Employing deep-learning and artificial-intelligence (AI) techniques onboard spacecraft can dramatically improve priority data selection to ensure more effective use of the available downlink. However, deployment of effective deep-learning models requires significant training on the ground, which may not be feasible, due to limited data available in an unexplored environment. Therefore, this research explores building robust classification models for onboard data processing where training data is highly limited using transfer-learning techniques. In this paper, we focus on the use case of hyperspectral imaging for remote sensing, a domain where the high dimensionality of the data from the sensor can rapidly saturate the downlink bandwidth. With this bottleneck, there is an impending need to autonomously and robustly classify data onboard to optimize downlink of high-impact measurements, thus maximizing the scientific utility per bit transmitted to the ground. This paper examines the use of deep neural networks onboard for hyperspectral image classification in a communication-limited scenario to analyze how the models perform with limited training data. The use of transfer learning can ameliorate the issue of poor generalization by transferring features learned from training on a large source dataset for one classification task to the target classification task with limited training data. For two deep-learning models from literature, we compare the accuracy of the models trained using transfer learning to models trained from scratch using a random weight initialization with varying amounts of training data. We demonstrate the feasibility and performance of running inference of the deep-learning models on representative flight-like hardware.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Onboard Hyperspectral Image Classification via Transfer Learning for Communication-Limited Spacecraft


    Beteiligte:


    Erscheinungsdatum :

    2022-03-05


    Format / Umfang :

    1214591 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Hyperspectral Feature Detection Onboard the Earth Observing One Spacecraft

    Thompson, David R. / Chien, Steve / Bornstein, Benjamin et al. | NTRS | 2012


    Method for Design of `smart' Spacecraft Onboard Decision Making in Case of Limited Onboard Resources

    Tyugashev, Andrey / Orlov, Sergei | British Library Conference Proceedings | 2020


    Spacecraft Onboard Data Management

    T. D. Guyenne | NTIS | 1978


    Standardized Spacecraft Onboard Interfaces

    Smith, Joseph / Plummer, Chris / Plancke, Patrick | AIAA | 2003


    Standardized Spacecraft Onboard Interfaces

    Smith, J. / Plummer, C. / Plancke, P. et al. | British Library Conference Proceedings | 2003