GESTURE RECOGNITION FOR PENCAK SILAT TAPAK SUCI REAL-TIME ANIMATION

GESTURE RECOGNITION FOR PENCAK SILAT TAPAK SUCI REAL-TIME ANIMATION

Gesture Recognition, Algorithm Dynamic time warping, Algorithm Genetic, Pencak Silat

The main target in this research is a design of a virtual martial arts training system in realtime and as a tool in learning martial arts independently using genetic algorithm methods and dynamic time warping. In this paper, it is still in the initial stages, which is focused on taking data sets of martial arts warriors using 3D animation and the Kinect sensor cameras, there are 2 warriors x 8 moves x 596 cases/gesture = 9,536 cases. Gesture Recognition Studies are usually distinguished: body gesture and hand and arm gesture, head and face gesture, and, all three can be studied simultaneously in martial arts pencak silat, using martial arts stance
detection with scoring methods. Silat movement data is recorded in the form of oni files using the OpenNI ™ (OFW) framework and BVH (Bio Vision Hierarchical) files as well as plugin support software on Mocap devices. Responsiveness is a measure of time responding to interruptions, and is critical because the system must be able to meet the demand.

Aminudin, Widi Hastomo, and L.M. Rasdi Rere

http://dx:doi:org/10:21609/jiki:v13i2.855

Faculty of Computer Science Universitas Indonesia

2020-06-30

Sri Wahyuni

e-ISSN : 2502-9274 printed ISSN : 2088-7051

PDF

English

Text

Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)