论文标题
使用HGCN在视觉大满贯中半监督矢量定量化
Semi-supervised Vector-Quantization in Visual SLAM using HGCN
论文作者
论文摘要
在本文中，引入了两种半监督外观循环闭合检测技术，HGCN-FABMAP和HGCN弓。此外，还提出了对艺术定位的当前状态的扩展。提出的HGCN-FABMAP方法是以离线方式实施的，该方法结合了贝叶斯概率模式进行环路检测决策。具体而言，我们让双曲线图卷积神经网络（HGCN）在冲浪中运行，并在SLAM过程中执行矢量量化部分。以前使用HKMeans，Kmeans ++等算法以无监督的方式进行此部分。使用HGCN的主要优点是它在图形边数的数量上线性缩放。实验结果表明，HGCN-FABMAP算法比HGCN-ORB需要更多的集群质心，否则它无法检测到环的封闭。因此，我们认为HGCN-ORB在记忆消耗方面更有效率，同样，我们就其他算法就HGCN-BOW和HGCN-FABMAP的优越性。
In this paper, two semi-supervised appearance based loop closure detection technique, HGCN-FABMAP and HGCN-BoW are introduced. Furthermore an extension to the current state of the art localization SLAM algorithm, ORB-SLAM, is presented. The proposed HGCN-FABMAP method is implemented in an off-line manner incorporating Bayesian probabilistic schema for loop detection decision making. Specifically, we let a Hyperbolic Graph Convolutional Neural Network (HGCN) to operate over the SURF features graph space, and perform vector quantization part of the SLAM procedure. This part previously was performed in an unsupervised manner using algorithms like HKmeans, kmeans++,..etc. The main Advantage of using HGCN, is that it scales linearly in number of graph edges. Experimental results shows that HGCN-FABMAP algorithm needs far more cluster centroids than HGCN-ORB, otherwise it fails to detect loop closures. Therefore we consider HGCN-ORB to be more efficient in terms of memory consumption, also we conclude the superiority of HGCN-BoW and HGCN-FABMAP with respect to other algorithms.
