A principled representation of elongated structures using heatmaps

Kordon FJ, Stiglmayr M, Maier A, Martín Vicario C, Pertlwieser T, Kunze H (2023)

Publication Type: Journal article

Publication year: 2023


Original Authors: Florian Kordon, Michael Stiglmayr, Andreas Maier, Celia Martín Vicario, Tobias Pertlwieser, Holger Kunze

Book Volume: 13

Article Number: 15253

Issue: 1

DOI: 10.1038/s41598-023-41221-2


The detection of elongated structures like lines or edges is an essential component in semantic image analysis. Classical approaches that rely on significant image gradients quickly reach their limits when the structure is context-dependent, amorphous, or not directly visible. This study introduces a principled mathematical description of elongated structures with various origins and shapes. Among others, it serves as an expressive operational description of target functions that can be well approximated by Convolutional Neural Networks. The nominal position of a curve and its positional uncertainty are encoded as a heatmap by convolving the curve distribution with a filter function. We propose a low-error approximation to the expensive numerical integration by evaluating a distance-dependent function, enabling a lightweight implementation with linear time complexity. We analyze the method’s numerical approximation error and behavior for different curve types and signal-to-noise levels. Application to surgical 2D and 3D data, semantic boundary detection, skeletonization, and other related tasks demonstrate the method’s versatility at low errors.

Authors with CRIS profile

Involved external institutions

How to cite


Kordon, F.J., Stiglmayr, M., Maier, A., Martín Vicario, C., Pertlwieser, T., & Kunze, H. (2023). A principled representation of elongated structures using heatmaps. Scientific Reports, 13. https://dx.doi.org/10.1038/s41598-023-41221-2


Kordon, Florian Johannes, et al. "A principled representation of elongated structures using heatmaps." Scientific Reports 13 (2023).

BibTeX: Download