meter-reading

Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by any camera or ESP32-CAM. 100% local, any CPU.

A component to run AI model on esphome

UFPR-AMR: a dataset for image-based automatic meter reading containing 2,000 images taken from inside a warehouse of the Energy Company of Paraná (Copel), which directly serves more than 4 million consuming units in the Brazilian state of Paraná.

Home Assistant Pesc (PSC/EIRC) integration

Meter display segmentation and reading the digits using OCR

meter (water, gas, electricity) reader from image to digits

ESPHome component for measuring momentary power and overall energy consumption using an analog Ferraris electricity meter

Copel-AMR: a dataset for image-based automatic meter reading containing 12,500 meter images acquired in the field by the employees of the Energy Company of Paraná (Copel), which directly serves more than 4 million consuming units in the Brazilian state of Paraná.

Central wmbusmeters decoding backend for a distributed Wireless M-Bus gateway — receives RAW telegrams from ESP32 via MQTT, with WebUI and Home Assistant Discovery.

UFPR-ADMR-v2: a dataset for image-based automatic meter reading containing 5,000 dial meter images obtained on-site by employees of the Energy Company of Paraná (Copel), which serves more than 4 million consuming units in the Brazilian state of Paraná.

UFPR-ADMR-v1: a dataset for image-based automatic meter reading containing 2,000 dial meter images obtained on-site by employees of the Energy Company of Paraná (Copel), which serves more than 4 million consuming units in the Brazilian state of Paraná.

An automated data collection system that can read sintering data on the meter by a single camera

Android app to track water, gas, electricity, heating oil and heat meters: readings, charts and yearly forecasts adjusted for degree days. Free and open source, no account, no ads, your data stays on your phone. EN · FR · NL · DE

⚡ TASKZ — Automated prepaid token tracker & blackout alerter for Kenya Power (KPLC) customers. Add a meter once, the backend does the rest: full purchase history, usage-rate prediction, days-left countdown, and pay-before alerts via Telegram.

SyncG is a tool designed for generating synthetic analogy gauge datasets. This repository provides both pre-built datasets and the original scripts to generate your own customized data.

Train AI-on-the-edge-device digit models in the browser, from the device page

Reading fuel meters without training a ML/DL model

Local image recognition helpers for Home Assistant: the state of an area (garage door, car, gate) and experimental meter reading, running on your own machine with tarsius.

Excel-based monthly consumption tracking template for office utilities, supplies, and manpower with automated calculations and summary dashboard

💧 Automated water meter reading system — AI-powered digit recognition for utility meters using OCR and deep learning