摘要
小型无人飞行器是一个新兴的研究领域,而无人飞行器的自主安全着陆则是该领域中的一个关键技术问题。无人飞行器通常装载有数字相机,可对飞行器下方的地貌进行实时拍摄。本文提出一种基于金字塔方法的地貌类型辨识方法,可利用飞行器所拍摄地貌图像中的色彩信息快速辨识出飞行器下方的地貌类别,从而指导无人飞行器规避危险区域,选择安全着陆点。实验结果表明,本文方法可有效利用不同类型地貌之间显著的彩色分布差异,实现对多种常见自然地貌与人工地貌类型的辨识。
Miniature pilotless flying vehicle( PFV) is an emerging research area,where the autonomous safe landing of the PFVs is a critical technical issue. PFVs usually contain digital cameras,which can take photos of landform below in real time. In the paper,a pyramid-based landform type identification method is proposed. It employs the color information of the landform pictures taken by PFVs to fast recognize the types of landforms beneath the PFVs,guiding the PFVs to steer clear of dangerous areas and select safe landing sites. The experimental results demonstrate that the proposed method can effectively use the color distribution differences of various landforms to identify a variety of natural and man-made landforms.
出处
《激光杂志》
北大核心
2015年第8期47-50,共4页
Laser Journal
基金
河南省教育厅高等学校重点科研项目(14A320029)
河南省科技攻关项目(112102210338)
关键词
图像处理
地貌辨识
金字塔方法
无人飞行器
Image processing
Landform identification
Pyramid-based method
Pilotless flying vehicles
