USING HAND RECOGNITION IN TELEROBOTICS

The objective of this project is to recognize selected hand gestures and imitate the recognized hand gesture using a robot. A telerobotics system that relies on computer vision to create the human-machine interface was build. Hand tracking was used as an intuitive control interface, as it represents a natural interaction medium. The system tracks the hand of the operator and the gesture it represents, and relays the appropriate signal to the robot to perform the respective action, in real time. The study focuses on two gestures, open hand, and closed hand, as the NAO robot is not equipped with a dexterous hand. Numerous object recognition algorithms were compared and the SURF based object detector was used. The system was successfully implemented, and was able to recognise the two gestures in 3D space using images from a 2D video camera.