基于深度学习的几何特征匹配方法  

Geometric Features Matching with Deep Learning

作　　者：李健[1] 杨祥如 何斌[2] LI Jian;YANG Xiang-ru;HE Bin(School of Electrical and Information Engineering,Shaanxi University of Science & Technology,Xi’an 710021,China;School of Electrical and Information Engineering,Tongji University,Shanghai 201804,China)

机构地区：[1]陕西科技大学电气与信息工程学院,西安710021 [2]同济大学电气与信息工程学院,上海201804

出　　处：《计算机科学》2019年第7期274-279,共6页Computer Science

基　　金：国家自然科学基金项目(51538009);陕西省工业攻关项目(2015GY044)资助

摘　　要：Kinect等深度相机采集的三维数据往往存在噪音、低分辨率等问题,导致两帧点云的局部几何特征匹配一直面临挑战。目前多采用基于特征直方图的方法解决这一问题,但其计算量较大,且对场景旋转平移的要求较为严格。文中提出了一种基于数据驱动的方法,首先从大量重建好的RGB-D数据集中,通过自监督的深度学习方法构建能够描述三维数据几何特征的模型;然后利用基于KD-Tree的K近邻算法(KNN)得到两部分点云的特征对应点,通过RANSAC剔除误匹配点对;最后通过得到的较准确的位置关系估计两帧点云的几何变换,从而完成配准。基于斯坦福大学点云库中的模型以及真实环境下Kinect采集到的大卫石膏像模型的配准和比较实验表明,所提方法不仅可以提取未知物体的局部几何特征进行配准,还可以较好地应对空间角度变换大的情况。Matching local geometric features on real-world depth images is a challenging task due to the noisy and low-resolution of 3D scan captured by depth cameras like Kinect.At present,most of the solutions to this problem are based on the feature histogram method,which requires a large amount of calculation and strict requirements on the rotation of the scene.This paper proposed a method based on data-driven.From a large number of well-reconstructed RGB-D data sets,a self-supervised deep learning method is used to construct a model that can describe the geometric correspondence between three-dimensional data.Then,corresponding approximate points of two parts of the point cloud are botained by using KD-Tree-based K Nearest Neighbor(KNN)algorithm.Through removing erroneous matching point pairs using RANSAC,a relatively accurate set of feature point pairs is obtained by estimating the geometric transformation.By regis-tering and comparing the models in the Stanford University point cloud library and the David plaster model collected in the real environment,the experiments show that the proposed method can not only extract the local geometric features of unknown objects for registration,but also show good performance when dealing with large changes in spatial angle.

关 键 词：点云特征配准 深度学习 自监督 KD-TREE 大角度变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]