标题：Vision Only Collision Detection with Omnidirectional Multi-Camera System * * This work was supported by the Institute for Computer Science and Control (SZTAKI) Grant Number 008
摘要：AbstractThis article presents an omnidirectional multi-camera system applied to monocular image based visual aircraft sense and avoid. The proposed system can cover 360 degrees horizontal field fo view and so estimate possibility of collision even for intruders coming from backward. First, the definitions of time-to-collision (TTC) and closest point of approach (CPA) are summarized then a simple image parameter based method is proposed for their estimation even in case of oblique camera placement relative to aircraft forward direction. An error analysis of the applied approximation formula is done and a solution to pass past measurements from one camera coordinate system to another if the intruder moves is also presented. Finally a six camera system covering all the horizontal plane is proposed and simulated in software-in-the-loop. A large range of collision and non collision situations with different intruder sizes, velocities, miss distances and flight directions is tested. The validity of decisions is evaluated and the further development directions are determined.
