CNN Feature Boosted SeqSLAM for Real-Time Loop Closure Detection

作     者：BAI Dongdong WANG Chaoqun ZHANG Bo YI Xiaodong YANG Xuejun 

作者机构：College of Computer National University of Defense Technology State Key Laboratory of High Performance Computing National University of Defense Technology National Institute of Defense Technology Innovation 

出 版 物：《Chinese Journal of Electronics》 (电子学报(英文))

年 卷 期：2018年第27卷第3期

页      面：488-499页

核心收录：

学科分类：080202[工学-机械电子工程] 08[工学] 080203[工学-机械设计及理论] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 

基　　金：the National Natural Science Foundation of China(No.615307,No.916484,No.61601486) Research Programs of National University of Defense Technology(No.ZDYYJCYJ140601) State Key Laboratory of High Performance Computing Project Fund(No.1502-02) 

主　　题：Simultaneous localization and mapping(SLAM) Loop closure detection(LCD) Convolutional neural network(CNN) SeqSLAM SeqCNNSLAM A-SeqCNNSLAM O-SeqCNNSLAM P-SeqCNNSLAM 

摘      要：This paper proposes an efficient and robust Loop closure detection(LCD) method based on Convolutional neural network(CNN) feature. The primary method is called SeqCNNSLAM, in which both the outputs of the intermediate layer of a pre-trained CNN and the outputs of traditional sequence-based matching procedure are incorporated, making it possible to handle the viewpoint and condition variance properly. An acceleration algorithm for SeqCNNSLAM is developed to reduce the search range for the current image, resulting in a new LCD method called A-SeqCNNSLAM. To improve the applicability of A-SeqCNNSLAM to new environments, O-SeqCNNSLAM is proposed for online parameters adjustment in A-SeqCNNSLAM. In addition to the above work, we further put forward a promising idea to enhance Seq SLAM by integrating the both CNN features and VLAD’s advantages called patch based Seq CNNSLAM(P-SeqCNNSLAM), and provide some preliminary experimental results to reveal its performance.