Detecting and identifying method for annular coding mark point

Abstract

The invention belongs to the field of close-range photogrammetry and relates to a detecting and identifying method for an annular coding mark point. The method includes that first, canny edge detection is conducted on a collected image, an outline centroid is closed through a series of limiting conditions and calculation, and noise and non-coding mark points are filtered; then least square ellipse fitting is adopted, coding mark point location is conducted, an ellipse fitting error is combined to judge a partition coding mark point outline, and the outline is filled; finally, ALPC transformation for transforming a local concentric ellipse into parallel straight lines is provided, the ALPC transformation is conducted on the partitioned coding mark point, and transformed image characteristics are used for decoding. By means of the detecting and identifying method, location of the coding mark point can reach a sub pixel level, local shape characteristics of a concentric ellipse are transformed into shape characteristics of parallel straight lines which are easy to detect and calculate, coding mark point identifying speed is improved, and effects of an included angle of a camera optical axis and a coding mark point normal on the coding mark point identifying accuracy can be reduced.

Description

technical field [0001] The invention relates to a method for detecting and identifying ring-shaped coding marking points, and more specifically, the invention relates to a method for detecting and identifying ring-shaped coding marking points for full-scale splicing of large workpieces. Background technique [0002] In machine 3D vision measurement, for images collected from large fields of view and from multiple angles, the accuracy of image matching is an important link to improve the accuracy of 3D data stitching. In the process of image matching, it is required to accurately detect and identify the corresponding points of the image. However, for high-resolution large field of view images, it is very difficult to identify the corresponding points of the two images, which requires the use of a marker point with a unique code value, which is artificially pasted on the key feature points of the measured object to take pictures , to identify the feature points of the two ima...

AI Technical Summary

Problems solved by technology

The detection and identification of coded markers is one of the difficulties in close-range photogrammetry. At present, the researches in this area at home and abroad mainly include (1) Forbes K proposed the arc segmentation method when using coded markers for calibration in 2002. This method It is easy to cause uneven segmentation, which affects the final decoding result

(2)Thomas Doring et al. applied Forbes K twelve-bit coding markers in scanner calibration, and increased the number of samples sampled by using the coding ring segmentation method, but at the same time it will increase the calculation cost, and this method is affected by the photographic The angle has a great influence; (3) Liang Jin, Liu Jianxin and Hu Hao from Xi'an Jiaotong University applied ring-shaped coding markers to camera calibration, and their decoding method has higher requirements on the shooting angle and environment of the coding markers

(4) Wang Man and Ye Zhenglin used morphological operators for recognition, but this method is greatly affected by the camera angle, and the recognition effect on images with complex backgrounds is poor

Images