Gesture imitation and recognition using Kinect sensor and extreme learning machines

Yavşan, Emrehan; Uçar, Ayşegül

doi:10.1016/j.measurement.2016.09.026

Cited by 31 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the hardware, Microsoft also released a software platform to develop customized software for the Kinect devices. Kinect devices are widely used in other fields such as machine learning (Yavsan and Ucar, 2016) and medical studies (Prochazka and others, 2016). Mankoff and Russo (2012) discussed possible applications of the Kinect sensor in Earth sciences.…”

Section: Methods and Instrumentationmentioning

confidence: 99%

Spatiotemporal dynamics of snow erosion, deposition and horizontal mass flux

2019

View full text Add to dashboard Cite

The quantification of snow transport, both in wind tunnels and the field, apply particle counting methods limited to punctual sampling of relatively small volumes. Particle counting can only capture horizontal mass fluxes, failing to measure snow erosion or deposition. Herein, we present a novel low-cost sensor tool, based on a Microsoft Kinect, adapted to capture snow surface changes during snow drifting at unprecedented spatial and temporal resolutions. In the wind tunnel setting of these experiments we observe a balance between erosion and deposition at low wind speeds, while erosion is dominant at higher wind speeds. Significant differences in power spectral densities of surface mass flux and horizontal particle mass flux are observed. We show that for the saltation-length-scale parameter λ = 1, the integrated particle flux can be used to estimate the total surface mass flux in the wind tunnel. This provides an important basis to interpret mass flux measurements in the field.

show abstract

Section: Methods and Instrumentationmentioning

confidence: 99%

Spatiotemporal dynamics of snow erosion, deposition and horizontal mass flux

2019

View full text Add to dashboard Cite

show abstract

“…This is a major disadvantage because it can not be used in simple applications. Yavşan used a Kinect camera in his study, detected human upper body movements in real-time, and transferring them to a humanoid robot, simulating the human being by the robot [4]. A similar study was performed without using Kinect Study;…”

Section: Image Processing Based Gesture Control Studiesmentioning

confidence: 99%

Realization of Gesture Control Application on Openmv Board Using Optical Flow in Real-Time Video Images

Turan¹

2021

Hittite J. Sci. Eng.

View full text Add to dashboard Cite

T oday, developments in the field of human-computer interaction (HCI) exponentially grows. HCI is most fundamentally carried out with keyboard and mouse. Humanity has been making efforts to develop the channel of interaction in this field. Today touch screens (especially indispensable on mobile devices), wearable devices, etc. are actively used in HCI. The technologies developed in this area and the studies that are still in progress can vary widely according to the purpose and place of use. For example, using webcam images to control of the cursor on the computer screen with the eye movements [1]. Control of smart TV, etc. systems [2, 3], control of humanoid robots [4], control with palm movement of the in-car multimedia device [5] can be realized by detecting and tracking of body movements with Kinect camera images. Studies in the field of HCI began in the 1980s [6].

show abstract

“…Yavşan et al [33] proposed an interface for gesture recognition and an NAO robot control using Kinect. In the proposed method, the learning and recognition experiments were conducted using K-nearest neighbor (K-NN) and feed-forward neural networks (FNNs).…”

Section: Related Workmentioning

confidence: 99%

Advanced Machine Learning for Gesture Learning and Recognition Based on Intelligent Big Data of Heterogeneous Sensors

et al. 2019

View full text Add to dashboard Cite

With intelligent big data, a variety of gesture-based recognition systems have been developed to enable intuitive interaction by utilizing machine learning algorithms. Realizing a high gesture recognition accuracy is crucial, and current systems learn extensive gestures in advance to augment their recognition accuracies. However, the process of accurately recognizing gestures relies on identifying and editing numerous gestures collected from the actual end users of the system. This final end-user learning component remains troublesome for most existing gesture recognition systems. This paper proposes a method that facilitates end-user gesture learning and recognition by improving the editing process applied on intelligent big data, which is collected through end-user gestures. The proposed method realizes the recognition of more complex and precise gestures by merging gestures collected from multiple sensors and processing them as a single gesture. To evaluate the proposed method, it was used in a shadow puppet performance that could interact with on-screen animations. An average gesture recognition rate of 90% was achieved in the experimental evaluation, demonstrating the efficacy and intuitiveness of the proposed method for editing visualized learning gestures.

show abstract

Gesture imitation and recognition using Kinect sensor and extreme learning machines

Cited by 31 publications

References 37 publications

Spatiotemporal dynamics of snow erosion, deposition and horizontal mass flux

Spatiotemporal dynamics of snow erosion, deposition and horizontal mass flux

Realization of Gesture Control Application on Openmv Board Using Optical Flow in Real-Time Video Images

Advanced Machine Learning for Gesture Learning and Recognition Based on Intelligent Big Data of Heterogeneous Sensors

Contact Info

Product

Resources

About