Gesture Recognition Aplication based on Dynamic Time Warping (DTW) FOR Omni-Wheel Mobile Robot

Gama, Indra (2011) Gesture Recognition Aplication based on Dynamic Time Warping (DTW) FOR Omni-Wheel Mobile Robot. EEPIS Final Project.

Preview

PDF Download (665Kb) | Preview

Abstract

This project presents of the movement of omni-wheel robot moves in the trajectory obtained from the gesture recognition system based on Dynamic Time Warping. Single camera is used as the input of the system, which is also a reference to the movement of the omni-wheel robot. Some systems for gesture recognition have been developed using various methods and different approaches. The movement of the omni-wheel robot using the method of Dynamic Time Wrapping (DTW) which has the advantage able to calculate the distance of two data vectors with different lengths. By using this method we can measure the similarity between two sequences at different times and speeds. Dynamic Time Warping to compare the two parameters at varying times and speeds. Application of DTW widely applied in video, audio, graphics, etc. Due to data that can be changed in a linear manner so that it can be analyzed with DTW. In short can find the most suitable value by minimizing the difference between two multidimensional signals that have been compressed. DTW method is expected to gesture recognition system to work optimally, have a high enough value of accuracy and processing time is realtime.

Actions (login required)