Real-time Video Streams of Hand Gestures to Control Unmanned Aerial Systems (UAVs)

Over past few years, unmanned aircraft vehicles (UAVs) have been becoming more and more popular for various purposes such as surveillance, automated industry, robotics, vehicle guidance, traffic monitoring and control system. It is very important to have multiple methods of UAVs controlling to fit in UAVs usages. The goal of this work is to develop a technique to control an UAV using 8 different hand gestures. To achieve that, a hand key point detection algorithm is developed to detect 21 key points of the hand. Then, those key points are used as the input to an intelligent system based on Convolutional Neural Networks (CNN) that is able to classify the hand gestures. After archiving hand gesture classifications, unique command for UAVs control is assigned to each hand gesture; and a programming is built in Python to send those commands to an UAV for operation