Pet Detector application uses Tensorflow Lite, OpenCV and Paho MQTT Client to detect objects and publish MQTT messages in order to trigger automatic processes.
Settings can be configured in config.ini file.
Example configuration can be found in config.ini.sample.
Compatible only with Rasbpian Buster or Rasbpian Stretch
Camera needs to be enabled in raspi-config
Raspberry Pi needs to be updated
sudo apt-get update
sudo apt-get dist-upgradestart with venv
chmod +x venv_start.sh
./venv_start.shInstall necessary dependencies
echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list
curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -
sudo apt-get update
sudo apt-get install libedgetpu1-stdChange following lines in config.ini
tflite_file = edgetpu.tflite
edgetpu = true