This is a DIY smart camera made with an esp32cam and a TFT screen, put together on some perf board.

To get this working requires three tweaks:
1. Use esp32 board version 1.0.6.
2. Change the User_setup.h file in the TFT_eSPI library to reflect the pins you are using for SPI connection to TFT screen (i've provided my copy on the gihub repo).
3. Update the calloc to ps_calloc in your C:\Users\yourname\Documents\Arduino\libraries\bird_classification_3_inferencing\src\edgeimpulsesdk\porting\arduino\ ei_classifier_porting.cpp file. The idea for this work around came from Ralph Bacon (   / ralphbacon  .

Links:
The code repo: https://github.com/jonathanrandall/ed...

Next episode: connecting the camera to Azure:
   • DIY smart camera #2: Using the Azure ...  

The RobotZero One project that this is based on:
https://robotzero.one/esp32camtfts...

The Kaggle datasets.
Animals: https://www.kaggle.com/datasets/ashis...
People: https://www.kaggle.com/datasets/ahmad...
Scenes: https://www.kaggle.com/datasets/aryan...

My Edge Impulse Project:
https://studio.edgeimpulse.com/studio...

Edge Impulse Repo:
https://github.com/edgeimpulse/exampl...