EIT-based Gesture Recognition Training with Augmented Reality

被引：0

作者：

Giesser, Christian ^{[1
]}

Gibas, Christian ^{[1
]}

Gruenewald, Armin ^{[1
]}

Eiler, Tanja Joan ^{[1
]}

Schmuecker, Vanessa ^{[1
]}

Brueck, Rainer ^{[1
]}

机构：

[1] Univ Siegen, Med Informat & Microsys Engn, D-57076 Siegen, Germany

来源：

2021 4TH IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND VIRTUAL REALITY (AIVR 2021) | 2021年

关键词：

Artificial Intelligence; Augmented Reality; Electrical Impedance Tomography; Magic Leap; Prosthesis Control;

D O I：

10.1109/AIVR52153.2021.00044

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Electrical impedance tomography (EIT) combined with artificial intelligence (AI) methods is suitable for recognizing gestures that can be used to control prostheses for disabled people. In this work, augmented reality (AR) is used to visualize gestures so that a neural network can be trained using EIT data. The aim is to create an AI that is as general and person-independent as possible. Person-specific differences should be automatically recognized and negated by a calibration process. The use of augmented reality helps to improve the AI-based training process on the basis of EIT data. Users work in an environment that is natural to them and are not distracted or confused by menus or complicated programs.

引用

页码：198 / 200

页数：3