Exploratorium_8.1.1
Previous Item Next Item
Input
- using Gestures in 3-space

Annotated Bibliography

Category
  • Visions of the Future
    • PAST Visions of the Future
  • Input
    • using Text
    • using Pointing Devices
    • using eyes
    • using Voice or Sign
    • using Machine Vision
    • using 1D Continuous Controls
    • using 2D to 6D Continuous Controls
    • using Gestures on a Surface (2D)
    • using Gestures in 3-space
    • Unique Combinations of Input Devices
    • Enhancing/Accelerating Input
  • Sensing (by device)
    • Biological
    • Mechanisms for Sensing
    • Environmental
    • Virtual sensors
    • Other
  • Output
    • to Visual sense
    • to Tactile or Pain sense
    • as Language (speech, text, sign-lang)
    • to Auditory sense
    • to Directly Activate/Control user
  • Altering/Enhancing Sensory Input
    • what is Seen
    • Translating Between Senses
  • Direct Brain Interfaces
    • Unique Combinations of DBI types
    • Mechanisms for Direct Brain Interfaces
    • DB Output, to Control or Project
    • DB Input - into Brain
    • Direct Brain Monitoring
  • Virtual & Augmented Reality (xR)
    • Mechanisms for AR/VR/xR
    • Uses of AR/VR/xR
  • Uses of AI
    • to Enhance Input
    • as Assistant (voice, text, etc.)
    • to Enhance/Adapt Output
    • to Enhance Sensing
    • Other uses of AI in interfaces
  • Accessibility + Digital Divide
    • Accessibility & HCI
    • Digital Divide - Digital Affinity
    • Digital Divide - Disability
  • Other
Search

COPY currently shown bibliography

Tan, P., Han, X., Zou, Y., Qu, X., Xue, J., Li, T., Wang, Y., Luo, R., Cui, X., Xi, Y., Wu, L., Xue, B., Luo, D., Fan, Y., Chen, X., Li, Z., Wang, Z. L., Self-Powered Gesture Recognition Wristband Enabled by Machine Learning for Full Keyboard and Multicommand Input. Adv. Mater.2022, 34, 2200793. https://doi.org/10.1002/adma.202200793

  • This study created a gesture recognition wristband to serve as a lightweight alternative to existing VR control systems that are more physically cumbersome. They achieved 92.6% accuracy and found the technology to have great potential.

Z. Lu, S. Cai, B. Chen, Z. Liu, L. Guo and L. Yao, "Wearable Real-Time Gesture Recognition Scheme Based on A-Mode Ultrasound," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 2623-2629, 2022, doi: 10.1109/TNSRE.2022.3205026. Accessed at: https://ieeexplore.ieee.org/abstract/document/9881558

  • This study tested a portable gesture recognition system using ultrasound with AI that can be used offline, finding it has a 96.92% accuracy rate, showing the technology has great potential for use in gesture-based interfaces in many contexts.

Fernández-Vázquez, D., Cano-de-la-Cuerda, R., & Navarro-López, V. (2022). Haptic Glove Systems in Combination with Semi-Immersive Virtual Reality for Upper Extremity Motor Rehabilitation after Stroke: A Systematic Review and Meta-Analysis. International Journal of Environmental Research and Public Health, 19(16), 10378.

  • "The effectiveness of the virtual reality (VR) for the upper extremity (UE) motor rehabilitation after stroke has been widely studied. However, the effectiveness of the combination between rehabilitation gloves and semi-immersive VR (SVR) compared to conventional treatment has not yet been studied...The combined use of rehabilitation haptic gloves and SVR with conventional rehabilitation produces significant improvements with respect to conventional rehabilitation treatment alone in terms of functionality of the UE in stroke patients." (Fernández-Vázquez, D. et al. 2022)

Xing, T., Yang, Q., Jiang, Z., Fu, X., Wang, J., Wu, C. Q., & Chen, X. (2022). WiFine: Real-time Gesture Recognition Using Wi-Fi with Edge Intelligence. ACM Transactions on Sensor Networks (TOSN) [cited 2022 Sep 29] Available from: https://dl.acm.org/doi/pdf/10.1145/3532094

  • "In this paper, we propose a lightweight Wi-Fi gesture recognition system, referred to as WiFine, which is designed and implemented for deployment on low-end edge devices without the use of any additional high-performance services in the process. Extensive experimental results show that the proposed system achieves fast recognition of various actions with an accuracy up to 96.03% in 0.19 seconds."

Previous Item Next Item