METHOD AND APPARATUS FOR ENHANCING VIDEO FRAME RESOLUTION

A method for enhancing video frame resolution according to one embodiment of the present disclosure may include loading video data including a plurality of frames having low resolution; selecting, from the group of artificial neural networks for image processing, artificial neural networks for image...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	CHOI, Hyun Dae, MOON, Seung Hwan, KIM, Young Kwon, HWANG, Keum Sung
Format:	Patent
Sprache:	eng
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:	A method for enhancing video frame resolution according to one embodiment of the present disclosure may include loading video data including a plurality of frames having low resolution; selecting, from the group of artificial neural networks for image processing, artificial neural networks for image processing having different complexity to apply to two different frames of a video; and generating a high resolution frame by processing each frame of the video according to the selected artificial neural networks for image processing. A neural network for image processing according to one embodiment of the present disclosure may be a deep neural network generated via machine learning, and an input and output of the video may take place in an Internet of Things environment using a 5G network.