METHOD AND DEVICE FOR DETECTING TIRE EXTERIOR DEFECT ON BASIS OF DEEP LEARNING

• Main Authors: KIM, Seong Kyu, LEE, Woo Ram, BAE, You Suk, HUR, Jo Hoon, LEE, Jae Geun, KEUM, Gi Ryun
• Format: Patent
• Language: English; French; Korean
• Published: 23.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

A method for detecting a tire exterior defect on the basis of deep learning according to the present invention comprises the steps of: collecting exterior images related to a tire; analyzing the collected exterior images by using a predefined failure detecting model, thereby detecting a failure related to the tire; and determining the type of the failure related to the tire, if a failure related to the tire is detected, by analyzing the detected failure area by using a failure classification model defined independently of the failure detecting model. Un procédé de détection d'un défaut extérieur de pneu sur la base d'un apprentissage profond selon la présente invention comprend les étapes consistant à : collecter des images extérieures associées à un pneu ; analyser les images extérieures collectées à l'aide d'un modèle de détection de défaillance prédéfini, ce qui permet de détecter une défaillance liée au pneu ; et déterminer le type de la défaillance liée au pneu, si une défaillance liée au pneu est détectée, par analyse de la zone de défaillance détectée à l'aide d'un modèle de classification de défaillance défini indépendamment du modèle de détection de défaillance. 본 발명에 따른 딥러닝 기반의 타이어 외관 결함 검출 방법은, 타이어에 대한 외관 이미지를 수집하는 단계; 상기 수집된 외관 이미지를 기정의된 불량 검출 모델을 이용해 분석하여 상기 타이어에 대한 불량 여부를 검출하는 단계; 및 상기 타이어에 대한 불량이 검출되면, 검출된 불량 영역을 상기 불량 검출 모델과 독립적으로 정의된 불량 분류 모델을 이용해 분석하여 상기 타이어에 대한 불량 유형을 결정하는 단계;를 포함한다.