GlassGesture: Exploring head gesture interface of smart glasses

Yi, Shanhe; Qin, Zhengrui; Novak, Ed; Yin, Yafeng; Li, Qun

doi:10.1109/infocom.2016.7524542

Cited by 48 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Head mounted devices can use the tracked head position in many ways, such as authenticating users based on their head gestures [42] or as a method to select moving targets by following their trajectories [9]. Yukang et al [41] conducted an elicitation study in which they explored what kind of head gestures could be used to create hands-free input while using an HMD device.…”

Section: Head Trackingmentioning

confidence: 99%

Headbang: Using Head Gestures to Trigger Discrete Actions on Mobile Devices

Hueber

Cherek

Wacker

et al. 2020

22nd International Conference on Human-Computer Interaction With Mobile Devices and Services

View full text Add to dashboard Cite

show abstract

Section: Head Trackingmentioning

confidence: 99%

Headbang: Using Head Gestures to Trigger Discrete Actions on Mobile Devices

Hueber

Cherek

Wacker

et al. 2020

22nd International Conference on Human-Computer Interaction With Mobile Devices and Services

View full text Add to dashboard Cite

show abstract

“…In [6] the authors have applied Dynamic Time Warping (DTW) algorithm in order to calculate the similarity between time sequences acquired with IMU sensors in order to classify four classes of actions. Application of weighted DTW classifier for head motions acquired by Smart Glasses is reported in [7]. However, due to a lack of detailed description of methodology and data it is hardly possible to reproduce the method and results.…”

Section: Head Motion Analysis and Classificationmentioning

confidence: 99%

“…The "idealized" shape of motions are visualized in Figure 1. We have chosen those templates basing on reports from other papers, where authors have found them to be natural, especially for commands in design gestures-based controlling interface [6,7,50]. We have chosen this set of gestures for several reasons.…”

Section: Evaluation Datasetmentioning

confidence: 99%

“…The DTW distance is calculated as normalized DTW distance. Our DTW classifier operates on spatial representation of head motion which is calculated using Equation (7). We can express head position in three-dimensional space as a unit vector [0, 0, 1] transformed by a quaternion that represents head rotation.…”

Section: Algorithm 2: Markley's Quaternion Averagingmentioning

confidence: 99%

“…However, linear projection might be redundant while the classification process is done with a classifier capable of partitioning the features space with appropriate decision hyperplanes. Also, in our case it is not necessary to apply convolution layers to calculate input features from time series, because the coordinates of vectors that represent head motion trajectory (7) are enough to train a fully connected network or a decision tree. In our case the only requirement for the training dataset is to perform resampling to the uniform size and "flattening", as described in Section 2.4.1.…”

Section: Neural Network and Random Forestmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Pattern Recognition Methods for Head Gesture-Based Interface of a Virtual Reality Helmet Equipped with a Single IMU Sensor

Hachaj

Piekarczyk

2019

Sensors

View full text Add to dashboard Cite

The motivation of this paper is to examine the effectiveness of state-of-the-art and newly proposed motion capture pattern recognition methods in the task of head gesture classifications. The head gestures are designed for a user interface that utilizes a virtual reality helmet equipped with an internal measurement unit (IMU) sensor that has 6-axis accelerometer and gyroscope. We will validate a classifier that uses Principal Components Analysis (PCA)-based features with various numbers of dimensions, a two-stage PCA-based method, a feedforward artificial neural network, and random forest. Moreover, we will also propose a Dynamic Time Warping (DTW) classifier trained with extension of DTW Barycenter Averaging (DBA) algorithm that utilizes quaternion averaging and a bagged variation of previous method (DTWb) that utilizes many DTW classifiers that perform voting. The evaluation has been performed on 975 head gesture recordings in seven classes acquired from 12 persons. The highest value of recognition rate in a leave-one-out test has been obtained for DTWb and it equals 0.975 (0.026 better than the best of state-of-the-art methods to which we have compared our approach). Among the most important applications of the proposed method is improving life quality for people who are disabled below the neck by supporting, for example, an assistive autonomous power chair with a head gesture interface or remote controlled interfaces in robotics.

show abstract

TEXTile: Eyes-Free Text Input on Smart Glasses Using Touch Enabled Textile on the Forearm

Belkacem

Pecci

Martin

et al. 2019

Human-Computer Interaction – INTERACT 2019

View full text Add to dashboard Cite

Smart glasses are autonomous and efficient computers that can perform complex tasks through mobile applications. This paper focuses on text input for mobile context. We present a new connected fabric to smart glasses as a device for text entry. This device, integrated into clothing, provides a new interaction technique called TEXTile. It allows typing without requiring users to hold a device. Users can put fingers anywhere on the fabric surface and release them, without needing to look at the fabric or using markers on the fabric. The text entry technique is based on eight combinations of fingers in contact or released, identified as pleasant among 15 in a survey involving 74 participants. A first user's study with 20 participants establishes that the eight combinations for TEXTile were significantly reliable (98.95% recognition rate). A second study with nine participants evaluates the learning curve of TEXTile. Users achieved a mean typing of 8.11 WPM at the end of ten 12-minute sessions, which can be slow, but sufficient with short text compared to other advantages of the technique. Results show low error rates for tasks completed and good usability (76% in SUS questionnaire). The NASA-TLX questionnaire establishes there is no important mental or physical workload to accomplish the task.

show abstract

GlassGesture: Exploring head gesture interface of smart glasses

Cited by 48 publications

References 16 publications

Headbang: Using Head Gestures to Trigger Discrete Actions on Mobile Devices

Headbang: Using Head Gestures to Trigger Discrete Actions on Mobile Devices

Evaluation of Pattern Recognition Methods for Head Gesture-Based Interface of a Virtual Reality Helmet Equipped with a Single IMU Sensor

TEXTile: Eyes-Free Text Input on Smart Glasses Using Touch Enabled Textile on the Forearm

Contact Info

Product

Resources

About