Thermal Anomaly Segmentation Dataset - Thermal UAS-based Images from Germany with Annotations for Semantic Segmentation Model Training

The Thermal Anomaly Segmentation (TASeg) dataset can be utilised for the multi-stage training of spectral deep learning models for binary semantic segmentation. Specifically, it was designed to be used in the context of leak detection in district heating networks to segment thermal anomalies from the background in urban cityscapes.

The provided data consists of thermal imagery recorded in Germany, close to Munich and Karlsruhe, in December 2019 and January / March 2021 using FLIR and DJI's Zenmuse XT2 and a Matrice 600 / Matrice 300 unmanned aircraft system (UAS). Seven datasets (KA1, KA2, MU1, MU2, MU6, MU15, and MU16) form the basis of the dataset. These are provided as part of a previous Zenodo dataset publication "Detecting District Heating Leaks in Thermal Imagery: Comparison of Anomaly Detection Methods - Source Code and Datasets".

The dataset as a whole consists of two sets:
- The "generated_set" contains segmented annotation masks generated via heuristic algorithm, specifically adaptive triangle-histogram-thresholding.
- The "manual_set" consists of segmented annotation masks created by hand, by means of a custom labelling GUI tool.
... mehr

These two datasets are split as follows for training:
- Generated: 3,171 images -> Train: 2,142, Validation: 404, Test: 625
- Manual: 269 images -> Train: 172, Validation: 52, Test: 45