3D Object Pose Parameters Estimation Method and Vision Equipment

Abstract

The invention relates to a three-dimensional object pose parameter estimation method and visual equipment, and the visual equipment can execute the method, and the method comprises the steps: obtaining a pose parameter determined based on a previous frame of image of a three-dimensional object, and taking the pose parameter as an initial pose parameter for determining a pose parameter corresponding to a current frame of image; projecting the three-dimensional space straight line segment of the three-dimensional object to a two-dimensional image plane based on the initial pose parameter to obtain a projection straight line segment of the three-dimensional space straight line segment on the two-dimensional image plane; determining an image straight line segment closest to the projection straight line segment on the two-dimensional image plane, and determining a distance error between the projection straight line segment and the closest image straight line segment; judging whether the distance error meets a preset condition or not; if not, determining a new pose parameter based on the distance error, and taking the new pose parameter as an initial pose parameter; and if yes, taking the initial pose parameter as the pose parameter of the current frame of image. According to the invention, the pose parameter estimation of the object with less texture is realized.

Description

technical field [0001] The present application relates to the field of visual equipment, in particular to a method for estimating pose parameters of a three-dimensional object and a visual equipment. Background technique [0002] For the pose estimation of 3D objects with sparse textures, sparse point features affect the accuracy of pose estimation, and relatively stable straight line features are beneficial to pose estimation. The core problem of using straight line features for pose estimation is the matching of 2D and 3D straight line features. Since there is too little description information available for 3D straight lines, it is difficult to directly complete the matching of 2D and 3D straight line features. Generally, the reference frame of the known two-dimensional and three-dimensional straight line correspondence is used to simplify the feature matching of two-dimensional and two-dimensional image straight lines. [0003] At present, line feature matching mainly f...

AI Technical Summary

Problems solved by technology

The core problem of using straight line features for pose estimation is the matching of 2D and 3D straight line features. Since there is too little description information available for 3D straight lines, it is difficult to directly complete the matching of 2D and 3D straight line features.

One is that the reference frames that need to mark the corresponding relationship between 2D and 3D offline are large and cumbersome; the other is that the linear features of the image need to be accurately extracted, but noise, blur and other factors will affect the integrity of the linear features

[0005] From the above analysis, it can be seen that the indirect matching method realizes the pose estimation of texture-sparse objects, and relies on historical images to label reference frames, and the workload of offline labeling is large.

Images