Loop closure detection using supervised and unsupervised deep neural networks for monocular SLAM systems
Loop closure detection using supervised and unsupervised deep neural networks for monocular SLAM systems
复制标题
使用监督和无监督深度神经网络进行单目 SLAM 系统的闭环检测
DOI：
10.1016/j.robot.2020.103470
复制
发表时间：
2020-04-01
影响因子：
4.3
通讯作者：
Hussain, Abid
中科院分区：
文献类型：
--
作者：
Memon, Azam Rafique;Wang, Hesheng;Hussain, Abid
在视觉同时定位和地图构建（vSLAM）中检测真实环路闭合可以在许多方面有所帮助，它有助于重新定位，提高地图的准确性，并且有助于配准算法获得更准确和一致的结果。环路闭合检测受许多参数的影响，包括光照条件、季节、不同视点和移动的物体。本文提出了一种基于超级字典的新方法，不同于传统的BoW字典，它使用了深度学习的更高级和更抽象的特征。所提出的方法不需要生成词汇表，这使得它的内存效率，而是它存储确切的功能，这是小的数量和持有非常少量的内存相比，传统的BoW方法，其中每个帧持有相同数量的内存作为词汇表中的单词的数量。两个深度神经网络一起使用，以加速环路闭合检测，并忽略移动的对象对环路闭合检测的影响。我们将结果与最流行的词袋方法DBoW 2和DBoW 3以及使用五个公开数据集的最先进的iBoW-LCD进行了比较，结果表明，所提出的方法鲁棒地执行循环闭合检测，并且比同类的最先进方法快8倍。(C)2020 Elsevier B. V.保留所有权利。
The detection of true loop closure in Visual Simultaneous Localization And Mapping (vSLAM) can help in many ways, it helps in re-localization, improves the accuracy of the map, and helps in registration algorithms to obtain more accurate and consistent results. The loop closure detection is affected by many parameters, including illumination conditions, seasons, different viewpoints and mobile objects. This paper proposes a novel approach based on super dictionary different from traditional BoW dictionary that uses more advanced and more abstract features of deep learning. The proposed approach does not need to generate vocabulary, which makes it memory efficient and instead it stores exact features, which are small in number and hold very less amount of memory as compared to traditional BoW approach in which each frame holds the same amount of memory as the number of words in the vocabulary. Two deep neural networks are used together to speed up the loop closure detection and to ignore the effect of mobile objects on loop closure detection. We have compared the results with most popular Bag of Words methods DBoW2 and DBoW3, and state-of-the-art iBoW-LCD using five publicly available datasets, and the results show that the proposed method robustly performs loop closure detection and is eight times faster than the state-of-the-art approaches of a similar kind. (C) 2020 Elsevier B.V. All rights reserved.