Recognition of Dynamic Hand Gestures from 3D Motion Data Using LSTM and CNN Architectures

2017 ◽  
Author(s):  
Chinmaya R. Naguri ◽  
Razvan C. Bunescu
Keyword(s):  
Hand Gestures ◽  
3D Motion ◽  
Motion Data

Motion Comparison Method Combining Segmented Multi-Joint Line Graphs with the SIFT Matching Technique

2014 ◽  
Vol 599-601 ◽  
pp. 1566-1570
Author(s):  
Ming Zeng ◽  
Hong Lin Ren ◽  
Qing Hao Meng ◽  
Chang Wei Chen ◽  
Shu Gen Ma
Keyword(s):  
Feature Matching ◽  
Line Graph ◽  
Comparison Method ◽  
Joint Line ◽  
Line Graphs ◽  
3D Motion ◽  
Motion Data ◽  
Comparison Results ◽  
Matching Technique ◽  
Sift Features

In this paper, an effective motion comparison method based on segmented multi-joint line graphs combined with the SIFT feature matching method is proposed. Firstly, the multi-joint 3D motion data are captured using the Kinect. Secondly, 3D motion data are normalized and distortion data are removed. Therefore, a 2D line graph can be obtained. Next, SIFT features of the 2D motion line graph are extracted. Finally, the line graphs are divided into several regions and then the comparison results can be calculated based on SIFT matching ratios between the tutor’s local line graph and the trainee’s local line graph. The experimental results show that the proposed method not only can easily deal with the several challenge problems in motion analysis, e.g., the problem of different rhythm of motions, the problem of a large amount of data, but also can provide detailed error correction cues.

On the Motion Dimension Reduction by Laplacian Eigenmap

2011 ◽  
Vol 52-54 ◽  
pp. 556-561
Author(s):  
Hao Jiang ◽  
Jie Xu ◽  
Zhuo Chen
Keyword(s):  
Data Analysis ◽  
Dimension Reduction ◽  
Motion Analysis ◽  
Video Analysis ◽  
Complex Data ◽  
3D Motion ◽  
Motion Data ◽  
3D Motion Analysis ◽  
Analysis Methods ◽  
Independent Motion

Laplacian eigenmap is used for motion dimension reduction. Eight Kinds of artificially typical 2D motion data are made as input of Laplacian eigenmap, and meaningful conclusions are obtained, which can be easily extended to complex data analysis in real applications. Advanced motion analysis methods have also been discussed briefly, such as 3D motion analysis, view independent motion analysis, pose representation and estimation as well as structural video analysis.

Abundant Information of Hip Joint for Gender Detection Using 3D Motion Data

2013 ◽  
Vol 5 (10) ◽  
pp. 149-160 ◽  
Author(s):  
Sajid Ali ◽  
Zhongke Wu ◽  
Mingquan Zhou ◽  
Muhammad Aslam Asadi ◽  
Hafeez Ahmed
Keyword(s):  
Hip Joint ◽  
3D Motion ◽  
Motion Data ◽  
Gender Detection

Character animation from 2D pictures and 3D motion data

2007 ◽  
Vol 26 (1) ◽  
pp. 1 ◽  
Author(s):  
Alexander Hornung ◽  
Ellen Dekkers ◽  
Leif Kobbelt
Keyword(s):  
Character Animation ◽  
3D Motion ◽  
Motion Data
Sign in / Sign up

Export Citation Format

Share Document