Improved VINS method for complex illumination environment

Abstract

The invention discloses an improved VINS method for a complex illumination environment, and the method comprises the steps: estimating a camera response function through an initialization process, enabling the process to carry out the modeling and calibration of a camera imaging process, disassembling a light flow process from the relation between a pose and gray scale into the relation between the pose and exposure parameters and the irradiance through the function, and carrying out the recognition of the exposure parameters and the irradiance. Therefore, the influence of the exposure parameters on pose estimation can be estimated in the process. According to the method, the change of camera parameters caused by complex illumination can be integrated into the overall VINS system pose estimation, so that the system adapts to the environment. And finally, the feasibility and effectiveness of the algorithm are proved by comparing the algorithm provided by the invention with the traditional VIINS algorithm through a real experiment, so that the realization of the improved SLAM system under the complex illumination environment based on the traditional VINS algorithm is completed.

Description

technical field [0001] Aiming at the problem of inaccurate pose estimation of the traditional VINS algorithm in complex lighting environments, the present invention designs an improved VINS system based on the traditional VINS system which is more robust to complex lighting environments. By estimating the imaging response function of the camera, this method further splits the gray level error in traditional optical flow into irradiance error, and at the same time adds the exposure parameters in the process of collecting the real scene in reality into visual information by the camera into the visual data association process. , performing data association and estimating exposure information at the same time, which improves the quality of visual signals in complex lighting environments, thus making the overall improved VINS system more robust in complex lighting environments. Background technique [0002] Navigation is the process of correctly guiding the carrier along the pred...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing system is not suitable for the complex lighting environment, the present invention estimates and compensates the gray level change, and improves the robustness of the system carried on the body in this environment

Many researchers have proposed photometric calibration algorithms to solve this problem

However, the current photometric calibration algorithm is mainly designed for the direct method. Due to the simultaneous calculation of the exposure time and the irradiance of each pixel, the optimization vector is very large, resulting in a slightly slower calculation speed of the exposure time.

Images