METHOD AND APPARATUS OF PROCESSING IMAGE

According to one embodiment, the present invention provides an image processing method and device, which may receive a first feature map, obtain a deterministically defined kernel based on the magnification ratio of the first feature map, and perform a transposition convolution operation between the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	KWON, DONG HYUK, CHO, MIN KYOUNG
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY GYROSCOPIC INSTRUMENTS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL MEASURING MEASURING DISTANCES, LEVELS OR BEARINGS NAVIGATION OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS OPTICS PHOTOGRAMMETRY OR VIDEOGRAMMETRY PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION SURVEYING TESTING TRANSMISSION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	According to one embodiment, the present invention provides an image processing method and device, which may receive a first feature map, obtain a deterministically defined kernel based on the magnification ratio of the first feature map, and perform a transposition convolution operation between the first feature map and the kernel, so as to up-sample the first feature map to the second feature map, and output the second feature map. 일 실시예에 따른 영상 처리 방법 및 장치는 제1 특징 맵을 수신하고, 제1 특징 맵의 확대 비율에 기초하여 결정적으로 정의되는 커널을 획득하고, 제1 특징 맵과 커널 간의 전치 합성곱 연산을 수행함으로써, 제1 특징 맵을 제2 특징 맵으로 업 샘플링하며, 제2 특징 맵을 출력한다.