Object pose measurement method and device and storage medium

Abstract

The invention discloses an object pose measurement method and device and a storage medium, the method comprises an offline modeling stage and an online matching stage, and the offline modeling stage is to perform feature modeling on an object three-dimensional model and store the feature modeling for subsequent scene object pose measurement; in the online matching stage, object pose measurement iscarried out on a given scene RGB-D image. Ihe invention provides an efficient model sampling strategy, which can reduce the subsequent operation amount; enough object surface change information can be reserved; the distance range when the point pair characteristics are calculated is limited, and the matching interference of excessive background point clouds is reduced; a quantitative expansion method is provided, and the influence of noise on point-to-feature calculation offset is reduced; edge information is extracted from a color image, candidate object poses are screened, ICP registrationis carried out, the measurement precision is improved, and therefore the scene recognition rate under the conditions of shielding, gathering, stacking and the like is more accurate. The method is widely applied to the field of three-dimensional computer vision.

Description

technical field [0001] The invention relates to the field of three-dimensional computer vision, in particular to an object pose measurement method, device and storage medium. Background technique [0002] In recent years, with the development of industrial upgrading, manufacturing automation has become an important driver of economic development, and the automatic sorting of objects by robots in manufacturing is an important manifestation of manufacturing automation. The pose of an object in three-dimensional space is an important reference for robots to identify, locate, grasp, and manipulate objects. The process of obtaining the pose of an object is called object 6D pose measurement, which is an important problem in the field of 3D computer vision. An object is transformed from A in a certain reference coordinate system to B through rotation and translation. This rotation and translation process is recorded as T AB ,T AB It consists of 3 translations of x, y, z and 3 ro...

AI Technical Summary

Problems solved by technology

[0004] Existing PPF-based methods have (1) the disadvantage of oversimplification of the sampling method; when the model is sampled according to a grid of a certain size, the The point cloud is simply averaged. When there is a large change in the angle between the normal vectors of the point cloud in the grid, the sampling method will lose more key information of surface changes, reducing the expression of model surface difference information. ability

(2) Disadvantage of large amount of calculation; after the model point cloud is sampled, it is necessary to perform feature calculation on all point pairs, but in the actual scene, the part of the object under any viewing angle is often smaller than the model diameter (the model diameter refers to the border surrounding the model Diagonal length), there is computational redundancy

(3) The lack of robustness to point cloud noise; the point cloud captured by the camera itself has noise, which will cause a certain deviation between the position and normal vector of the point cloud, and the calculated scene features will have a certain deviation. method cannot compensate for noise bias

(4) The shortcomings of color-depth (RGB-D) images cannot be comprehensively utilized; this method only operates on depth images, only uses the three-dimensional space information of the scene, and cannot obtain some information from color images to assist attitude measurement

Images