Title :
3-D real-time image matching based on kinect skeleton
Author :
Jingxuan Chen ; Xiaoyu Wu ; Tianchu Guo
Author_Institution :
Digital Media Technol., Commun. Univ. of China, Beijing, China
Abstract :
We present a 3-D real-time image matching system based on the skeleton tracking module of Kinect Sensor. To determine an optimal correspondence between real- time and standard image data, we use a dimensional angular representation as a descriptor of the skeleton designed for recognition robustness under noisy input. And we compute a distance metric to evaluate the difference in motion between the poser´s body and the template. The grading formula for image matching is adaptively based on our experimental data, which makes our system, stands a high accuracy under input noise from the real-time depth sensor.
Keywords :
bone; image matching; image sensors; object tracking; three-dimensional displays; 3D display; 3D real-time image matching system; dimensional angular representation; distance metric; grading formula; input noise; kinect sensor; optimal correspondence; poser body; poser template; recognition robustness; skeleton descriptor; skeleton tracking module; standard image data; Joints; Minimization; Standards; 3D; Gesture classification; Kinect sensor; Skeleton;
Conference_Titel :
Electrical and Computer Engineering (CCECE), 2014 IEEE 27th Canadian Conference on
Conference_Location :
Toronto, ON
Print_ISBN :
978-1-4799-3099-9
DOI :
10.1109/CCECE.2014.6900983
