题名: | Mitigating the Effects of Boom Occlusion on Automated Aerial Refueling Through Shadow Volumes. |
作者: | Paulson, Z. C. |
关键词: | Computer vision, Unmanned aerial vehicles, Refueling in flight, Air navigation, Global positioning systems, Reliability, Simulations, Point clouds, Image processing, Flight paths, Algorithms, Artificial intelligence, Virtual reality, Automated aerial refueling, Virtual world, Position estimation, Relative navigation, Shadow volumes |
摘要: | In flight refueling of Unmanned Aerial Vehicles (UAVs) is critical to the United States Air Force. However, the large communication latency between an operator and his/her remote UAV makes aerial refueling unsafe. This latency may be overcome by a tanker-based vision system that observes and computes an approaching receivers relative pose. Unfortunately, the boom an arm responsible for physically pumping fuel into the receiver occludes large portions of the receiver. The vision system must be able to compensate for the booms occlusion of the receiver. Our algorithm dynamically compensates for occluded receiver geometry by transforming the occluded areas into shadow volumes. These shadow volumes are then used to cull hidden geometry that is traditionally consumed, in error, by the vision processing pipeline. |
报告类型: | 科技报告 |