2022
DOI: 10.3390/drones6010023
|View full text |Cite
|
Sign up to set email alerts
|

A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features

Abstract: In view of traditional point-line feature visual inertial simultaneous localization and mapping (SLAM) system, which has weak performance in accuracy so that it cannot be processed in real time under the condition of weak indoor texture and light and shade change, this paper proposes an inertial SLAM method based on point-line vision for indoor weak texture and illumination. Firstly, based on Bilateral Filtering, we apply the Speeded Up Robust Features (SURF) point feature extraction and Fast Nearest neighbor … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
10
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 15 publications
(10 citation statements)
references
References 16 publications
0
10
0
Order By: Relevance
“…Zhang et al proposed a point-line vision-based inertial localization method based on the PL-VIO algorithm [35]. A bilateral filtering algorithm and SURF feature extraction algorithm were adopted, combined with the fast nearest neighbor algorithm for feature matching.…”
Section: Related Workmentioning
confidence: 99%
“…Zhang et al proposed a point-line vision-based inertial localization method based on the PL-VIO algorithm [35]. A bilateral filtering algorithm and SURF feature extraction algorithm were adopted, combined with the fast nearest neighbor algorithm for feature matching.…”
Section: Related Workmentioning
confidence: 99%
“…Compared with the single threshold set by experience in the paper [ 20 , 30 , 31 , 32 ], the threshold set in this paper is associated with the number of line segments extracted, image size and scene, which can more effectively adapt to the impact of different indoor scene changes.…”
Section: Point Line Feature Processingmentioning
confidence: 99%
“…In feature point-based methods, in order to make full use of environmental characteristic information and improve environmental adaptability, line features are added in [5,13,14,[20][21][22][23]. For example, PL-VIO [5] adds the reprojection error and a priori information into the back end's optimization based on the VINS-MONO theory.…”
Section: Related Workmentioning
confidence: 99%
“…However, their high time cost makes it hard to achieve real-time tracking. In Zhang et al's work [23], the authors adjust the internal parameters of LSD, such as the pyramid number, scale factor and minimum density threshold, to improve the extraction speed. It is true that the speed is improved a lot, but the extraction quality is difficult to guarantee, and these parameters may be affected by the image size.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation