Multi-band image generation system and method for optical satellite imagery using deep-learning network

The present invention relates to a multi-band image generation system for an optical satellite image using a deep-learning network and a method thereof. The present invention relates to technology for generating a multi-band image based on the image of a PAN band by analyzing a non-linear relationsh...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	KIM SHINWOOK, HEO HAENG PAL
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The present invention relates to a multi-band image generation system for an optical satellite image using a deep-learning network and a method thereof. The present invention relates to technology for generating a multi-band image based on the image of a PAN band by analyzing a non-linear relationship between the PAN band and each multi-band using a deep learning network. The multi-band image generation system includes: a data input part; and a model processing part. 본 발명은 딥러닝을 이용한 광학 위성영상 다중 대역 이미지 생성 시스템 및 그 방법에 관한 것으로서, 딥러닝 네트워크를 이용하여 PAN 대역과 각 다중 대역 사이의 비선형적인 관계의 분석을 수행하여, PAN 대역의 이미지를 기반으로 다중 대역 이미지를 생성할 수 있는 기술에 관한 것이다.