ESP32-CAM for Computational Photography

H. G. Dietz

Department of Electrical and Computer Engineering
Center for Visualization & Virtual Environments
University of Kentucky, Lexington, KY 40506-0046

Initial release: March 4, 2021

This document should be cited using something like the bibtex entry:

author={Henry Gordon Dietz},
title={{ESP32-CAM For Computational Photography}},
institution={University of Kentucky},
howpublished={Aggregate.Org online technical report},

For quite some years now, I, Professor Hank Dietz, and my students have been using CHDK (Canon Hack Development Kit) to do evil things inside Canon PowerShot cameras. Those cameras generally start at around $80, and they provide quite good image quality with high resolution, but they aren't really very beefy computing systems: typically, they are dual-core ARMs at around 80MHz. They are also very difficult to pull apart; for example, removing the lens to use an interchangeable mount isn't really feasible.

In contrast, the $7 AI Thinker ESP32-CAM camera is only 2MP, but it's trivial to unscrew the lens. In a board just 27x40mm, it provides a 240MHz dual-core 32-bit Tensilica processor, 802.11 WiFi and BlueTooth as well as wired interfaces, a microSD slot, low power modes, etc.

ESP32-CAM Observations & References

ESP32-CAM Useful Libraries

The Aggregate. The only thing set in stone is our name.