公开(公告)号：US20210192271A1

公开(公告)日：2021-06-24

申请号：US16725357

申请日：2019-12-23

Applicant: Beijing Institute of Technology

Inventor： Qiang Huang ,  Xiaopeng Chen ,  Wei Cheng ,  Zhangguo Yu ,  Xuechao Chen ,  Junyao Gao ,  Yang Xu

IPC: G06K9/62 ,  G06T1/00 ,  G06T3/00 ,  G06K9/46

Abstract: The present application provides a method and apparatus for pose planar constraining on the basis of planar feature extraction, wherein the method includes: inputting the acquired RGB color image and point cloud image into spatial transformation network to obtain two-dimensional and three-dimensional affine transformation matrixes; extracting the planar features of the transformed two-dimensional affine transformation matrix and three-dimensional affine transformation matrix; inputting the acquired planar features into the decoder and obtain the pixel classification of the planar features; clustering the vectors corresponding to the planar pixels to obtain the segmentation result of the planar sample; using planar fitted by the segmentation result to make planar constraint to the pose calculated by vision algorithm. The application combines RGB-D information to perform plane extraction, and designs a new spatial transformation network to transform two-dimensional color image and three-dimensional point cloud image.