ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Real-time Precise Object Segmentation Using a Pixel-wise Coarse-fine Method with Deep Learning for Automated Manufacturing
Cited 10 time in scopus Download 145 time Share share facebook twitter linkedin kakaostory
저자
조재민, 강상승, 김계경
발행일
202201
출처
Journal of Manufacturing Systems, v.62, pp.114-123
ISSN
0278-6125
출판사
Society of Manufacturing Engineers (SME)
DOI
https://dx.doi.org/10.1016/j.jmsy.2021.11.004
협약과제
18PS1500, 작업자 공간공유 및 스마트공장 적용을 위한 차세대 제조용 로봇, 강상승
초록
The Fourth Industrial Revolution has rapidly increased the demand, beyond the pace of industrial automation, for artificial intelligence (AI) and robots to undertake sophisticated tasks such as assembly and packaging without the use of feed devices. For commercial use, suitable technologies for stable real-time detection and precise segmentation are deemed essential. Particularly, because AI is used in an embedded environment, the model and algorithm should be lightweight. To satisfy the industrial requirements and solve related difficulties, this paper proposes a precision object segmentation method to accurately detect objects moving on a conveyor belt without using feed devices. A new backbone network was designed to reinforce the feature extraction layers using convolutional blocks, and it was added to the object detection component. To maintain lightweight compactness and complement feature mapping, a multi-level pooling layer was included. In addition, a loss function that focuses on difficult samples and a data augmentation method for learning were used to improve the performance without affecting the model architecture. In the segmentation step, the authors extracted and analyzed pixel-wise features to acquire more pertinent vertex candidates and utilized an intensity-difference search algorithm to select the optimal outline component among the candidates for precise segmentation. Finally, the posture information of the object was estimated using the object's geometric features to estimate the grasping point. The experimental results confirmed the improved precision and accuracy of the proposed method in object-detection and segmentation, demonstrating that the model is ideal for our manufacturing dataset.
KSP 제안 키워드
Augmentation method, Automated manufacturing, Backbone Network, Coarse-fine, Data Augmentation, Embedded environment, Feature extractioN, Geometric features, Industrial automation, Industrial requirements, Model architecture
본 저작물은 크리에이티브 커먼즈 저작자 표시 - 비영리 - 변경금지 (CC BY NC ND) 조건에 따라 이용할 수 있습니다.
저작자 표시 - 비영리 - 변경금지 (CC BY NC ND)