| 摘要 |
An object pose recognition apparatus and method. The object pose recognition method includes acquiring first image data of an object to be recognized and 3-dimensional (3D) point cloud data of the first image data, and storing the first image data and the 3D point cloud data in a database, receiving input image data of the object photographed by a camera, extracting feature points from the stored first image data and the input image data, matching the stored 3D point cloud data and the input image data based on the extracted feature points and calculating a pose of the photographed object, and shifting the 3D point cloud data based on the calculated pose of the object, restoring second image data based on the shifted 3D point cloud data, and re-calculating the pose of the object using the restored second image data and the input image data. |
| 主权项 |
1. An object pose recognition method, comprising:
acquiring first image data of an object to be recognized and 3-dimensional (3D) point cloud data of the first image data, and storing the first image data and the 3D point cloud data in a database; after said acquiring,
receiving input image data of the object photographed by a camera,extracting, by a computer, feature points from the stored first image data and the input image data,matching, by a computer, the stored 3D point cloud data and the input image data based on the extracted feature points,calculating a pose of the photographed object based on said matching, the calculated pose including a rotation vector which is rotation information of the object and a translation vector which is location information of the object,shifting, by a computer, the 3D point cloud data based on the calculated pose by applying the rotation vector and the translation vector to the 3D point cloud data,projecting the shifted 3D point cloud data onto a normalized plane, to thereby provide shifted, normalized 3D point cloud data,restoring second image data based on the shifted, normalized 3D point cloud data, andre-calculating the pose using the restored second image data and the input image data.
|
