1. Nonlinear back-end optimization method for VSLAM with multi-convex combined maximum correntropy criterion.
- Author
-
Cheng, Lan, Wang, Ting, Xu, Xinying, Yan, Gaowei, Ren, Mifeng, and Zhang, Zhe
- Subjects
COST functions ,RANDOM noise theory ,PROBLEM solving - Abstract
Back-end optimization plays a key role in eliminating the accumulated error in Visual Simultaneous Localization And Mapping (VSLAM). Existing back-end optimization methods are usually premised on the Gaussian noise assumption which does not always hold true due to the non-convex nature of the image and the fact that non-Gaussian noises are often encountered in real scenes. In view of this, we propose a back-end optimization method based on Multi-Convex combined Maximum Correntropy Criterion (MCMCC). A MCMCC-based cost function is first tailored for nonlinear back-end optimization in the context of VSLAM and the optimization problem is solved through Levenberg–Marquardt algorithm iteratively. Then, the proposed method is applied to ORB-SLAM3 to test its performance on public indoor and outdoor datasets. The real time performance is also validated using a RaceBot platform in real indoor and outdoor environments. In addition, the reprojection error is statistically analyzed to demonstrate the non-Gaussian characteristics in the back-end optimization process. Finally, the suggestion parameters are also provided through experiments for further study. • The MCMCC-based cost function for VSLAM back-end optimization is designed and the optimization problem is then solved through Levenberg-Marquardt method iteratively. To our knowledge, this is the first time a ITL-based cost function is considered in nonlinear back-end optimization. • The proposed method is implemented in the visual mode in ORB-SLAM3 and a comprehensive analysis is performed by comparing the proposed method with other widely used robust kernel function-based methods in the context of VSLAM on EuRoC, TUM and KITTI datasets. In addition, the method is also tested in real environment. • The reprojection error in back-end is analyzed from the prospective of stochastic statistics to provide an insight on the back-end problem in non-Gaussian setting in VSLAM. • The suggestion parameters are provided as guidance for both indoor applications and outdoor applications. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF