摘要
通过理论分析和计算机仿真研究了一种应用于无人直升机自主着舰的双目立体计算机视觉系统及相关计算机视觉技术。从工程实践的角度研究了计算机视觉技术在无人直升机自主着舰过程中的应用,并提出了一种快速Hough变换算法,这种快速Hough变换比同精度的标准Hough变换快10倍以上,它的应用使整套算法的抗噪声能力很强。整套算法达到了无人直升机自主着舰的实时性和实用性要求。
A computer vision solution scheme for the automatic landing of an unmanned helicopter on ship was examined from the view of engineering application. A series of computer vision algorithms such as Sobel filter and Fast Hough Transform were adapted and integrated to get the relative positions between the helicopter and ship, from which their relative movement parameters could be obtained. A new kind of Fast Hough Transform was developed to detect the linear parameters, and the speed of which is 10 times faster than the standard Hough Transform. The new Hough Transform makes the stereo vision scheme very robust to noise. Computer simulation results indicate that the presented algorithms are robust and reliable.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2006年第5期1139-1142,共4页
Journal of System Simulation
关键词
无人直升机
计算机视觉
仿真
哈夫变换
unmanned helicopter
computer vision
simulation
Hough transform
