2016 IEEE International Conference on Real-Time Computing and Robotics (RCAR) 2016
DOI: 10.1109/rcar.2016.7784003
|View full text |Cite
|
Sign up to set email alerts
|

Matching-range-constrained real-time loop closure detection with CNNs features

Abstract: The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional neural networks (CNNs) have outperformed state-of-the-art solutions that use traditional hand-crafted features in many computer vision and pattern recognition applications. After the great success of CNNs, there has … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
4
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(4 citation statements)
references
References 27 publications
0
4
0
Order By: Relevance
“…Manual sparse image features, on the other hand, are currently limited due to challenges in mapping complex dynamics or large-scale scenarios with too many or too few feature points. Within the visual SLAM-based system, a deep learning-enhanced categorized image feature extraction approach has emerged in recent years, which is used for loop closure detection (Gao and Zhang, 2015) and visual odometry (Dosovitskiy et al, 2015;Handa et al, 2016;Costante et al, 2015;Bai, 2016). Bescos et al (2018) describe DynaSLAM, a visual SLAM system, that extends ORB-SLAM2 (Mur-Artal and Tard os, 2017) with dynamic object identification and backdrop inpainting.…”
Section: Introductionmentioning
confidence: 99%
“…Manual sparse image features, on the other hand, are currently limited due to challenges in mapping complex dynamics or large-scale scenarios with too many or too few feature points. Within the visual SLAM-based system, a deep learning-enhanced categorized image feature extraction approach has emerged in recent years, which is used for loop closure detection (Gao and Zhang, 2015) and visual odometry (Dosovitskiy et al, 2015;Handa et al, 2016;Costante et al, 2015;Bai, 2016). Bescos et al (2018) describe DynaSLAM, a visual SLAM system, that extends ORB-SLAM2 (Mur-Artal and Tard os, 2017) with dynamic object identification and backdrop inpainting.…”
Section: Introductionmentioning
confidence: 99%
“…Deep learning has made outstanding achievements in image processing and has shown excellent performance in image classification [10][11][12] and image detection [13][14][15]. Deep learning has become increasingly popular in the field of SLAM in recent years [16]. The features of the image can be extracted well by the large-scale pre-trained neural network.…”
Section: Introductionmentioning
confidence: 99%
“…Compared with FAB-MAP, it was superior with higher recall rate. [17] used Places-CNNs and provided matching range of candidate images to prevent the matching between adjacent images. [18] utilized outputs at intermediate layer as descriptors.…”
Section: Introductionmentioning
confidence: 99%