This paper presents the development of an efficient artificial intelligence (AI) methodologies for onboard satellite image processing. The proposed system features a fast and efficient neural network designed to process radiometrically corrected multispectral optical images directly onboard satellites. The architecture is composed of a backbone feature extractor that generates semantically meaningful feature representations of input data, which are shared with multiple task-specific heads for various applications, including image classification, segmentation, and object detection. Training employs a self-supervised learning approach, significantly reducing the need for labelled data, with only small application-specific datasets required. The flexible design allows new tasks to be added without retraining the entire model or making major code changes. To ensure suitability for onboard use, the model is optimized for efficiency and low energy consumption through the use of quantization techniques and efficient deep learning modules. Key applications include cloud segmentation, fire detection, and flood detection, which demand low-latency responses for early warning and damage assessment.
A multi-service edge-AI architecture based on self-supervised learning / Magli, E; Angarano, S.; Bassetti, S.; Bianchi, T.; Boccardo, P.; Bucci, S.; Chiaberge, M.; Inzerillo, G.; Lisi, D.; Mascetti, G.; Mergè, M.; Monaco, C.; Pasturensi, M.; Piccinini, D.; Valsesia, D.; Zema, G.. - ELETTRONICO. - (2024), pp. 1-9. (Intervento presentato al convegno 75th International Astronautical Congress tenutosi a Milan (Ita) nel 14-18 October 2024).
A multi-service edge-AI architecture based on self-supervised learning
Magli E;Angarano S.;Bianchi T.;Boccardo P.;Bucci S.;Chiaberge M.;Inzerillo G.;Piccinini D.;Valsesia D.;
2024
Abstract
This paper presents the development of an efficient artificial intelligence (AI) methodologies for onboard satellite image processing. The proposed system features a fast and efficient neural network designed to process radiometrically corrected multispectral optical images directly onboard satellites. The architecture is composed of a backbone feature extractor that generates semantically meaningful feature representations of input data, which are shared with multiple task-specific heads for various applications, including image classification, segmentation, and object detection. Training employs a self-supervised learning approach, significantly reducing the need for labelled data, with only small application-specific datasets required. The flexible design allows new tasks to be added without retraining the entire model or making major code changes. To ensure suitability for onboard use, the model is optimized for efficiency and low energy consumption through the use of quantization techniques and efficient deep learning modules. Key applications include cloud segmentation, fire detection, and flood detection, which demand low-latency responses for early warning and damage assessment.File | Dimensione | Formato | |
---|---|---|---|
IAC-24,B1,4,2,x87460.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
743.31 kB
Formato
Adobe PDF
|
743.31 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2995769