Simultaneous Localization and Mapping (SLAM) has used RGB camera as a prior choice of sensor traditionally. However, in dark or low-light conditions, the image quality of RGB cameras deteriorates greatly, making reliable attitude estimation difficult. In contrast, infrared cameras are not affected by changes of ambient light, making them a viable sensing alternative. In this paper, We propose a calibration method for infrared camera and IMU to achieve higher pose estimation accuracy under the conditions of low light environment and heat treatment. Meanwhile, we propose a system called I2-SLAM based on MSCKF that is suitable for fusion positioning of infrared camera and IMU. We test the performance of I2-SLAM in daytime and night scenes on the vehicle-mounted data set, and compare it with other VIO systems. In result, the fusion of the infrared camera and IMU in the night scene can achieve high accuracy.
I2-SLAM: Fusing Infrared Camera and IMU for Simultaneous Localization and Mapping
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 278 ; 2834-2844
18.03.2022
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
I2-SLAM: Fusing Infrared Camera and IMU for Simultaneous Localization and Mapping
British Library Conference Proceedings | 2022
|Map Management for Efficient Simultaneous Localization and Mapping (SLAM)
British Library Online Contents | 2002
|Indoor and outdoor rover with Simultaneous Localization And Mapping (SLAM)
BASE | 2011
|Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learning
Springer Verlag | 2023
|