A method for recognizing and locating geometrical marks by using generalized features

Abstract

The invention belongs to the technical field of photogrammetry and computer vision, and discloses a method for recognizing and locating geometrical marks by using generalized features, which generatestraining data sets for corresponding geometrical graphics objects by using a three-dimensional rendering engine, trains the geometrical marks in images through a depth learning network, and realizesrecognition of the geometrical marks in images. The common features such as contour extraction are processed, and then the dimension-reduced ICP algorithm is used to realize the registration in the discretized state, and the transformation parameters are obtained, so as to obtain the precise location of the geometrical markers. The invention realizes quantitative description of deformation of geometric identification primitive in image and obtains satisfactory positioning accuracy. For common geometrical identification, it does not need to customize the specific algorithm, but directly throughthe above process, to achieve accurate positioning of the identification, thus simplifying the manual identification extraction and positioning process, forming a common way.

Description

technical field [0001] The invention belongs to the technical field of photogrammetry and computer vision, and in particular relates to a method for recognizing and locating geometric marks by using generalized features. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] In the field of photogrammetry and computer vision, geometric mark recognition and positioning is a commonly used technical link in algorithms such as calibration, control point extraction, and code recognition. In general, for the geometric identification of a certain type of shape, it is necessary to design a targeted algorithm, compile a program for identification, or directly locate the geometric identification manually. [0004] In summary, the problems in the prior art are: [0005] (1) At present, the method of deep learning has not been used for the recognition of geometric marks, and a specific recognition algorithm is still d...

AI Technical Summary

Problems solved by technology

[0005] (1) At present, the method of deep learning has not been used for the recognition of geometric marks, and it is still to design specific recognition algorithms for specific geometric marks

[0006] (2) In the positioning process of the geometric mark, its common features have not been effectively utilized, and it is still necessary to rely on the unique features of the specific geometric mark

[0007] (3) The identification and positioning process of the entire geometric mark still needs manual intervention, and the efficiency needs to be improved

[0011] The main difficulty in solving the problem in the prior art lies in the inability to use the generalization method to accurately locate the geometric mark

Images