mahingaRodin/rwanda-water-meter-readiing-system

An AI-based computer vision project for automatic water meter detection and reading using YOLO object detection. # Rwanda Water Meter Reading System An AI-based computer vision project for automatic water meter detection and reading using YOLO object detection. This project includes: - dataset collection - image labeling - dataset preparation - YOLO training - retraining - prediction - reading reconstruction The system is trained to detect: - water meter - reading window - digits `0–9` - unclear digits (`unknown`) --- # Features The project provides tools for: - collecting water meter datasets - labeling water meter images - rotating and cleaning images - validating YOLO datasets - preparing train/val/test datasets - training YOLO models - retraining from latest best model - predicting on test images - reconstructing final meter readings --- # Project Structure ```text rwanda-water-meter-reading-system/ ├── raw_dataset/ │ ├── images/ │ └── labels/ │ ├── dataset/ │ ├── images/ │ │ ├── train/ │ │ ├── val/ │ │ └── test/ │ │ │ ├── labels/ │ │ ├── train/ │ │ ├── val/ │ │ └── test/ │ │ │ ├── reports/ │ └── data.yaml │ ├── scripts/ │ ├── 01_label_images.py │ ├── 02_prepare_yolo_dataset.py │ ├── 03_train_yolo.py │ ├── 04_predict_on_test_images.py │ └── 05_retrain.py │ ├── training_runs/ ├── prediction_outputs/ └── README.md ``` --- # Supported Classes | Class ID | Class Name | Description | |---|---|---| | 0 | meter | Full physical water meter | | 1 | window | Reading/display window | | 2 | 0 | Digit 0 | | 3 | 1 | Digit 1 | | 4 | 2 | Digit 2 | | 5 | 3 | Digit 3 | | 6 | 4 | Digit 4 | | 7 | 5 | Digit 5 | | 8 | 6 | Digit 6 | | 9 | 7 | Digit 7 | | 10 | 8 | Digit 8 | | 11 | 9 | Digit 9 | | 12 | unknown | Unclear/unreadable digit | --- # Installation ## Install dependencies ```bash pip install ultralytics pip install opencv-python pip install PySide6 ``` --- # Dataset Structure Expected raw dataset structure: ```text raw_dataset/ ├── images/ └── labels/ ``` Example: ```text raw_dataset/ ├── images/ │ ├── wm_0001.jp …