结合多重注意力机制的V-SLAM闭环检测特征匹配算法  

V-SLAM Loop Closure Detection Feature Matching Algorithm Combined with Multiple Attention Mechanisms

作　　者：伍宣衡 高贵 王忠美 薛子豪 龙永红[1] WU Xuanheng;GAO Gui;WANG Zhongmei;XUE Zihao;LONG Yonghong(College of Railway Transportation,Hunan University of Technology,Zhuzhou Hunan 412007,China;Faculty of Geosciences and Environmental Engineering,Southwest Jiaotong University,Chengdu 610000,China)

机构地区：[1]湖南工业大学轨道交通学院,湖南株洲412007 [2]西南交通大学地球科学与环境工程学院,四川成都610000

出　　处：《湖南工业大学学报》2023年第5期9-16,共8页Journal of Hunan University of Technology

基　　金：国家级创新创业基金资助项目(S202111535505,S202111535041);湖南省教育厅科研基金资助项目(22A0391,22B0586)。

摘　　要：为了在复杂环境下对V-SLAM闭环检测的准确率-召回率有更好的鲁棒性,提出一种在图神经网络中结合多重注意力机制的局部特征匹配算法,并在闭环检测上进行应用。首先,采用SuperPoint检测器获取图像序列中的关键点,再将提取出来的特征点输入关键点编码器内,通过多层感知器将其升维到与局部描述子维度一样;然后,同时经过多重注意力机制网络中重复9次,得到更具有代表信息的局部描述子;其次,在最优匹配层中采用SinkHorn算法求解出最优匹配矩阵,通过对阈值的合理设定,得到闭环检测结果;最后,在New College和City Centre两个公共数据集上与5种其他闭环检测基准算法进行实验,结果表明该算法在召回率一定的情况下,其准确率比其他实验算法的要高,有更强的鲁棒性,满足闭环检测要求。In order to obtain an improved robustness to the accuracy recall of V-SLAM loop closure detection in complex environments,a local feature matching algorithm,combined with multiple attention mechanisms in graph neural network,has been proposed with an application to the loop closure detection.Firstly,the SuperPoint detector is used to obtain the key points in the image sequence,followed by an input of the extracted feature points into the key point encoder,with its dimension raised to the same as the local descriptor sub-dimension by using a multi-layer perceptron.Then,a more representative local description can be obtained after being repeated 9 times in a multiple attention mechanism network.Next,the SinkHorn algorithm is used to solve the optimal matching matrix in the optimal matching layer,thus obtaining the loop closure detection result by setting the threshold reasonably.Finally,experiments are conducted,alongside with five other loop closure detection benchmark algorithms,on two common datasets of New College and City Centre.The results show that the proposed algorithm is characterized with a higher accuracy and a stronger robustness than other experimental algorithms under a certain recall rate,meeting the requirements of closed-loop detection.

关 键 词：同步定位与建图 闭环检测 图神经网络 多重注意力机制 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]