ELECTRONIC DEVICE, METHOD, AND COMPUTER-READABLE STORAGE MEDIUM FOR IDENTIFYING OBJECT FROM IMAGE DATA

An electronic device according to an embodiment comprises a memory for storing instructions and at least one processor operably coupled to the memory, wherein the at least one processor may be configured to, when the instructions are executed: receive an image obtained by capturing at least one obje...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: OH, Myeongseok, YANG, Cheoljong, LEE, Jusung, JUNG, Harim, PARK, Junhyoung, LEE, Younghyun, LEE, Seongwhan
Format: Patent
Sprache:eng ; fre ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:An electronic device according to an embodiment comprises a memory for storing instructions and at least one processor operably coupled to the memory, wherein the at least one processor may be configured to, when the instructions are executed: receive an image obtained by capturing at least one object; obtain first information from the image by using a first neural network including blocks of channels for processing the image, on the basis of a convolution operation; and obtain a class of the at least one object and second information indicating a location where the at least one object is captured within the image, by using a second neural network for processing the obtained first information, wherein the first neural network may be an interconnection of the blocks selected from among candidate blocks, on the basis of third information related to the number of channels of the candidate blocks and allocated to the candidate blocks. Various other embodiments are possible. Un dispositif électronique selon un mode de réalisation comprend une mémoire pour stocker des instructions et au moins un processeur couplé de manière fonctionnelle à la mémoire, l'au moins un processeur pouvant être configuré pour, lorsque les instructions sont exécutées : recevoir une image obtenue par capture d'au moins un objet ; obtenir des premières informations à partir de l'image à l'aide d'un premier réseau neuronal comprenant des blocs de canaux pour traiter l'image, sur la base d'une opération de convolution ; et obtenir une classe de l'au moins un objet et des secondes informations indiquant un emplacement où l'au moins un objet est capturé à l'intérieur de l'image, à l'aide d'un second réseau neuronal pour traiter les premières informations obtenues, le premier réseau neuronal pouvant être une interconnexion des blocs sélectionnés parmi des blocs candidats, sur la base de troisièmes informations relatives au nombre de canaux des blocs candidats et attribuées aux blocs candidats. Divers autres modes de réalisation sont possibles. 일 실시예에 따른 전자 장치는, 인스트럭션들을 저장하기 위한 메모리 및 상기 메모리와 작동적으로 결합된(operably coupled to) 적어도 하나의 프로세서를 포함하고, 상기 적어도 하나의 프로세서는, 상기 인스트럭션들이 실행될 때에, 적어도 하나의 객체가 캡쳐된 이미지를 수신하고 콘볼루션 연산(convolution operation)에 기반하여 상기 이미지를 처리하기 위한 채널들의 블록들을 포함하는 제1 뉴럴 네트워크를 이용하여, 상기 이미지로부터 제1 정보를 획득하고 및 상기 획득된 제1 정보를 처리하기 위한 제2 뉴럴 네트워크를 이용하여, 상기 적어도 하나의 객체의 클래스, 및 상기 이미지 내에서 상기 적어도 하나의 객체가 캡쳐된 위치를 나타내는 제2 정보를 획득하도록 구성될 수 있고, 상기 제1 뉴럴 네트워크는, 후보 블록들에 할당되고, 상기 후보 블록들의 상기 채널들의 수와 관련된, 제3 정