Hierarchical Visual Place Recognition Approach for Robots Based on Joint Decision-making of Tightly-coupled Local and Global Descriptors
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.
visual place recognitionloop closure detectiondeep learningvisual SLAMscene recognition
国家科技期刊平台
NSTL
万方数据
