Object surface deformation feature extraction method based on line-scanning 3D point cloud

Abstract

The invention discloses a method for extracting object surface deformation features based on line scanning three-dimensional point cloud. Including the use of three-dimensional measurement sensors based on line structured light scanning for data collection, data preprocessing to obtain three-dimensional point cloud data on the surface of the object; eliminating the influence of abnormal data and texture on the extraction of the main profile of the section, and accurately obtaining the main profile of the object section; combined Deformation feature knowledge base, based on section extraction of deformation feature points to obtain binary images, based on sub-block images to initially locate deformation areas to obtain target shape sub-block sets; then perform morphological operations on deformation feature points in sub-block sets to generate trusted deformation areas ROC, and then use the geometric features of ROC to perform region growth and restore the target to ensure the integrity of the deformation region detection; finally, according to the predefined deformation characteristics, the deformation characteristic value of the deformation region on the surface of the object is counted, so as to accurately obtain the completeness of the deformation of the object attribute information.

Description

technical field [0001] The invention relates to the technical field of surface detection, in particular to the technical field of object deformation feature extraction methods. Background technique [0002] With the advancement of social science and technology, people's requirements for the quality of objects are getting higher and higher, even reaching the state of "nearly perfect". When an object is stressed, it will show mechanical properties such as deformation and failure. It is one of the important contents of material science to make the material serve within the failure limit range, and at the same time have better stability and economy. Due to production defects or wear and tear, various deformations (such as cracks, holes, road rutting, track bending, lining deformation, can deformation, pipe deformation, etc.) may appear on the surface of the object, which will affect the performance of the object and even cause safety accidents. Therefore, timely detection of ob...

AI Technical Summary

Problems solved by technology

This method can be used for fixed site monitoring where objects slowly deform. However, in aspects such as road defect detection, tunnel measurement, track defect detection, online chip weak defect detection, and cultural relic archaeology, etc., it is required to measure in a high-speed dynamic environment, and requires a The measurement can obtain a measurement section in the strict sense, that is, the points on the section are measured at the same attitude and at the same time, such as road rutting detection, the measurement width is at least 2000 mm, and the measurement resolution (points on the same section use intervals) at least reaches mm, the distance measurement accuracy reaches 0.01 mm, and the measurement frequency is above 10KHz, which is equivalent to measuring 200 million points per second. The existing laser three-dimensional radar measurement technology cannot meet the measurement requirements

Images