Gesture-recognition with Non-referenced Tracking

Keir, Paul; Payne, John T.; Elgoyhen, Jocelyn; Horner, Martyn; Naef, Martin; Anderson, Paul

doi:10.1109/vr.2006.64

Cited by 21 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study builds on the field of sensor-based HAR. In this field, activity recognition was generally achieved by performing signal processing of the acceleration data [18,19]. Chen et al [20] used surface electromyography (sEMG) and 2D accelerometers to achieve hand motion recognition.…”

Section: Related Workmentioning

confidence: 99%

Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition

2021

View full text Add to dashboard Cite

The neural-network-based human activity recognition (HAR) technique is being increasingly used for activity recognition in virtual reality (VR) users. The major issue of a such technique is the collection large-scale training datasets which are key for deriving a robust recognition model. However, collecting large-scale data is a costly and time-consuming process. Furthermore, increasing the number of activities to be classified will require a much larger number of training datasets. Since training the model with a sparse dataset can only provide limited features to recognition models, it can cause problems such as overfitting and suboptimal results. In this paper, we present a data augmentation technique named gravity control-based augmentation (GCDA) to alleviate the sparse data problem by generating new training data based on the existing data. The benefits of the symmetrical structure of the data are that it increased the number of data while preserving the properties of the data. The core concept of GCDA is two-fold: (1) decomposing the acceleration data obtained from the inertial measurement unit (IMU) into zero-gravity acceleration and gravitational acceleration, and augmenting them separately, and (2) exploiting gravity as a directional feature and controlling it to augment training datasets. Through the comparative evaluations, we validated that the application of GCDA to training datasets showed a larger improvement in classification accuracy (96.39%) compared to the typical data augmentation methods (92.29%) applied and those that did not apply the augmentation method (85.21%).

show abstract

Section: Related Workmentioning

confidence: 99%

Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition

2021

View full text Add to dashboard Cite

show abstract

“…The XWand [4] [5]. 3motion [6] was developed as a 3D hand gesture input device with general-purpose software development kit. Soapbox [7] was introduced as a light, matchboxsized device for a 3D gesture input.…”

Section: Related Workmentioning

confidence: 99%

“…a numerical score) can for instance be used to improve user performance or to correct wrong gestures as presented in our previous work [1]. Similar to the practical motion training process [6], the evaluation consists of both posture evaluation and gesture evaluation.…”

Section: Gesture Evaluationmentioning

confidence: 99%

A Framework for 3D Hand Gesture Design and Modeling

Kwon¹

2013

Journal of the Korea Academia-Industrial cooperation Society

View full text Add to dashboard Cite

We present a framework for 3D hand gesture design and modeling. We adapted two different pattern matching techniques, Dynamic Time Warping (DTW) and Hidden Markov Models (HMMs), to support the registration and evaluation of 3D hand gestures as well as their recognition. One key ingredient of our framework is a concept for the convenient gesture design and registration using HMMs. DTW is used to recognize hand gestures with a limited training data, and evaluate how the performed gesture is similar to its template gesture. We facilitate the use of visual sensors and body sensors for capturing both locative and inertial gesture information. In our experimental evaluation, we designed 18 example hand gestures and analyzed the performance of recognition methods and gesture features under various conditions. We discuss the variability between users in gesture performance.

show abstract