ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Real-Time Hair Segmentation Using Mobile-Unet
Cited 5 time in scopus Download 12 time Share share facebook twitter linkedin kakaostory
저자
윤호섭, 박성우, 유장희
발행일
202101
출처
Electronics, v.10 no.2, pp.1-12
ISSN
2079-9292
출판사
MDPI
DOI
https://dx.doi.org/10.3390/electronics10020099
협약과제
20PS2400, 서비스 로봇의 사회적 상호작용을 위한 소셜 로봇지능 원천 기술 개발, 윤호섭
초록
We described a real-time hair segmentation method based on a fully convolutional network with the basic structure of an encoder?밺ecoder. In one of the traditional computer vision techniques for hair segmentation, the mean shift and watershed methodologies suffer from inaccuracy and slow execution due to multi-step, complex image processing. It is also difficult to execute the process in real-time unless an optimization technique is applied to the partition. To solve this problem, we exploited Mobile-Unet using the U-Net segmentation model, which incorporates the optimization techniques of MobileNetV2. In experiments, hair segmentation accuracy was evaluated by different genders and races, and the average accuracy was 89.9%. By comparing the accuracy and execution speed of our model with those of other models in related studies, we confirmed that the proposed model achieved the same or better performance. As such, the results of hair segmentation can obtain hair information (style, color, length), which has a significant impact on human-robot interaction with people.
키워드
Computer vision, Deep learning, FCN, Hair segmentation, HRI, Mobile-Unet
KSP 제안 키워드
Basic structure, Complex image, Computer Vision(CV), Execution speed, Fully Convolutional network, Human-Robot Interaction(HRI), Image processing, Mean-shift(MS), Multi-step, Optimization techniques(OT), Proposed model
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)