A real-time ball trajectory follower using Robot Operating System

摘要

Modern sports events involve multiple cameras recording the event with very high quality of video. The multiple camera system is complex and generally requires a team of trained men to get the best shot of the ball especially in challenging cases such as line calls in tennis events, corner detection in football events etc. This paper suggests a simple, economical and less time consuming solution using an object tracking algorithm implemented via an Unmanned Aerial Vehicle (UAV). The UAV used in the paper is the Vertical Take-off and Landing (VTOL) Parrot A.R. Drone 2.0 which acts as a moving aerial platform and aims at tracking fast moving ground objects by processing real-time camera feed. Presently, the images from the front camera of the drone are obtained and the moving ground object detected by colour segmentation techniques. The detected object is continuously tracked by centering the image frame. Open Source Computer Vision libraries (OpenCV) are used to process the images obtained from the drone which is controlled by an environment created using Robot Operating System (ROS).