Real-Time Recognition of the User's Arm Gestures in 2D Space with a Smart Camera

Abstract

Gesture control technology is one of the most important technologies introduced today to facilitate human-machine communication. In this article, we propose a Smart Camera One (SCO) to remotely monitor a user's arm movements in order to control a machine. Therefore, its main role is to act as an intermediary between the user and the machine to facilitate communication. This instrument technology can measure and control the different arm positions in real-time with an accuracy of up to 81.5%. The technique consists of learning to perform live tasks. SCO is able to immediately execute a user's task without going through the machine learning phase through demonstrations. During the time of the test, the setup of the demonstrator is done visually by SCO, it can recognize users according to their skin color and distinguish them from colorful backgrounds. This is based on image processing using an intelligent algorithm implemented in the SCO through the Python programming languages and the OpenCV library as described in this article. Although initially a specialized application, SCO could be important in several areas, from remote control of mobile robots to gaming, education, and even marketing. Extensive experiments demonstrate the effectiveness of the developed model as shown in [1].