사람의 포즈와 골격 데이터 학습을 이용한 정확한 거북목 자세 감지
An Accurate Forward Head Posture Detection using Human Pose and Skeletal Data Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 논문에서는 사용자의 골격 자세를 분석하여 네트워크 학습 기반으로 거북목 자세를 정확하고 효율적으로 판별하는 시스템을 제안한다. 거북목 증후군이란 목이 구부정하게 앞으로 나오는자세를 오래 유지함으로써 목의 자세가 바뀌고 뒷목, 어깨, 허리 등에 통증이 생기는 증상을 말하며, 수술이나 약물치료보다 평소의 자세 습관이 효과적이라고 알려져 있다. 기존의 방법들은 웹캠을 이용한 합성곱 신경망을 이용하였고, 이러한 접근법은 영상의 명도와 조명, 피부 색 등에 영향을 받기 때문에 특정 인물에 대해서만 수행되는 문제가 있다. 본 논문에서는 이 문제를 완화하고자 영상으로부터 골격을 추출하고, 정면보다는 측면에 해당하는 데이터를 학습하여 이전 기법보다 효율적이고 정확하게 거북목 자세를 찾아낸다. 결과적으로 이전 기법에 비해 다양한 실험 장면에서 정확도가 되었음을 보여준다.
Abstract
In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.
참고문헌 (20)
- M. S. Kwon, "The survey on internet overdependence", Ministry of Science, ICT, and Future Planning, National Information Society Agency, ~ (2016)
- Jung-Ho Kang, "The Effect of The Forward Head Posture on Postural Balance in Long Time Computer Based Worker", Annals of Rehabilitation Medicine, 36(1), pp.98~104 (2012), 대한재활의학회
- Kim, Se-Yoon, "Effects of cervical sustained natural apophyseal glide on forward head posture and respiratory function", Journal of physical therapy science, 27(6), pp.1851~1854 (2015)
- Yoo, I. S, "Modern disease, prevention and exercise for turtle neck syndrome", Journal of Korean Society of Steel Construction, 22(4), pp.80~ (2010)
- Julie Swann, "Good positioning: the importance of posture", Nursing and Residential Care, 11(9), pp.467~469 (2009), Mark Allen Group[DOI]
- Son, Dong-Hyeop, "Implementation of Turtle Neck Syndrome Diagnosis using CNN", Proceedings of the Korean Society of Computer Information Conference, pp.7~10 (2021)
- 한지예, "CNN기반의 학습모델을 활용한 거북목 증후군 자세 교정 시스템", 한국콘텐츠학회 논문지, 20(7), pp.47~55 (2020), 한국콘텐츠학회[DOI]
- 정현우, "전방머리자세(Forward Head Posture)의 정도와 척추 만곡 변형의 상관관계", 한방재활의학과학회지, 23(4), pp.195~202 (2013), 한방재활의학과학회
- 이한숙, "The Analysis of severity of forward head posture with observation and photographic method", 대한물리의학회지, 10(3), pp.227~235 (2015), 대한물리의학회
- S. Y. Chee, "Neck tilt angle sensing device and method", U.S. Patent Application, No. 17, ~ (2017)
- K. H. Kim, "Design and implementation of pervasive systems for preventing forward head posture syndrome", M.S, pp.2013
- Woo Jun Kim, "Forward Head Posture Detection and Warning System using Image Equipment", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.571~572 (2016)
- Kim, T., "Detecting and preventing forward head posture with wireless inertial body sensor networks", International Conference on Body Sensor Networks, pp.125~126 (2011)
- 하호진, "압력센서와 영상처리 보간기법을 이용한 앉은 자세의 교정 알고리즘 설계", 한국정보기술학회논문지, 14(1), pp.37~44 (2016), 한국정보기술학회[DOI]
- Kim, Y. S., "Preliminary Study of Real-time Turtle Neck Syndrome Monitoring System using EMG analysis", Transactions of the Korean Institute of Electrical Engineers, 7, pp.1663~1664 (2013)
- Qi Wang, "Zishi: A Smart Garment for Posture Monitoring", Proceedings of the CHI Conference Extended Abstracts on Human Factors in Computing Systems, Association for Computing Machinery, pp.3792~3795 (2016)
- Rushil Khurana, "NeckGraffe: a postural awareness system", CHI Extended Abstracts on Human Factors in Computing Systems, Association for Computing Machinery, pp.227~232 (2014)
- Cao, Zhe, "OpenPose: Realtime multi-person 2d pose estimation using part affinity fields", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.7291~7299 (2017)
- Simon, Tomas, "Hand keypoint detection in single images using multiview bootstrapping", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.1145~1153 (2017)