AI on the Edge Device: Digitizing Your non-digital meters with an ESP32-CAM
## Table of Contents
- [Key Features π](#key-features-)
- [Workflow π§](#workflow-)
- [Impressions π·](#impressions-)
- [AI-on-the-edge-device on a Water Meter π§](#ai-on-the-edge-device-on-a-water-meter-)
- [Web Interface (Water Meter) π»](#web-interface-water-meter-)
- [AI-on-the-edge-device on an Electrical Power Meter β‘](#ai-on-the-edge-device-on-an-electrical-power-meter-)
- [Setup π οΈ](#setup-%EF%B8%8F)
- [Download π½](#download-)
- [Flashing the ESP32 πΎ](#flashing-the-esp32-)
- [Flashing the SD Card πΎ](#flashing-the-sd-card-)
- [Casing π οΈ](#casing-%EF%B8%8F)
- [Donate β](#donate-)
- [Support π¬](#support-)
- [Changes and History π](#changes-and-history-)
- [Build It Yourself π¨](#build-it-yourself-)
- [Tools π οΈ](#tools-%EF%B8%8F)
- [Additional Ideas π‘](#additional-ideas-)
- [Our Contributors β€οΈ](#our-contributors-%EF%B8%8F)
[](https://github.com/jomjol/AI-on-the-edge-device/tree/main/code)
[](https://jomjol.github.io/AI-on-the-edge-device-docs/)
[](https://GitHub.com/jomjol/AI-on-the-edge-device/releases/)
[](https://GitHub.com/jomjol/AI-on-the-edge-device/releases/)
[](https://GitHub.com/jomjol/AI-on-the-edge-device/network/)
[](https://GitHub.com/jomjol/AI-on-the-edge-device/stargazers/)
Artificial intelligence is everywhere, from speech to image recognition. While most AI systems rely on powerful processors or cloud computing, **edge computing** brings AI closer to the end user by utilizing the capabilities of modern processors.
This project demonstrates edge computing using the **ESP32**, a low-cost, AI-capable device, to digitize your analog metersβwhether water, gas, or electricity. With affordable hardware and simple instructions, you can turn any standard meter into a smart device.
Let's explore how to make **AI on the Edge** a reality! π
All you need is an [ESP32 board with a supported camera](https://jomjol.github.io/AI-on-the-edge-device-docs/Hardware-Compatibility/) and some practical skills. π οΈ
---
## Key Features π
- π **Tensorflow Lite (TFLite) integration** β including an easy-to-use wrapper.
- πΈ **Inline image processing** (feature detection, alignment, ROI extraction).
- π‘ **Small** and **affordable** device (3 x 4.5 x 2 cmΒ³, less than 10 EUR).
- π· Integrated camera and illumination.
- π Web interface for administration and control.
- π OTA interface for updating directly via the web interface.
- π Full integration with Home Assistant.
- π Support for **Influx DB 1** and **2**.
- π‘ **MQTT protocol** support.
- π₯ **REST API** available for data access.
## Workflow π§
The device captures a photo of your meter at set intervals. It then extracts the Regions of Interest (ROIs) from the image and runs them through artificial intelligence. As a result, you get the digitized value of your meter.
There are several options for what to do with that value:
- π€ Send it to a **MQTT broker**.
- π Write it to an **InfluxDb**.
- π Provide access via a **REST API**.
---
## Impressions π·
+ ### AI-on-the-edge-device on a Water Meter π§
+ ### Web Interface (Water Meter) π»
+ ### AI-on-the-edge-device on an Electrical Power Meter β‘
---
## Setup π οΈ
There is growing [documentation](https://jomjol.github.io/AI-on-the-edge-device-docs/) which provides you with a lot of information. Head there to get started, set it up, and configure it.
