Comparison Between 2D and 3D Hand Gesture Interaction for Augmented Reality Applications

2011 ◽  
Author(s):  
Rafael Radkowski ◽  
Christian Stritzke
Keyword(s):  
Augmented Reality ◽  
Gesture Recognition ◽  
Recognition System ◽  
Hand Gesture ◽  
Interaction Techniques ◽  
3D Interaction ◽  
Gesture Interaction ◽  
Depth Images ◽  
2D And 3D ◽  
Hand Gesture Interaction

This paper presents a comparison between 2D and 3D interaction techniques for Augmented Reality (AR) applications. The interaction techniques are based on hand gestures and a computer vision-based hand gesture recognition system. We have compared 2D gestures and 3D gestures for interaction in AR application. The 3D recognition system is based on a video camera, which provides an additional depth image to each 2D color image. Thus, spatial interactions become possible. Our major question during this work was: Do depth images and 3D interaction techniques improve the interaction with AR applications, respectively with virtual 3D objects? Therefore, we have tested and compared the hand gesture recognition systems. The results show two things: First, they show that the depth images facilitate a more robust hand recognition and gesture identification. Second, the results are a strong indication that 3D hand gesture interactions techniques are more intuitive than 2D hand gesture interaction techniques. In summary the results emphasis, that depth images improve the hand gesture interaction for AR applications.

scholarly journals Virtual Block Augmented Reality Game Using Freehand Gesture Interaction

2020 ◽  
Vol 10 (2) ◽  
Author(s):  
Cik Suhaimi Yusof ◽  
Ajune Wanis Ismail
Keyword(s):  
Augmented Reality ◽  
Tracking System ◽  
Recognition System ◽  
Hand Gesture ◽  
Leap Motion ◽  
Gesture Interaction ◽  
Hand Gesture Interaction ◽  
Augmented Reality Game ◽  
World Environment ◽  
Real Hand

Augmented Reality (AR) manages to bring a virtual environment into a real-world environment seamlessly. As AR has been recognised as advancing technology, AR brings future changes to the learning process. The goal of this study is to use freehand gestures to create a virtual block game in AR. First of all, the stages of this study are to explore block games and freehand movements by using Leap Motion. Secondly, the design and development of Leap Motion virtual block games, and thirdly, the implementation of free-hand gesture interaction virtual block games. The paper explains about virtual blocks AR game using freehand gesture. AR tracking system with real hand gesture recognition system is merged to execute the freehand gesture. A prototype virtual block has been described in this paper. The paper ends with the conclusion and future works.

scholarly journals Surface EMG-Based Instantaneous Hand Gesture Recognition Using Convolutional Neural Network with the Transfer Learning Method

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2540
Author(s):  
Zhipeng Yu ◽  
Jianghai Zhao ◽  
Yucheng Wang ◽  
Linglong He ◽  
Shaonan Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Gesture Recognition ◽  
Recognition System ◽  
Surface Emg ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Training Time ◽  
Generalization Ability

In recent years, surface electromyography (sEMG)-based human–computer interaction has been developed to improve the quality of life for people. Gesture recognition based on the instantaneous values of sEMG has the advantages of accurate prediction and low latency. However, the low generalization ability of the hand gesture recognition method limits its application to new subjects and new hand gestures, and brings a heavy training burden. For this reason, based on a convolutional neural network, a transfer learning (TL) strategy for instantaneous gesture recognition is proposed to improve the generalization performance of the target network. CapgMyo and NinaPro DB1 are used to evaluate the validity of our proposed strategy. Compared with the non-transfer learning (non-TL) strategy, our proposed strategy improves the average accuracy of new subject and new gesture recognition by 18.7% and 8.74%, respectively, when up to three repeated gestures are employed. The TL strategy reduces the training time by a factor of three. Experiments verify the transferability of spatial features and the validity of the proposed strategy in improving the recognition accuracy of new subjects and new gestures, and reducing the training burden. The proposed TL strategy provides an effective way of improving the generalization ability of the gesture recognition system.

Sign in / Sign up

Export Citation Format

Share Document