公开(公告)号：US20230070287A1

公开(公告)日：2023-03-09

申请号：US17988096

申请日：2022-11-16

Applicant: Guangdong University of Technology

Inventor： Jian GAO ,  Yuanyang WEI ,  Lanyu ZHANG ,  Yongbin ZHONG ,  Haixiang DENG ,  Yun CHEN ,  Xin CHEN

IPC: G06T7/70 ,  G06T9/00

Abstract: A real-time pose measurement method of a planar coding target for a vision system. The planar coding target includes a plurality of coding elements, a coding block, a coding template, a minimum identification unit pattern and a coding pattern. Each coding element has a unique coding value, and serial numbers of the coding elements are different from each other. The coding block includes four coding elements that are distributed in the same rectangle ABCD and do not overlap with each other. A center of the coding block is an intersection point O of two diagonals of the rectangle ABCD. A coding value of the coding block is associated with coding values of the four coding elements contained therein.

公开(公告)号：US20210081827A1

公开(公告)日：2021-03-18

申请号：US17088577

申请日：2020-11-03

Applicant: GUANGDONG UNIVERSITY OF TECHNOLOGY

Inventor： Jian GAO ,  Ruirong LUO ,  Lanyu ZHANG ,  Haixiang DENG ,  Xin CHEN

IPC: G06N5/04 ,  G06K9/62 ,  G06T5/00

Abstract: A fast clustering algorithm of kernel fuzzy C-means integrated with spatial constraints, including (1) applying the illumination processing algorithm, the preprocessed image affected by illumination is constructed; (2) After step (1), the original image and preprocessed image are mapped to the feature space using Gaussian kernel to cluster and segment. Providing a defect segmentation method for fluorescent glue which is robust to illumination to process and calculate the illuminated image, so as to complete the detection of foreign matters, bubbles and discoloration defects of fluorescent glue in lighting products. The disclosure provides a fast clustering algorithm of kernel fuzzy C-means integrated with spatial constraints. The image is mapped into the feature space, and the objective function of kernel fuzzy C-means clustering is optimized by using the spatial relationship of pixels, so that the clustering process has segmentation robustness to the gray value change of similar pixels caused by environmental changes.