论文部分内容阅读
作为一种新兴的无人机,微小型飞行器(MAV)近年来广受关注。研究微小型飞行器导航技术的关键是研究视觉导航技术在微小型飞行器中的应用。针对微小型飞行器视觉导航中的运算量大而导致算法实时性差的问题,给出了一个新的计算框架。利用主元分析技术(PCA),在最小方差意义下得到了图像的简化表示。在此简化的基础上,进行了图像特征的提取。对真实图像的实验结果表明,利用主元分析处理后的图像进行导航特征的提取,其实时性优于RGB三通道求和取平均的方法。
As a new type of UAV, the micro-aircraft (MAV) has drawn much attention in recent years. The key to the research of micro-aircraft navigation technology is to study the application of visual navigation technology in micro-aircraft. Aiming at the problem of poor real-time performance of the algorithm in the visual navigation of micro-aircraft, a new calculation framework is given. Using principal component analysis (PCA), a simplified representation of the image is obtained in the sense of minimum variance. On the basis of this simplification, image feature extraction was carried out. Experimental results on real images show that the method of extracting the navigation features using the image processed by the principal component analysis is superior to the real-time nature of RGB triple-channel summation.