Unmanned aerial vehicle object tracking and following

Abstract

Today, the use of Quadcopter on human activities are increasingly dominant, especially in the field of search and rescue. One of the most challenging case on SAR using Unmanned Aerial Vehicle quadcopter is tracking and following an object which is newly recognized. The system could track any kind of object which the user choose in real time and the object could be immediately recognize. After the object recognized, the quadcopter could track and follow the object with a high degree of precision. This research reports the results of design and program for quadcopter control that can track and follow a 3D objects which was initially determined first. The algorithm for tracking system used several method from image processing to extract the information from the image (feature extraction base on color), then the information will be used as a reference movement quadcopter in following the target. The object tracking system, used various methods of image processing in the domain of HSV-RGB, Camshift, and Kanade-Lucas-Tomasi Tracker to optimizing 2D tracking system and increase the succes rate of the program. While the method of distance estimation using the camera calibration towards the distance. Output from the tracking system are the object coordinates (x, y, z). This information is fed back to the quadcopter Robot Operating System (ROS) as the error between the positions of the camera with the position of objects, and is known as Visual Servoing. Quadcopter control system using PID constants in the leading to the movement of the pitch, throttle, and roll, to maintain the position of quadcopter towards the target and follow an object moving forwards or backwards.