A visual odometry method, device, apparatus and storage medium

Abstract

The application discloses a visual odometer method, device and equipment and a storage medium, and comprises the following steps: extracting line segment information contained in an image to be processed by using an LSD algorithm; screening a plurality of strong gradient line segments from the line segment information by a quadtree uniformization screening method based on a gradient intensity scoring principle; uniformly sampling each strong gradient line segment to obtain a plurality of sampling points; and obtaining a spatial point set by back projecting the sampling points to calculate the spatial point set covariance. The method uniformly processes the line segments detected by the LSD algorithm by using a quadtree, thereby solving the problem of a sharp increase in calculation amount caused by excessive line segment constraints in a structured scene. In the uniformization process, the average gradient intensity of the pixel points contained in the line segments is calculated, the line segments with strong linear constraints are screened for the point-line model constructed by the algorithm, and the robustness of the algorithm brought by the introduction of the linear constraints is improved.

Images