信息与控制2024，Vol.53Issue(3)：400-415,16.DOI:10.13976/j.cnki.xk.2024.3039
基于局部与全局描述符紧耦合联合决策的机器人分层式视觉位置识别方法
Hierarchical Visual Place Recognition Approach for Robots Based on Joint Decision-making of Tightly-coupled Local and Global Descriptors
摘要
Abstract
Visual place recognition(VPR)is an important means for mobile robots to maintain high-pre-cision localization and map consistency.However,due to the interference of viewpoint and appear-ance changes,the VPR problem remains extremely difficult.We propose a hierarchical VPR meth-od based on joint decision-making of tightly coupled local and global descriptors.The proposed ap-proach learns the ability to extract descriptors based on knowledge distillation.The well-trained lightweight model extracts global and local descriptors of an image in a tightly coupled form,fur-ther converts local descriptors into a binary representation,and maps it to the Bag of Visual Words space.In the constructed VPR architecture,a hierarchical recognition strategy is presented for coarse-to-fine place retrieval and a phase-correlation-based approach is employed to assign the joint decision weights of global and local descriptors.The evaluation results on several benchmark datasets confirm that the proposed approach achieves a significant improvement in performance with acceptable matching efficiency and exhibits strong generalization and robustness in various complex environments.关键词
视觉位置识别/闭环检测/深度学习/视觉SLAM/场景识别Key words
visual place recognition/loop closure detection/deep learning/visual SLAM/scene recognition分类
信息技术与安全科学引用本文复制引用
李康宇,王西峰,朱守泰..基于局部与全局描述符紧耦合联合决策的机器人分层式视觉位置识别方法[J].信息与控制,2024,53(3):400-415,16.基金项目
国家重点研发计划项目(2020YFB1313304) （2020YFB1313304）
