Visual Loop Closure Detection Based on SqueezeNet Multi-layer Feature Fusion and Adaptive Range Matching Algorithm

Loop closure detection(LCD) is an essential part of the visual SLAM system, which can reduce the cumulative error caused by drift. LCD based on traditional methods adopts artificially designed image features. However, this method lacks semantic information and is vulnerable to the external lighting...

Full description

Saved in:
Bibliographic Details
Published inJournal of intelligent & robotic systems Vol. 108; no. 3; p. 55
Main Authors Hu, Zhengnan, Hu, Likun
Format Journal Article
LanguageEnglish
Published Dordrecht Springer Netherlands 01.07.2023
Springer Nature B.V
Subjects
Accuracy
Adaptive algorithms
Artificial Intelligence
Control
Electrical Engineering
Engineering
Feature extraction
Matching
Mechanical Engineering
Mechatronics
Multilayers
Regular Paper
Robotics
SqueezeNet
Feature matching
Visual SLAM
Loop closure detection
Feature fusion
Online AccessGet full text

Cover

More Information
Summary:Loop closure detection(LCD) is an essential part of the visual SLAM system, which can reduce the cumulative error caused by drift. LCD based on traditional methods adopts artificially designed image features. However, this method lacks semantic information and is vulnerable to the external lighting environment. Aiming at the problem of missing information in the image feature representation of LCD, this article proposes a feature extraction method based on multi-layer feature fusion of the lightweight network SqueezeNet. This method can reduce the loss of location and detail information and significantly improve the feature-matching accuracy and extraction rate. Then we employ the nonlinear KPCA method to reduce the dimension of the extracted image feature vectors. In addition, in order to prevent the error matching of adjacent images and the long matching time, we propose an adaptive range matching algorithm, which adaptively limits the matching range in the matching feature stage and jumps out of unnecessary candidate ranges by setting corresponding thresholds and dictionaries of candidate key frames. It not only improves the accuracy of LCD but also dramatically reduces the matching time. The extensive experiments on relevant datasets show that the proposed method has higher accuracy and rate than other methods of CNNs, achieving better robustness and real-time requirements and proving the method’s effectiveness for LCD.
ISSN:0921-0296
1573-0409
DOI:10.1007/s10846-023-01912-4