Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion
To achieve a high precision estimation of indoor robot motion, a tightly coupled RGB-D visual-inertial SLAM system is proposed herein based on multiple features. Most of the traditional visual SLAM methods only rely on points for feature matching and they often underperform in low textured scenes. B...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4666 |
| _version_ | 1797557144100274176 |
|---|---|
| author | Xiongwei Zhao Cunxiao Miao He Zhang |
| author_facet | Xiongwei Zhao Cunxiao Miao He Zhang |
| author_sort | Xiongwei Zhao |
| collection | DOAJ |
| description | To achieve a high precision estimation of indoor robot motion, a tightly coupled RGB-D visual-inertial SLAM system is proposed herein based on multiple features. Most of the traditional visual SLAM methods only rely on points for feature matching and they often underperform in low textured scenes. Besides point features, line segments can also provide geometrical structure information of the environment. This paper utilized both points and lines in low-textured scenes to increase the robustness of RGB-D SLAM system. In addition, we implemented a fast initialization process based on the RGB-D camera to improve the real-time performance of the proposed system and designed a new backend nonlinear optimization framework. By minimizing the cost function formed by the pre-integrated IMU residuals and re-projection errors of points and lines in sliding windows, the state vector is optimized. The experiments evaluated on public datasets show that our system achieves higher accuracy and robustness on trajectories and in pose estimation compared with several state-of-the-art visual SLAM systems. |
| first_indexed | 2024-03-10T17:13:11Z |
| format | Article |
| id | doaj.art-659a7d4d9ab648d2a6e6581aa9bd1c03 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:13:11Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-659a7d4d9ab648d2a6e6581aa9bd1c032023-11-20T10:36:18ZengMDPI AGSensors1424-82202020-08-012017466610.3390/s20174666Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial FusionXiongwei Zhao0Cunxiao Miao1He Zhang2School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaTo achieve a high precision estimation of indoor robot motion, a tightly coupled RGB-D visual-inertial SLAM system is proposed herein based on multiple features. Most of the traditional visual SLAM methods only rely on points for feature matching and they often underperform in low textured scenes. Besides point features, line segments can also provide geometrical structure information of the environment. This paper utilized both points and lines in low-textured scenes to increase the robustness of RGB-D SLAM system. In addition, we implemented a fast initialization process based on the RGB-D camera to improve the real-time performance of the proposed system and designed a new backend nonlinear optimization framework. By minimizing the cost function formed by the pre-integrated IMU residuals and re-projection errors of points and lines in sliding windows, the state vector is optimized. The experiments evaluated on public datasets show that our system achieves higher accuracy and robustness on trajectories and in pose estimation compared with several state-of-the-art visual SLAM systems.https://www.mdpi.com/1424-8220/20/17/4666nonlinear optimizationmultiple featuresmotion estimationRGB-D visual-inertial odometrysliding windows |
| spellingShingle | Xiongwei Zhao Cunxiao Miao He Zhang Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion Sensors nonlinear optimization multiple features motion estimation RGB-D visual-inertial odometry sliding windows |
| title | Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion |
| title_full | Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion |
| title_fullStr | Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion |
| title_full_unstemmed | Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion |
| title_short | Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion |
| title_sort | multi feature nonlinear optimization motion estimation based on rgb d and inertial fusion |
| topic | nonlinear optimization multiple features motion estimation RGB-D visual-inertial odometry sliding windows |
| url | https://www.mdpi.com/1424-8220/20/17/4666 |
| work_keys_str_mv | AT xiongweizhao multifeaturenonlinearoptimizationmotionestimationbasedonrgbdandinertialfusion AT cunxiaomiao multifeaturenonlinearoptimizationmotionestimationbasedonrgbdandinertialfusion AT hezhang multifeaturenonlinearoptimizationmotionestimationbasedonrgbdandinertialfusion |