Towards a vision-based targeting system for counter unmanned aerial systems (CUAS)

Unmanned aerial vehicles (UAVs) are rapidly increasing in popularity. Despite attempts at regulation, stopping small, Class 1 (typically hobby-grade) UAVs from entering protected or sensitive airspace is an unsolved problem. Many companies and researchers offer a piece of a solution, but as of this writing, there is no publicly available, feasible, end-to-end solution. Ultimately, what is needed is a sensor-based system that autonomously detects, tracks, and neutralizes/disables an incoming UAV. However, such a system is currently not available, so as development toward that goal continues, a temporary solution is required. Augmenting the skill, dexterity, and processing power of human pilots with inexpensive cameras and computer vision algorithms can offer such a solution. The foundations of a framework for a system that uses computer vision to target and ultimately destroy a target in mid-air is introduced. The proposed solution utilizes a light-weight, inexpensive UAV with an on-board camera. The detection and tracking is performed in real-time on a companion computer mounted to the frame of the vehicle, with ROS as the primary communication infrastructure. Initial simulations provide insight into the feasibility of using computer vision with a monocular camera to offer reliable assistance to the pilot.