Anti-highlight interference engineering survey mark extraction method based on color-edge fusion feature growth

Abstract

The invention discloses an anti-highlight interference engineering survey mark extraction method based on color-edge fusion feature growth. The method comprises the following steps: arranging a survey mark of a selected feature at a target designated part; training a target detection software model capable of identifying a specified target object; carrying out target detection on an image, and extracting a Region of Interest (ROI) region in the image; in combination with a digital image processing method, performing target primary extraction on the extracted ROI based on color-edge features to complete image preprocessing; performing edge detection on the image obtained after preprocessing according to a Canny edge detection algorithm, and selecting a part of pixel points in an edge contour as candidate seed points according to a specified rule; taking the candidate seed point as a starting point, carrying out region growth according to a growth rule, and merging the pixel points according with the growth rule into the growth region until no pixel points according with the growth rule are merged into the growth region; and finally, further extracting geometric feature information and target feature point information based on the growth region.

Description

technical field [0001] The invention relates to the fields of machine vision technology, digital image processing, and engineering photogrammetry, and relates to an anti-highlight interference engineering measurement mark extraction method based on color-edge fusion feature growth, which realizes target segmentation and recognition of measurement marks in images, and has strong anti-interference ability . Background technique [0002] Engineering photogrammetry is the theory and technology of studying the photography of various targets and objects to determine their shape, size and geometric position. In order to solve the spatial information of the target object, it is often necessary to perform target segmentation and feature extraction on the target image, so as to obtain the solution parameters of the solution model. [0003] Image segmentation is the process of extracting the specified target or meaningful features and regions in the image. It is the basis of target fe...

AI Technical Summary

Problems solved by technology

When the object is in a high-light environment or the reflected light on the object surface contains specular reflection components, the color and texture features of the object surface will be weakened or even disappeared, which seriously affects the results of image segmentation

Images