UTM Dataset

Dataset Description This dataset was created to support Article: VisionGauge: a computer vision model to detect and read U-tube manometers and is available on Roboflow and Hugging Face. It consists of images of U-tube manometers constructed using a transparent PVC water level hose (5/16" × 1 mm) and flexible measuring tapes of different colors, each with a length of 150 cm (60 inches). The manometric fluids represented in the dataset include water, oil, and dyed water. The dataset is intended for computer vision regression and classification tasks, specifically targeting the reading of liquid column levels. The dataset includes 48,218 augmented images, derived from 20,036 unique original images. All annotations were performed using the RoboFlow Annotate Tool, with label precision within ± 0.1 cm. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Dataset Split Training set: 42274 images Validation set: 5319 images Test set: 625 images -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Data Structure dataset/├── train.zip/│ ├── 10.2/│ │ ├── image23.png│ │ └── ...│ ├── 10.4/│ └── ...├── validation.zip/│ ├── 9.8/│ └── ...└── test.zip/│ ├── 10.0/│ └── ...└── dataset_mapping.csv Each subfolder name corresponds to the label value (e.g., water column height in centimeters). Images inside the folder share the same height value. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- LICENSE This dataset is released under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license. You are free to share and adapt the material, provided you give appropriate credit and distribute any derivative works under the same license. For details, see the LICENSE file. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- CITATION @misc{santos2026utm, author = {Santos, C.S. and Arima, M. N.}, title = {{UTM Dataset}}, year = {2026}, month = {jan}, publisher = {Hugging Face}, doi = {10.57967/hf/7558}, url = {https://huggingface.co/datasets/claytonsds/UTM_Dataset}}