What question did this study set out to answer?

The aim is to develop a robust optical localization method for hypersonic platforms using deep learning techniques.

April 23, 2026Open Access

Deep learning-based robust optical localization for hypersonic platforms

ACAdrien Chan-Hon-TongUniversité Paris-Saclay APAurélien PlyerUniversité Paris-Saclay BCBaptiste CadalenUniversité Paris-Saclay

Key Points

The aim is to develop a robust optical localization method for hypersonic platforms using deep learning techniques.
Developed a new framework that encodes the appearance of the target's surroundings from multiple images.
Tested performance against a classical image registration baseline in various conditions, including snowy scenes.
The new deep learning framework outperformed the traditional image registration method.
Improvements were particularly notable in challenging bimodal scenes, suggesting greater robustness.

Abstract

Abstract Sensor-based localization is required for long-range platforms when GNSS can be denied. To bypass the structural limitations of the classical registration-on-reference-image framework, we offer in this paper to encode the appearance of the surrounding of the target (at all resolutions) from a stack of images of the scene into a deep network. This new framework outperforms the registration baseline in our experiments, in particular on a bimodal scene (which can or can not be snowy). This invites larger benchmarks from academic and industrial community to conclude on the applicability of this method on real use cases.

Perguntar à IA

Bookmark

View Full Paper