There are also articles in the German Heise magazine "make:" about the setup and technical background (behind a paywall): [DIY - Setup](https://www.heise.de/select/make/2021/2/2103513300897420296) π°
A lot of people have created useful YouTube videos that might help you get started:
- π₯ [youtube.com/watch?v=HKBofb1cnNc](https://www.youtube.com/watch?v=HKBofb1cnNc)
- π₯ [youtube.com/watch?v=yyf0ORNLCk4](https://www.youtube.com/watch?v=yyf0ORNLCk4)
- π₯ [youtube.com/watch?v=XxmTubGek6M](https://www.youtube.com/watch?v=XxmTubGek6M)
- π₯ [youtube.com/watch?v=mDIJEyElkAU](https://www.youtube.com/watch?v=mDIJEyElkAU)
- π₯ [youtube.com/watch?v=SssiPkyKVVs](https://www.youtube.com/watch?v=SssiPkyKVVs)
- π₯ [youtube.com/watch?v=MAHE_QyHZFQ](https://www.youtube.com/watch?v=MAHE_QyHZFQ)
- π₯ [youtube.com/watch?v=Uap_6bwtILQ](https://www.youtube.com/watch?v=Uap_6bwtILQ)
For further background information, head to:
- [Neural Networks](https://www.heise.de/select/make/2021/6/2126410443385102621)
- [Training Neural Networks](https://www.heise.de/select/make/2022/1/2134114065999161585)
- [Programming on the ESP32](https://www.heise.de/select/make/2022/2/2204010051597422030)
---
## Download π½
The latest available version can be found on the [Releases page](https://github.com/jomjol/AI-on-the-edge-device/releases).
---
## Flashing the ESP32 πΎ
Initially, you will have to flash the ESP32 via a USB connection. Later updates are possible directly over the air (OTA using Wi-Fi).
There are different ways to flash your ESP32:
- The preferred way is the [Web Installer and Console](https://jomjol.github.io/AI-on-the-edge-device/index.html), a browser-based tool to flash the ESP32 and extract the log over USB:
- Flash Tool from Espressif
- ESPtool (command-line tool)
See the [documentation](https://jomjol.github.io/AI-on-the-edge-device-docs/Installation/) for more information.
---
## Flashing the SD Card πΎ
The SD card can be set up automatically after the firmware is installed. See the [documentation](https://jomjol.github.io/AI-on-the-edge-device-docs/Installation/#remote-setup-using-the-built-in-access-point) for details. For this to work, the SD card must be FAT formatted (which is the default on a new SD card).
Alternatively, the SD card can still be set up manually. See the [documentation](https://jomjol.github.io/AI-on-the-edge-device-docs/Installation/#3-sd-card) for details.
---
## Casing π οΈ
Various 3D-printable housings can be found here:
- π§ [Water Meter](https://www.thingiverse.com/thing:4573481)
- β‘ [Power Meter](https://www.thingiverse.com/thing:5028229)
- π₯ [Gas Meter](https://www.thingiverse.com/thing:5224101)
- π· [ESP32-cam housing only](https://www.thingiverse.com/thing:4571627)
- π‘ [Top cover and Antenna Holder](https://www.printables.com/model/452139-cover-for-esp32-cam-water-meter)
---
## Donate β
If you'd like to support the developer with a cup of coffee, you can do so via [PayPal](https://www.paypal.com/donate?hosted_button_id=8TRSVYNYKDSWL).
---
## Support π¬
If you have any technical problems, please search the [discussions](https://github.com/jomjol/AI-on-the-edge-device/discussions). In case you find a bug or have a feature request, please open an [issue](https://github.com/jomjol/AI-on-the-edge-device/issues).
For any other issues, you can contact the developer via email:
---
## Changes and History π
See the [Changelog](Changelog.md) for detailed information.
---
## Build It Yourself π¨
See the [Build Instructions](code/README.md) for step-by-step guidance.
---
## Tools π οΈ
* Logfile downloader and combiner (Thanks to [reserve85](https://github.com/reserve85))
* It can be found at ['/tools/logfile-tool'](https://github.com/jomjol/AI-on-the-edge-device/tree/main/tools/logfile-tool).
---
## Additional Ideas π‘
There are some ideas and feature requests which are not currently being pursuedβmainly due to capacity constraints on the part of the developers. These features are collected in the [issues](https://github.com/jomjol/AI-on-the-edge-device/issues) and in [FeatureRequest.md](FeatureRequest.md).
---
## Our Contributors β€οΈ
---
