Design and Implementation of a Flexible Hand Gesture Command Interface for Games Based on Computer Vision

Bernardes, João Luiz; Nakamura, Ricardo; Tori, Romero

doi:10.1109/sbgames.2009.16

Cited by 10 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the computer vision method, visual features can be obtained through various visual equipment, and conduct activity recognition [3], [7], [10]- [14], [19]. It can recognize human activity by capturing relevant features of human activity from images.…”

Section: B Computer Vision-basedmentioning

confidence: 99%

Temporal-Frequency Attention-Based Human Activity Recognition Using Commercial WiFi Devices

et al. 2020

View full text Add to dashboard Cite

Human activity recognition has been growing for decades in a variety of technological disciplines. However, in the existing WiFi-based human activity recognition systems, there are the following problems: Firstly, in the processing of channel state information (CSI) data, mainly for the removal of noise in the superimposed signal, there is no effective removal of useless multipath signals; Secondly, the data segmentation algorithm based on the empirical threshold requires manual adjustment of the threshold in different environments, resulting in poor robustness and unstable segmentation; Thirdly, simple learning classification is applied without specific design for CSI data structure and sufficiently abstracting information features. In this paper, a device-free human activity recognition system with a temporalfrequency attention mechanism is proposed, which can be deployed on commercial WiFi devices to identify human's daily activities. Firstly, the multipath signal affected by the channel change is extracted by using the difference of the propagation delay of different multipath, thereby eliminating the delay and invalid multipath signals that have undergone multiple reflections and refractions. Secondly, a neural network model based on attention mechanism is proposed, which assigns different weights to different characteristics and sequences by imitating the human brain to dedicate more attention to important information. Then, the long short-term memory (LSTM) model is used to learn the correlation features of different dimensions to realize human activity recognition. Finally, the system performance is evaluated in different environments, and the experimental results show that our syetem holds a better performance in both line-of-sight (LOS) and non-line-of-sight (NLOS) than the existing human activity recognition systems.

show abstract

Section: B Computer Vision-basedmentioning

confidence: 99%

Temporal-Frequency Attention-Based Human Activity Recognition Using Commercial WiFi Devices

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The use of gestures to control computerized devices has long been a topic of research [12], even for fields such as mobile devices [13]. A generic goal is to leverage users' preexisting experience of bodily interaction in space and its associated rich semantics, to shrink the conceptual gap between users' actions and system response, and thus enable users to work with more complex mental models [14].…”

Section: B Low-cost Gesture Acquisitionmentioning

confidence: 99%

Separating Gesture Detection and Application Control Concerns with a Multimodal Architecture

Morgado

Cardoso

Carvalho

et al. 2015

2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable,

View full text Add to dashboard Cite

Gesture-controlled applications typically are tied to specific gestures, and also tied to specific recognition methods and specific gesture-detection devices. We propose a concernseparation architecture, which mediates the following concerns: gesture acquisition; gesture recognition; and gestural control. It enables application developers to respond to gesture-independent commands, recognized using plug-in gesture-recognition modules that process gesture data via both device-dependent and deviceindependent data formats and callbacks. Its feasibility is demonstrated with a sample implementation.

show abstract

“…Mariappan et al used infrared markers worn by subjects to capture human movements, achieving good quality of computer mapping results but requiring markers [7]. Bernardes et al [1] used a color based system without markers on the user to establish gesture-based controls, but the mapping result is not always accurate due to unstable illuminations or the problems of image capture. Ren et al [10] utilized a Kinect device to recognize gestures in real-time.…”

Section: Background and Related Workmentioning

confidence: 99%

Empirically measuring control quality of gesture input

Chastine

Franklin

Peng

et al. 2014

2014 Computer Games: AI, Animation, Mobile, Multimedia, Educational and Serious Games (CGAMES)

View full text Add to dashboard Cite

As new input devices emerge new paradigms of interaction must emerge with them. Recent advances in technology have lowered the cost of gesture-based hardware, enabling them to be adopted by and integrated into mainstream applications. Given the novelty of these devices, however, little is known about how this form of interaction can be integrated into existing computing paradigms or how it compares with existing input methods. It is therefore important to examine the role of gesture control across current applications in various contexts. While gesture-based input is likely to yield a variety of novel interaction techniques for immersive 3D environments, it is important to understand how spatial controls map to 2D interfaces and how lessons learned in the 2D space map into these 3D environments.In this paper, we present the results of a study of using gesture alone to control a top-down shooter game using two novel techniques; interaction via a gamepad was used to establish a baseline of performance. We measured users' performance of basic tasks (moving and aiming), and then utilized a subjective post-study survey. The motivation of this study is not to directly compare the performance of the gamepad with gesture controls (given a time-on-task bias in favor of gamepad control), but rather to establish a baseline of expected user performance for those with no prior gesture-based experience. The contributions of this research include the design and evaluation of two new gesture-based techniques for 2D control and the presentation and analysis of our results.

show abstract

Design and Implementation of a Flexible Hand Gesture Command Interface for Games Based on Computer Vision

Cited by 10 publications

References 26 publications

Temporal-Frequency Attention-Based Human Activity Recognition Using Commercial WiFi Devices

Temporal-Frequency Attention-Based Human Activity Recognition Using Commercial WiFi Devices

Separating Gesture Detection and Application Control Concerns with a Multimodal Architecture

Empirically measuring control quality of gesture input

Contact Info

Product

Resources

About