People Detection and Tracking Using an On-Board Drone Camera

The problem of people detection and tracking in unmanned ground vehicles has been studied in depth in computer vision and autonomous robotics research communities. Different well-known proposals have already been proposed to solve the problem of people detection and tracking using machine vision algorithms. However, for unmanned aerial vehicles, it is still a subject of research today. The lack of highquality sensors and on-board cameras and the capability to process the data collected in real-time makes it difficult to achieve optimal solutions in real-time. In this work, we propose to use machine vision algorithms to process in real-time the images collected by the camera of a drone and subsequently performing the detection and tracking of people who are located in the environment. The proposal was experimentally evaluated comparing different semantic segmentation techniques. Finally, to validate the proposal, a real scenario was created and carried out, which consisted of detecting and tracking people with a drone autonomously in a controlled environment.