Open AccessFast target recognition and location based on graph model and point cloud model
Author(s) -
Yun-Tao Zhao,
Jiaming Hu,
Li Weigang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1861/1/012065
Subject(s) - point cloud , computer science , artificial intelligence , graph , transformation matrix , computer vision , cloud computing , point (geometry) , coordinate system , algorithm , pattern recognition (psychology) , mathematics , theoretical computer science , geometry , physics , kinematics , classical mechanics , operating system
When using the point cloud model to identify and locate the target, there are some problems, such as low recognition accuracy and slow positioning speed. In order to solve these problems, this paper proposes a fast target recognition and location method based on point cloud model and graph model, which combines the characteristics of graph model processing speed, algorithm efficiency and recognition accuracy. Through the analysis of the characteristics of the target graph model, the pixel coordinates and rotation angle of the target grabbing points are calculated. After the transformation matrix and mapping relationship, the spatial coordinates of the point cloud model are obtained. The efficiency and accuracy of the method are verified by the recognition and positioning experiments on the robot target grabbing platform.