METHOD FOR CLASSIFYING SCENE FROM VIDEO CONTENTS AND SCENE CLASSIFICATION DEVICE PERFORMING METHOD

A method for classifying a scene in a video content according to one embodiment of the present invention may comprise: a step of classifying a plurality of frames into a plurality of shots, based on image information of the plurality of frames included in the video content; a step of classifying the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SHIN HYUNJUNG, SONG MINGYUNG
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method for classifying a scene in a video content according to one embodiment of the present invention may comprise: a step of classifying a plurality of frames into a plurality of shots, based on image information of the plurality of frames included in the video content; a step of classifying the plurality of shots into a plurality of shot groups, based on a similarity between the frames included in each of the plurality of shots; and a step of classifying the plurality of shot groups into at least one scene, based on first time information of the plurality of shot groups. Therefore, the present invention enables the scene to be accurately classified in the video content without a human handwork. 본 발명의 일 실시 예에 따른 비디오 콘텐츠에서 씬을 구분하는 방법은, 비디오 콘텐츠에 포함된 복수의 프레임들의 영상 정보에 기초하여, 상기 복수의 프레임들을 복수의 샷들로 구분하는 단계; 상기 복수의 샷들 각각에 포함된 프레임 사이의 유사도에 기초하여, 상기 복수의 샷들을 복수의 샷 그룹들로 구분하는 단계; 상기 복수의 샷 그룹들의 제1 시간 정보에 기초하여, 상기 복수의 샷 그룹들을 적어도 하나의 씬으로 구분하는 단계를 포함할 수 있다.