Saved in:
Bibliographic Details
Main Authors: Thomas, Mia, Ablett, Trevor, Kelly, Jonathan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12593
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912384895942656
author Thomas, Mia
Ablett, Trevor
Kelly, Jonathan
author_facet Thomas, Mia
Ablett, Trevor
Kelly, Jonathan
contents Unmanned aerial vehicles (UAVs) enable operations in remote and hazardous environments, yet the visible-spectrum, camera-based navigation systems often relied upon by UAVs struggle in low-visibility conditions. Thermal cameras, which capture long-wave infrared radiation, are able to function effectively in darkness and smoke, where visible-light cameras fail. This work explores learned cross-spectral (thermal-visible) point features as a means to integrate thermal imagery into established camera-based navigation systems. Existing methods typically train a feature network's detection and description outputs directly, which often focuses training on image regions where thermal and visible-spectrum images exhibit similar appearance. Aiming to more fully utilize the available data, we propose a method to train the feature network on the tasks of matching and registration. We run our feature network on thermal-visible image pairs, then feed the network response into a differentiable registration pipeline. Losses are applied to the matching and registration estimates of this pipeline. Our selected model, trained on the task of matching, achieves a registration error (corner error) below 10 pixels for more than 75% of estimates on the MultiPoint dataset. We further demonstrate that our model can also be used with a classical pipeline for matching and registration.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12593
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Cross-Spectral Point Features with Task-Oriented Training
Thomas, Mia
Ablett, Trevor
Kelly, Jonathan
Computer Vision and Pattern Recognition
Unmanned aerial vehicles (UAVs) enable operations in remote and hazardous environments, yet the visible-spectrum, camera-based navigation systems often relied upon by UAVs struggle in low-visibility conditions. Thermal cameras, which capture long-wave infrared radiation, are able to function effectively in darkness and smoke, where visible-light cameras fail. This work explores learned cross-spectral (thermal-visible) point features as a means to integrate thermal imagery into established camera-based navigation systems. Existing methods typically train a feature network's detection and description outputs directly, which often focuses training on image regions where thermal and visible-spectrum images exhibit similar appearance. Aiming to more fully utilize the available data, we propose a method to train the feature network on the tasks of matching and registration. We run our feature network on thermal-visible image pairs, then feed the network response into a differentiable registration pipeline. Losses are applied to the matching and registration estimates of this pipeline. Our selected model, trained on the task of matching, achieves a registration error (corner error) below 10 pixels for more than 75% of estimates on the MultiPoint dataset. We further demonstrate that our model can also be used with a classical pipeline for matching and registration.
title Learning Cross-Spectral Point Features with Task-Oriented Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12593