullseye, released at least from 2022-04-04. The code to run the TensorFlow Lite model in this chapter has to run on an ARMv7 device to support the Coral USB Accelerator device and the LCD screen. ARM64 is not supported...
