【摘要】 准确估计无人机着陆时的相对位置和姿态对实现无人机安全着陆具有重要的意义,正确地提取出合作目标中的特征点是一个重要环节。本文提出了一种合作目标特征点的提取方法,首先,通过Sobel算子对合作目标进行边缘检测;然后,利用轮廓跟踪获得合作目标的轮廓链码表;最后,利用合作目标的形状特征以及链码的特性,从合作目标的图像中提取出10个特征点。实验结果表明,本文的方法能很好地提取出合作目标的特征点,为后续的无人机姿态信息的精确计算提供了保障。更多还原

【Abstract】 Precisely estimating the position and pose information of the unmanned aerial vehicle(UAV) plays an important role in the safe landing of the UAV,and feature point extraction of the cooperative object is a key point in the procedure.This paper presents a method to extract the feature point of the cooperative object.Firstly,the edge of the object using Sobel method is detected;secondly,the chain code of the outline is gotten;finally,10 feature points of the cooperative object are extracted by using the characteristic of the cooperative object and chain code.Experiment results show that the method can pick-up the feature points accurately,and these points can provide a guarantee for the computing of the UAV’s landing information.更多还原