论文部分内容阅读
提出了一种基于结构张量的、无需先验知识的、可广泛应用于各种环境的多尺度激光雷达数据特征提取方法.这种方法与经典的图像处理方法具有相似的数学意义,利用数据对应的结构张量来评价特征的显著性.在经典数据集上对比了文中提出方法与经典方法的重复度和计算复杂度,实验结果表明:这种方法具有广泛适用性,并比传统方法具有更高的精度和重复度.
A feature-based multi-scale lidar data feature extraction method based on structure tensor without prior knowledge is presented, which can be widely used in a variety of environments.This method has similar mathematical meaning with the classical image processing method, The corresponding structure tensor is used to evaluate the saliency of the feature.The repeatability and computational complexity of the proposed method and the classical method are compared on the classical data set.The experimental results show that this method has a wide range of applicability and has more advantages than the traditional method Higher accuracy and repeatability.