Ground-Penetrating Radar-Based Detection of Railroad Switches and Direction Classification using Near-Surface Features
Noll M, Kohnert S, Caldero P (2025)
Publication Type: Conference contribution
Publication year: 2025
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 339-342
Conference Proceedings Title: 2025 22nd European Radar Conference, EuRAD 2025
Event location: Utrecht, NLD
ISBN: 9782874870835
DOI: 10.23919/EuRAD65285.2025.11234006
Abstract
In this work, a novel approach for railroad switch detection and direction classification using ground-penetrating radar (GPR) is presented. At first, relevant features are extracted from data collected by a GPR sensor array. A sample signature is created from these features, that captures the general feature pattern along switches. Part of this signature then serves as the basis for a detection and classification approach that combines a static similarity assessment with a dynamic time-warping (DTW) approach. The outcome from both methods are then compared within a decision-making framework, which classifies GPR measurement data based on threshold values. The proposed approach is able to detect and accurately classify 93.75% of switches within the evaluated track network.
Involved external institutions
Germany (DE)How to cite
APA:
Noll, M., Kohnert, S., & Caldero, P. (2025). Ground-Penetrating Radar-Based Detection of Railroad Switches and Direction Classification using Near-Surface Features. In 2025 22nd European Radar Conference, EuRAD 2025 (pp. 339-342). Utrecht, NLD: Institute of Electrical and Electronics Engineers Inc..
MLA:
Noll, Maximilian, Soren Kohnert, and Pau Caldero. "Ground-Penetrating Radar-Based Detection of Railroad Switches and Direction Classification using Near-Surface Features." Proceedings of the 22nd European Radar Conference, EuRAD 2025, Utrecht, NLD Institute of Electrical and Electronics Engineers Inc., 2025. 339-342.
BibTeX: Download