AR 전신 상호작용을 위한 이종 센서 간 좌표계 보정 기법
Heterogeneous Sensor Coordinate System Calibration Technique for AR Whole Body Interaction
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
꾸준히 증가하는 노인성 질환 환자 대상으로 몰입형 디지털 콘텐츠를 이용한 쉽고 정확한 전신 재활 상호작용 기술이 필요하며, 본 연구에서는이를 위해 홀로렌즈와 키넥트를 사용한 전신 상호작용 기술을 소개한다. 이를 위해 메쉬 특징점 기반 변환, AR 마커 기반 변환, 신체 인식 기반변환 방법의 3가지 좌표 변환 방식을 제안한다. 메쉬 특징점 기반 변환은 공간 메쉬에 3개의 특징점을 지정하고 변환 행렬을 이용하여 좌표계를일치시킨다. 이 방법은 수작업이 필요하여 사용성이 떨어지지만 정확도가 8.5mm로 상대적으로 높다. AR 마커 기반 방식은 홀로렌즈s와 키넥트가동시에 인식하는 AR, QR마커를 사용하여 평균오차 11.2mm로 준수한 정확도를 달성했다. 신체 인식 기반 변환 방법은 두 기기가 동시에 인식하는머리 혹은 HMD위치와 양 손 혹은 컨트롤러 위치를 이용하여 좌표계를 일치시킨다. 이 방법은 정확도가 떨어지지만 부가적인 도구나 수작업이필요 없으므로 사용성이 좋다. 또한 후처리 기술로 RANSAC을 적용함으로써 오차를 10% 이상 줄였다. 이러한 3가지 방식은 콘텐츠가 필요한 사용편의성과 정확도에 따라서 선택적으로 적용할 수 있다. 본 연구에서는 이 기술을 이용해서 ‘썬더펀치’와 재활 치료 콘텐츠에 적용하여 검증하였다.
Abstract
A simple and accurate whole body rehabilitation interaction technology using immersive digital content is needed for elderly patientswith steadily increasing age-related diseases. In this study, we introduce whole-body interaction technology using HoloLens and Kinectfor this purpose. To achieve this, we propose three coordinate transformation methods: mesh feature point-based transformation, ARmarker-based transformation, and body recognition-based transformation. The mesh feature point-based transformation aligns thecoordinate system by designating three feature points on the spatial mesh and using a transform matrix. This method requires manualwork and has lower usability, but has relatively high accuracy of 8.5mm. The AR marker-based method uses AR and QR markers recognizedby HoloLens and Kinect simultaneously to achieve a compliant accuracy of 11.2mm. The body recognition-based transformation alignsthe coordinate system by using the position of the head or HMD recognized by both devices and the position of both hands or controllers. This method has lower accuracy, but does not require additional tools or manual work, making it more user-friendly. Additionally, wereduced the error by more than 10% using RANSAC as a post-processing technique. These three methods can be selectively applieddepending on the usability and accuracy required for the content. In this study, we validated this technology by applying it to the “ThunderPunch” and rehabilitation therapy content.
참고문헌 (21)
- International Comparison of Low Fertility and Aging Trends and Implications, "KERI", ~ (2021)
- S. H. Shin, "Use of rehabilitation medical services for stroke patients", HIRA, pp.72~81 (2019)
- S. H. Kollins, "A novel digital intervention for actively reducing severity of paediatric ADHD(STARS-ADHD) : A randomised controlled trial", The Lancet Digital Health, 2(4), pp.168~178 (2020)
- S. C. Cramer, "Efficacy of home-based telerehabilitation vs in-clinic therapy for adults after stroke : A randomized clinical trial", JAMA neurology, 76(9), pp.1079~1087 (2019)
- M. Maier, "Principles of neurorehabilitation after stroke based on motor learning and brain plasticity mechanisms", Frontiers in Systems Neuroscience (2019)
- D. Y. Kim, "Clinical practice guideline for stroke rehabilitation in Korea 2016", Brain & Neurorehabilatation, 13, pp.74~ (2016)
- B. Liu, "A rapid coordinate transformation method applied in industrial robot calibration based on characteristic line coincidence", Sensors, 16(2), pp.239~ (2016)
- M. De Cecco, "Sharing augmented reality between a patient and a clinician for assessment and rehabilitation in daily living activities", Information, 14(4), pp.204~ (2023)
- M. Garon, "Real-time high resolution 3D data on the HoloLens", 2016 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct), pp.189~191 (2016)
- J. Smisek, "Consumer Depth Cameras for Computer Vision: Research Topics and Applications", pp.3~25 (2013)
- S. H. Choi, "An integrated mixed reality system for safety-aware human-robot collaboration using deep learning and digital twin generation", Robotics and ComputerIntegrated Manufacturing, 73 (2022)
- C. -H. Hsieh, "A Kinect-based medical augmented reality system for craniofacial applications using image-to-patient registration", Neuropsychiatry, 7(6), pp.927~939 (2017)
- M. -L. Wu, "An augmented reality system using improved-iterative closest point algorithm for on-patient medical image visualization", Sensors, 18(8), pp.2505~ (2018)
- K. Hattori, "Inside-out tracking controller for VR", AR HMD using image recognition with smartphones, 2020, ~
- C. T. Russell, "Geophysical coordinate transformations", Cosmic Electrodynamics, 2(2), pp.184~196 (1971)
- S. Garrido-Jurado, "Automatic generation and detection of highly reliable fiducial markers under occlusion", Pattern Recognition, 47(6), pp.2280~2292 (2014)
- H. Kato, "Marker tracking and hmd calibration for a video-based augmented reality conferencing system", Proceedings 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR'99), 85(94), pp.85~94 (1999), IEEE
- "QR Code features"[URL]
- M. A. Fischler, "Random sample consensus : A paradigm for model fitting with applications to image analysis and automated cartography", Communications of the ACM, 24(6), pp.381~395 (1981)
- S. Park, "Development of Projection based Virtual Experience System using Punching", Korea HCI Conference, pp.847~849 (2017)
- D. H. Kim, "ThunderPunch : A bare-hand, gesturebased, large interactive display interface with upperbody-part detection in a top view", IEEE Computer Graphics and Applications, 38(5), pp.100~111 (2018)