멀티스펙트럴 영상기반 전기시설물 이상치 감지 (Defect Detection for Electrical Facilities based on Multispectral Imagery)

서지정보

· 발행기관 : 제어·로봇·시스템학회
· 수록지 정보 : 제어.로봇.시스템학회 논문지 / 28권 / 3호 / 225 ~ 231페이지
· 저자명 : 김형준, 김태주, 최유경

초록

Regular inspection of electrical facilities plays a significant role in preventing deterioration caused by aging equipment, but thedangers associated with these inspections make it difficult for examiners to perform them without first suspending the power. Currently,these inspections cause shutdowns and result in loss of productivity. For this reason, researchers are actively exploring new ways to detectfaults in electrical facilities using deep learning algorithms and various modalities such as single-infrared, single-RGB, and multispectralimagery. Existing methods either use a single modality or fuse two modalities with image registration that decreases technologyaccessibility. This paper will explore the use of a multispectral anomaly pre-detector based on YOLOv5s, a simple yet effective singlestagedetector. The anomaly region detector is a real-world application of this technology that detects parts in the potentially anomalousdevice and finds the anomalous regions within those parts. In order to verify the two detectors, far- and near-distance datasets were obtainedand evaluated using the proposed models. The results indicate that the proposed pipeline enables pixel-level electrical fault detection.

영어초록

Regular inspection of electrical facilities plays a significant role in preventing deterioration caused by aging equipment, but thedangers associated with these inspections make it difficult for examiners to perform them without first suspending the power. Currently,these inspections cause shutdowns and result in loss of productivity. For this reason, researchers are actively exploring new ways to detectfaults in electrical facilities using deep learning algorithms and various modalities such as single-infrared, single-RGB, and multispectralimagery. Existing methods either use a single modality or fuse two modalities with image registration that decreases technologyaccessibility. This paper will explore the use of a multispectral anomaly pre-detector based on YOLOv5s, a simple yet effective singlestagedetector. The anomaly region detector is a real-world application of this technology that detects parts in the potentially anomalousdevice and finds the anomalous regions within those parts. In order to verify the two detectors, far- and near-distance datasets were obtainedand evaluated using the proposed models. The results indicate that the proposed pipeline enables pixel-level electrical fault detection.

참고자료

· 없음