结合注意力机制的多重引导点云配准网络  

Multi-guided Point Cloud Registration Network Combined with Attention Mechanism

作　　者：刘旭珩 柏正尧[1] 许祝 杜佳锦 肖霄 LIU Xuheng;BAI Zhengyao;XU Zhu;DU Jiajin;XIAO Xiao(School of Information Science and Engineering,Yunnan University,Kunming 650221,China)

机构地区：[1]云南大学信息学院,昆明650221

出　　处：《计算机科学》2024年第2期142-150,共9页Computer Science

基　　金：云南省重大科技专项课题(202002AD080001);云南大学第十四届研究生科研创新项目(KC-22222543)。

摘　　要：针对点云配准过程中仅仅利用点云特征寻求对应关系使得离群点多、配准精度不高的问题进行研究,提出了一种使用点云之间匹配点概率矩阵和点云空间信息特征矩阵共同搜寻对应关系,并且相互配合确定对应点权重的点云配准网络——AMGNet。首先使用点云特征提取网络获得两片待配准点云的高维特征;然后采用Transformer对独立特征进行上下文信息融合,之后利用关键点提取模块选取出特征更强的点,使用SoftBBS方法获得点云匹配点概率矩阵后,结合点云空间特征矩阵搜索到最终的对应关系,同时,权重分配也使用了双重矩阵共同决定的策略;最后使用奇异值分解获得需要的刚性变换矩阵。在ModelNet40,7Scenes等人工合成数据集和真实场景数据集上进行了多次实验。结果表明,在ModelNet40目标未知实验中的旋转矩阵和平移向量的均方误差分别降低至0.025和0.0046。AMGNet配准精度较高,抗干扰能力强,泛化能力强。This paper proposes a point cloud alignment network,AMGNet,which uses the probability matrix of matching points between point clouds and the spatial information feature matrix of point clouds to search for correspondence and determine the weights of corresponding points with each other.First,the point cloud feature extraction network is used to get the high-dimensional features of the two unaligned point clouds and then the Transformer is used to fuse the independent features with the contextual information.Also,the weight assignment uses the strategy of double matrix co-determination.Finally,the singular value decomposition is used to obtain the required rigid transformation matrix.Several experiments are conducted on synthetic datasets,such as ModelNet40,7Scenes and real scenes.The results show that the mean square error of rotation matrix and translation vector in ModelNet40 target unknown experiments is reduced to 0.025 and 0.0046,respectively.AMGNet alignment has high accuracy,high interference resistance,and good generalization ability.

关 键 词：点云配准 注意力机制 多重矩阵引导 加权SVD 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]