Abstract
The initialization process has a great effect on the performance of the monocular visual inertial simultaneous localization and mapping (VI‐SLAM) system. The initial estimation is usually solved by least squares such as the Gauss‐Newton (G‐N) algorithm, but the large iteration increment might lead to the slow convergence or even divergence. In order to solve this problem, an improved iterative strategy for initial estimation is proposed. The methodology of our initialization can be divided into four steps: Firstly, the pure visual ORB‐SLAM model is utilized to make all variables observable. Secondly, the IMU preintegration technology is adopted for IMU‐camera frequency alignment at the same time with key frame generation. Thirdly, an improved iterative strategy which is based on the trust region is introduced for the gyroscope bias estimation as well as the gravity direction is refined. Finally, the accelerometer bias and visual scale are estimated on the basis of previous estimations. Experimental results on the public datasets show that the estimation of initial values can be converged faster, as well as the velocity and pose of sensor suite can be estimated more accurately than the original method.
Highlights
With the development of artificial intelligent (AI), the monocular visual inertial simultaneous localization and mapping (VI-SLAM) technology has become an active research topic in the robotics and computer vision communities
The results show that the estimation of initial values can be converged in a faster speed, as well as the velocity and poses of a sensor suite can be estimated more accurately than the original method
Where f k = f ðxkÞ is the objective function, Equation (10) is the approximate model of f k around the current point xk, gk = ∇f ðxkÞ is the gradient of f k, Δk represents the radius of the trust region, γ = xk+1 − xk, Γk is the class of path, Gk = ∇2f ðxkÞ is the Hessian matrix of f ðxkÞ, and k:k denotes the
Summary
With the development of artificial intelligent (AI), the monocular visual inertial simultaneous localization and mapping (VI-SLAM) technology has become an active research topic in the robotics and computer vision communities. (ii) The disjoint method is first introduced by Murartal and Tardos [16] and latter adapted by Qin and Shen and Yang and Shen [20, 21] with a good performance In both cases, the parameters of IMU are estimated in different steps by solving a series of linear formulas with the least-squares method such as Gauss-Newton (GN) and Levenberg-Marquardt (L-M) [22, 23]. Levenberg [26] and Marquardt [27] suggest to use a damped G-N method, in which the size and direction of the iterative step are influenced by the damped parameter It makes this method without a specific line search which guarantees the global convergence performance [28]. The contribution of this paper is that an improved iterative strategy is proposed based on the trust region method to speed up the initial estimation.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
