微飞行器视觉下自主着陆跑道识别技术研究毕业论文.doc

哈尔滨工程大学本科生毕业论文 PAGE 微飞行器视觉下自主着陆跑道识别技术研究 毕业论文 摘 要 随着应用的需要和航空技术的发展，近年来在世界范围内掀起了微飞行器的研究热潮。基于视觉的微飞行器自主着陆得到了广泛的研究。本文主要研究了微飞行器着陆过程中，利用机载照相设备获取微飞行器着陆姿态、识别跑道的技术。 本文以微型无人直升机飞行过程中拍摄到的着陆场景图像为研究对象，选择着陆平台为图像处理中特征提取的目标，研究利用机器视觉的理论，通过数字图像处理的方法以及代数与几何的知识，实时提取着陆过程中的飞行参数，为微飞行器自主着陆提供导航信息。首先，对拍摄到的图片运用MATLAB进行图像处理，消除噪声并提取出跑道特征；其次，对着陆平台进行直线检测，深入分析了特征直线和图像边界线与微飞行器姿态角之间的关系，确定了从着陆平台直线参数中求解微飞行器偏航角和俯仰角的方法，因微飞行器降落过程中滚转角很小，是一个小角度量，在降落过程中可以不予考虑。 微飞行器的姿态角是它稳定飞行和安全着陆的重要导航参数。理论分析和实验结果表明，基于视觉的微飞行器自主着陆导航是可行的，具有一定的实时性和较高的计算精度，可以对微飞行器实现自主着陆。 关键词：微飞行器；图像处理；跑道识别；飞行参数 ABSTRACT With the demands of applicatoin and development of aeronautic technology, more and more attentions are paid to the research on Micro Air Vehicle(MAV) all over the world in recent years. A lot of research on computer vision-based for MAV autonomous landing has been done. In this paper ,we do some research on how to segment the runway area out of the image and obtain the attitude of the MAV with the vision technology. In this article, we process the image sequence of the runway which is got from an onboard camera, estimate the attitude and position of the aircraft. This article select the landing platform to target feature extraction for image processing, the theory of the use of machine vision, digital image processing methods, and knowledge of algebra and geometry, real-time to extract the parameters of the flight in the landing process, to provide navigation information for automomous landing of the MAV. In order to obtain the attitude information of the MAV, we research the relations betwwen the characterristics of a straight line and the image boundary line and the attitude. From the linear parameters of the landing platform, the yaw angle and pitch angle can be found. The theoretical analysis and the experiment result show that the extraction and conversion of vision-based navigation information for aircraft autonomous landing are feasible. It has a certain real-time and a high precision, so very suitable for a real-tim