Object recognition and tracking using Haar-like Features Cascade Classifiers: Application to a quad-rotor UAV

This paper develops a functional Unmanned Aerial Vehicle (UAV) capable of tracking an object using a Haar feature-based cascade classifier. The object in question is a human face; the experiments were conducted in a two-step detection, searching first for the upper body and then searching for the face inside the human body detected area. Once the human face is detected, the quadrotor must follow it automatically. The quadrotor must track the face in a central position and maintain a safe distance. The image processing is made on-board with a high processor single-board computer. Experiments have been conducted showing our mythology's effectiveness; these results are shown in a video.