시각 장애인 가상현실 체험 환경을 위한 딥 러닝을 활용한 몰입형 보행 상호작용 설계
Design of Immersive Walking Interaction Using Deep Learning for Virtual Reality Experience Environment of Visually Impaired People
0
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
본 연구는 시각 장애인의 도보 적응올 위한 새로운 가상현실 체험 환경을 제안한다. 제안하는 가상현실 체험 환경의 핵심은 몰입형 보행 상호작용과 딥러닝 기반 점자 블록 인식으로 구성된다. 우선, 시각 장애인의 입장에서 현실적인 걷기 경험을 제공함을 목적으로 제자리 걸음을 감지하여 걷기를 판단하는 트래커 기반 걷기 처리과정과 시각 장애인의 보행 보조 도구를 가상현실에 적용한 컨트롤러 기반 VR 횐지광이를 설계한다. 또한, VR 횐지광이를 활용한 길 안내 과정에서 도로 위의 점자 블록 인지 및 반응 등 종합적인 의사결정을 수행하는 학습 모델을 제안한다. 이를 기반으로 가상현실 도보 체험 환경에 대한 실험을 위하여 실외 도시 환경으로 구성된 가상현실 어플리케이션을 제작하고, 참가자를 대상으로 설문 실험 및 성능 분석을 진행하였다. 결과적으로 제안한 가상현실 체험 환경이 시각 장애인의 입장에서 현존감 높은 도보 체험을 제공하고 있음을 확인하였다. 그리고 제안한 학습과 처 리과정이 인도와 차도, 인도 위의 점자 블록을 높은 정확도로 인지함을 확인하였다.
Abstract
In this study, a novel virtual reality (VR) experience environment is proposed for enabling walking adaptation of visually impaired people. The core of proposed VR environment is based on immersive walking interactions and deep learning based braille blocks recognition. To provide a realistic walking experience from the perspective of visually impaired people, a tracker-based walking process is designed for determining the walking state by detecting marching in place, and a controller-based VR white cane is developed that serves as the walking assistance tool for visually impaired people. Additionally, a learning model is developed for conducting comprehensive decision-making by recognizing and responding to braille blocks situated on roads that are followed during the course of directions provided by the VR white cane. Based on the same, a VR application comprising an outdoor urban environment is designed for analyzing the VR walking environment experience. An experimental survey and performance analysis were also conducted for the participants. Obtained results corroborate that the proposed VR walking environment provides a presence of high-level walking experience from the perspective of visually impaired people. Furthermore, the results verify that the proposed learning algorithm and process can recognize braille blocks situated on sidewalks and roadways with high accuracy.
참고문헌 (26)
- H. Joo, "Total capture: A 3d deformation model for tracking faces, hands, and bodies", Proceedings of The 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ser. CVPR ’18 (2018), IEEE Computer Society
- S. Marwecki, "Virtualspace - overloading physical space with multiple virtual reality users", Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, ser. CHI ’18, pp.241:1~241:10 (2018)
- 박성준, "몰입형 가상현실에서의 협업 기반 다수 사용자 상호작용의 현존감에 관한 연구", 한국컴퓨터그래픽스학회논문지, 24(3), pp.11~20 (2018), (사)한국컴퓨터그래픽스학회[DOI]
- M. Slater, "Enhancing our lives with immersive virtual reality", Frontiers in Robotics and AI, 3, pp.74~ (2016)
- C. Pacchierotti, "Two finger grasping simulation with cutaneous and kinesthetic force feedback", Haptics: Perception, Devices, Mobility, and Communication (EuroHaptics 2012), pp.373~382 (2012)
- E. Remelli, "Lowdimensionality calibration through local anisotropic scaling for robust hand model personalization", 2017 IEEE International Conference on Computer Vision (ICCV), pp.2554~2562 (2017)
- Z.-C. Dong, "Smooth assembled mappings for large-scale real walking", ACM Trans. Graph., 36(6), pp.211:1~211:13 (2017)
- J. Lee, "Mave : Maze-based immersive virtual environment for new presence and experience", Computer Animation and Virtual Worlds, 28(3-4), pp.e1756~ (2017)
- Huiyue Wu, "User-defined gesture interaction for immersive VR shopping applications", Behaviour & Information Technology, 38(7), pp.726~741 (2018), Informa UK Limited[DOI]
- 유경호, "가상 홈 트레이닝 – 가상현실 기반 소근육 재활 시스템", 한국컴퓨터그래픽스학회논문지, 24(3), pp.93~100 (2018), (사)한국컴퓨터그래픽스학회[DOI]
- 김한섭, "가상현실 기반 범죄 프로파일링 시뮬레이션 교육 및 평가 시스템", 한국컴퓨터그래픽스학회논문지, 24(3), pp.83~92 (2018), (사)한국컴퓨터그래픽스학회[DOI]
- M. Kim, "A study on immersion and presence of a portable hand haptic system for immersive virtual reality", Sensors, 17(5), pp.1141~ (2017)
- M. Kim, "A study on interaction of gaze pointer-based user interface in mobile virtual reality environment", Symmetry, 9(9), pp.189~ (2017)
- S. Han, "A study on immersion of hand interaction for mobile platform virtual reality contents", Symmetry, 9(2), pp.22~ (2017)
- W. Zhao, "Combining markerbased mocap and rgb-d camera for acquiring high-fidelity hand motion data", Proceedings of the ACM SIGGRAPH, 2012, 33~42
- C. Carvalheiro, "User redirection and direct haptics in virtual environments", Proceedings of the 2016 ACM on Multimedia Conference, ser. MM ’16, pp.1146~1155 (2016)
- A. Jayasiri, "Desktop versions of the string-based haptic interface—spidar", 2015 IEEE Virtual Reality (VR). IEEE, pp.199~200 (2015)
- D. Leonardis, "A 3-rsr haptic wearable device for rendering fingertip contact forces", IEEE Transactions on Haptics, 10(3), pp.305~316 (2017)
- D. Prattichizzo, "Towards wearability in fingertip haptics : A 3-dof wearable device for cutaneous force feedback", IEEE Transactions on Haptics, 6(4), pp.506~516 (2013)
- M. Slater, "Simulating peripheral vision in immersive virtual environments", Computers & Graphics, 17(6), pp.643~653 (1993)
- M. Slater, "Taking steps : The influence of a walking technique on presence in virtual reality", ACM Trans. Comput. -Hum. Interact, 2(3), pp.201~219 (1995)
- V. Vinayagamoorthy, "An eye gaze model for dyadic interaction in an immersive virtual environment : Practice and experience", Computer Graphics Forum, 23(1), pp.1~11 (2004)
- 정기성, "몰입형 전래동화 콘텐츠 제작을 위한 가상현실 기술에 대한 연구", 한국컴퓨터그래픽스학회논문지, 22(3), pp.43~52 (2016), (사)한국컴퓨터그래픽스학회[DOI]
- J. Lee, "A study on immersion and vr sickness in walking interaction for immersive virtual reality applications", Symmetry, 9(5), pp.78~ (2017)
- "Rethinking the inception architecture for computer vision" (2015)[URL]
- B. G. Witmer, "The factor structure of the presence questionnaire", Presence: Teleoper. Virtual Environ, 14(3), pp.298~312 (2005)