| 引用本文: | 周朗明,钟磬,张跃强,等.运用跑道平面结构化线特征的固定翼无人机视觉导航算法.[J].国防科技大学学报,2016,38(3):182-190.[点击复制] |
| ZHOU Langming,ZHONG Qing,ZHANG Yueqiang,et al.Vision-based landing method using structured line features of runway surface for fixed-wing unmanned aerial vehicles[J].Journal of National University of Defense Technology,2016,38(3):182-190[点击复制] |
|
| |
|
|
| 本文已被：浏览 7845次 下载 6959次 |
| 运用跑道平面结构化线特征的固定翼无人机视觉导航算法 |
| 周朗明, 钟磬, 张跃强, 雷志辉, 张小虎 |
|
(国防科技大学 航天科学与工程学院， 湖南 长沙 410073)
|
| 摘要: |
| 针对固定翼无人机在着陆阶段的位姿估计的问题，提出运用跑道平面结构化线特征的无人机视觉导航算法。利用单台固连在无人机上的前视相机对跑道区域进行成像，自动提取结构化线特征。在无人机降落前期利用完整的结构化线特征配置解算出无人机的六自由度位姿参数（偏航角、俯仰角、滚转角、纵向位置、横向位置、高度），并在无人机降落到较低高度时，利用退化的结构化线特征（跑道边缘）解算出无人机的关键位姿参数（偏航角、俯仰角、横向位置、高度）。三维实景仿真实验证明，在距离机场200 m处，无人机的距离参数精度小于0.5 m，角度参数精度小于0.1°。 |
| 关键词: 计算机视觉 固定翼无人机 着陆引导 消影点 位姿估计 |
| DOI：10.11887/j.cn.201603030 |
| 投稿日期：2015-03-18 |
| 基金项目:第57批中国博士后基金资助项目（2015M572706） |
|
| Vision-based landing method using structured line features of runway surface for fixed-wing unmanned aerial vehicles |
| ZHOU Langming, ZHONG Qing, ZHANG Yueqiang, LEI Zhihui, ZHANG Xiaohu |
|
(College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China)
|
| Abstract: |
| For the estimation problem of pose and attitude of fixed-wing unmanned aerial vehicles in the terminal landing stage, a vision-based landing method using structured line features was proposed. One forward looking camera equipped in the fixed-wing unmanned aerial vehicles was used to capture multiple pictures of the structured line features and these features were extracted automatically. 6 degrees of freedom pose and attitude parameters (pitch angle, yaw angle, roll angle, longitudinal position, lateral position and altitude) were calculated by using geometric constraint of full configuration structured line features in the earlier stage of the landing, the key parameters (pitch angle, yaw angle, lateral position and altitude) were calculated by using degenerate configuration structured line features (only the runway edges) in the final stage of the landing. In the 3D stimulation experiment, the accuracy of distance is less than 0.5 m, the accuracy of angle is less than 0.1°when the fixed-wing unmanned aerial vehicle is 200 m distant from the airport. |
| Keywords: computer vision fixed-wing unmanned aerial vehicles landing assistant vanish point pose attitude estimation |
|
|
|
|
|
