A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features
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 SLA...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Drones |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-446X/6/1/23 |
_version_ | 1797494620435775488 |
---|---|
author | Tong Zhang Chunjiang Liu Jiaqi Li Minghui Pang Mingang Wang |
author_facet | Tong Zhang Chunjiang Liu Jiaqi Li Minghui Pang Mingang Wang |
author_sort | Tong Zhang |
collection | DOAJ |
description | 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 (FLANN) algorithms to improve the robustness of point feature extraction result. Secondly, we establish a minimum density threshold and length suppression parameter selection strategy of line feature, and take the geometric constraint line feature matching into consideration to improve the efficiency of processing line feature. And the parameters and biases of visual inertia are initialized based on maximum posterior estimation method. Finally, the simulation experiments are compared with the traditional tightly-coupled monocular visual–inertial odometry using point and line features (PL-VIO) algorithm. The simulation results demonstrate that the proposed an inertial SLAM method based on point-line vision for indoor weak texture and illumination can be effectively operated in real time, and its positioning accuracy is 22% higher on average and 40% higher in the scenario that illumination changes and blurred image. |
first_indexed | 2024-03-10T01:36:57Z |
format | Article |
id | doaj.art-ec63e8af2eed49019290851790d67a5c |
institution | Directory Open Access Journal |
issn | 2504-446X |
language | English |
last_indexed | 2024-03-10T01:36:57Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Drones |
spelling | doaj.art-ec63e8af2eed49019290851790d67a5c2023-11-23T13:31:46ZengMDPI AGDrones2504-446X2022-01-01612310.3390/drones6010023A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line FeaturesTong Zhang0Chunjiang Liu1Jiaqi Li2Minghui Pang3Mingang Wang4Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710072, ChinaSystem Engineering Institute of Sichuan Aerospace, Chengdu 610100, ChinaSchool of Astronautics, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Astronautics, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Astronautics, Northwestern Polytechnical University, Xi’an 710072, ChinaIn 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 (FLANN) algorithms to improve the robustness of point feature extraction result. Secondly, we establish a minimum density threshold and length suppression parameter selection strategy of line feature, and take the geometric constraint line feature matching into consideration to improve the efficiency of processing line feature. And the parameters and biases of visual inertia are initialized based on maximum posterior estimation method. Finally, the simulation experiments are compared with the traditional tightly-coupled monocular visual–inertial odometry using point and line features (PL-VIO) algorithm. The simulation results demonstrate that the proposed an inertial SLAM method based on point-line vision for indoor weak texture and illumination can be effectively operated in real time, and its positioning accuracy is 22% higher on average and 40% higher in the scenario that illumination changes and blurred image.https://www.mdpi.com/2504-446X/6/1/23simultaneous localization and mapping (SLAM)fast bilateral filteringSURF algorithmnearest-neighbor algorithmgeometric constraintsfeature extraction |
spellingShingle | Tong Zhang Chunjiang Liu Jiaqi Li Minghui Pang Mingang Wang A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features Drones simultaneous localization and mapping (SLAM) fast bilateral filtering SURF algorithm nearest-neighbor algorithm geometric constraints feature extraction |
title | A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features |
title_full | A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features |
title_fullStr | A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features |
title_full_unstemmed | A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features |
title_short | A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features |
title_sort | new visual inertial simultaneous localization and mapping slam algorithm based on point and line features |
topic | simultaneous localization and mapping (SLAM) fast bilateral filtering SURF algorithm nearest-neighbor algorithm geometric constraints feature extraction |
url | https://www.mdpi.com/2504-446X/6/1/23 |
work_keys_str_mv | AT tongzhang anewvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT chunjiangliu anewvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT jiaqili anewvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT minghuipang anewvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT mingangwang anewvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT tongzhang newvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT chunjiangliu newvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT jiaqili newvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT minghuipang newvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures AT mingangwang newvisualinertialsimultaneouslocalizationandmappingslamalgorithmbasedonpointandlinefeatures |