用于无人直升机着舰控制的计算机视觉技术研究  

Computer Vision Scheme Used for the Automate Landing of Unmanned Helicopter on Ship Deck

作　　者：邱力为[1] 宋子善[1] 沈为群[1] 

机构地区：[1]北京航空航天大学自动化与电气工程学院,北京100083

出　　处：《航空学报》2003年第4期351-354,共4页Acta Aeronautica et Astronautica Sinica

摘　　要：通过理论分析和计算机半实物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。研究了基于HSV均匀色标的计算机视觉技术在无人直升机着舰控制中的应用。使用Hough变换算法检测直线参数 ,在Hough变换中利用梯度信息 ,它的应用打破了Hough变换的计算瓶颈。整套算法的抗噪声能力很强 。A computer vision solution scheme for the automatic landing of an unmanned helicopter on a ship was examined from the view of engineering application. A series of computer vision algorithms such as Sobel filter and Fast Hough Transform, were adopted and integrated to get the relative positions between the helicopter and the ship, from which their relative movement parameters can be obtained. The image segmentation was executed in HSV color space. Hough Transform was adopted to detect the linear parameters, the bottle neck of which was broken with the use of gradient information. The use of Hough Transform makes the stereo vision scheme very robust to noise. Computer simulation results indicate that the presented algorithms are robust and reliable.

关 键 词：无人直升机 计算机视觉 图像分割 边缘提取 Houhg变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] V249.1[自动化与计算机技术—计算机科学与技术]