Open AccessLoop Closure Detection based on Regional Weighted and Siamese Network
Author(s) -
Wenju Li,
Qianwen Ma,
Cui Liu,
Tianzhen Dong
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1848/1/012105
Subject(s) - robustness (evolution) , artificial intelligence , simultaneous localization and mapping , computer science , for loop , convolution (computer science) , weighting , feature (linguistics) , pattern recognition (psychology) , closure (psychology) , feature extraction , consistency (knowledge bases) , fuse (electrical) , computer vision , loop (graph theory) , robot , mathematics , mobile robot , engineering , artificial neural network , combinatorics , philosophy , linguistics , chemistry , biochemistry , market economy , radiology , medicine , electrical engineering , economics , gene
Loop closure detection (LCD) is essential for the Simultaneous Localization and Mapping (SLAM) system of an autonomous robot. Aiming at the problem of false positive in traditional loop closure detection methods, in this paper we propose an end-to-end siamese network model. Firstly, the siamese network with two same branches is designed to learn the characteristics of each image pairs. Secondly, the multi-region feature weighting method is introduced to fuse saliency regions of convolutional feature map, which well reflect structured information of the environment. In the end, the geometric consistency verification is used on the candidate convolution feature map to determine the true loop. As a result, experiments on several public datasets have illustrated the superiority of our approach. Compared with traditional methods, under the precision of 100% accuracy, the recall rate is increased by 15%. Our model is more stable in different scenarios, which can achieve robustness loop closure detection.