TPLDetect: Thermography-based Pipeline Leak Detection

Read full text Summarise with VIRAT
Authors: Elena Vollmer
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This release contains the version of the TPLDetect (Thermography-based Pipeline Leak Detection) software accompanying the PhD dissertation by E. Vollmer titled "Towards Automatic Thermography-Based Leak Detection in District Heating Systems". TPLDetect implements a fully automated analysis pipeline for unmanned aircraft system (UAS)-based thermal infrared (TIR) imagery, including: preprocessing (georeferencing, masking, temperature extraction), thermal anomaly detection using the transformer model TASeg (Thermal Anomaly Segmenter), false alarm removal using the CNN model TUFSeg (Thermal Urban Feature Segmenter), postprocessing and mapping of leak candidates. This version corresponds to the implementation used in the dissertation and associated publications and is archived to ensure transparency and reproducibility. Further details of related publications are provided in the repository README. Repository: https://github.com/emvollmer/TPLDetect

Fields of Study & Subjects

Infrastructure Maintenance and Monitoring Thermography and Photoacoustic Techniques Water Systems and Optimization

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 March 2026
Language
EN