| Autor: |
LI Heng, YANG Yanzhu, LIU Junxian, YANG Xiao |
| Předmět: |
|
| Zdroj: |
Journal of Donghua University (Natural Science Edition); Feb2024, Vol. 50 Issue 1, p77-84, 8p |
| Abstrakt: |
A set of algorithms with high positioning accuracy and recognition stability is proposed to meet the requirements of accurate positioning and recognition of ring-code targets. A method based on concentric projection transformation to solve the circle center is proposed for the precise positioning of annular coded targets. In the recognition of coded targets, the ellipse is changed into a standard circle by affine transformation, and then the internal coded band is decoded to get its unique decoded value. The experimental results show that the average error of the circle center extraction method is 0.225 pixels with the ideal circle center, 0.501 pixels with the ellipse fitting to extract the outer circle center, and 0.294 pixels with the inner circle center, and its accuracy is improved by 122.05% and 30.26% respectively. The angle between the camera and the coding target needs to be controlled within 75°, when the angle is less than 75°, the recognition rate of the coding target can reach 100%. The study finds that the coded target recognition and positioning method meets the photogrammetry requirements and has practical significance because it is more accurate than the ellipse fitting algorithm. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
