LAUSR

Unmanned Aerial Vehicle (UAV) technology is being increasingly used in a wide variety of applications ranging from remote sensing, to delivery and security. As the number of UAVs increases, there is a growing need for UAV to UAV detection and tracking systems for both collision avoidance and coordination. Among possible solutions, autonomous “see-and-avoid” systems based on low-cost high-resolution video cameras offer important advantages in terms of light weight and low power consumption. However, in order to be effective, camera based “see-and-avoid” systems require sensitive, robust, and computationally efficient algorithms for autonomous detection and tracking of UAVs from a moving camera. In this article, we propose a general architecture for a highly accurate and computationally efficient UAV to UAV detection and tracking (U2U-D&T) algorithm from a camera mounted on a moving UAV platform. The system is based on a computationally efficient pipeline consisting of a moving target detector, followed by a target tracker. The algorithm is validated using video data collected from multiple fixed-wing UAVs that is manually ground-truthed and is publicly available. Results indicate that the proposed algorithm can be implemented on commodity hardware and robustly achieves highly accurate detection and tracking of even distant and faint UAVs. Open source code for the U2U-D&T algorithm is available at: https://github.com/jingliinpurdue/Fast-and-Robust-UAV-to-UAV-Detection-and-Tracking.git.