Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Glue point three-dimensional reconstruction method based on uncalibrated photometric stereoscopic vision

A photometric three-dimensional, glue point technology, applied in the field of three-dimensional measurement, can solve the problems of low efficiency, complex light source calibration, environmental restrictions and so on

Inactive Publication Date: 2021-08-31
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the weighing method, if the weight is directly weighed, it will be submerged because the mass of the glue dot is much smaller than the mass of the substrate. In fact, it can only be measured indirectly by spotting the colloid on a microslide, which is very inefficient and it is not easy to see the specific shape of the glue dot.
The two-dimensional visual measurement method is to evaluate the consistency of the glue distribution through the online measurement of the glue point area. Although its efficiency is high, this method is based on the assumption that the glue point height is consistent or the glue point is not deformed.
However, in the actual application process, the calibration of the light source is more complicated and has certain restrictions on the environment, so the uncalibrated photometric stereo technology appears, that is, to reconstruct the surface of the object in the case of an unknown light source.
There are many existing methods to solve uncalibrated photometric stereo technology, but they all assume that the object is a Lambertian body, or directly remove the image highlights for research.
Not suitable for 3D reconstruction of glue dots

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Glue point three-dimensional reconstruction method based on uncalibrated photometric stereoscopic vision
  • Glue point three-dimensional reconstruction method based on uncalibrated photometric stereoscopic vision
  • Glue point three-dimensional reconstruction method based on uncalibrated photometric stereoscopic vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] This method is experimented on real objects to achieve the purpose of three-dimensional reconstruction.

[0081] Step 1, obtain object pictures under multiple light sources, such as Figure three One of these is shown. The image source is DiLiGenT database.

[0082] Step 2, preprocess the image set and perform batch separation, and separate it into specular reflection image set I 1 and Diffuse Image Set I 2 . Figure 4 and Figure 5 respectively Figure 1 Separated diffuse and specular reflection images.

[0083] Step three, for I 2 Perform SVD decomposition to initialize GBR parameters, find the LDR gray maximum value set, and calculate the reflection maximum value function to solve the candidate set P of GBR parameters μ, ν, λ. then to I 1 Calculate the low-rank structure of BRDF slices and solve the minimum value of the objective function. The obtained parameter values ​​of μ, ν, and λ are the parameter values ​​of the final GBR transformation matrix, and t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a glue point three-dimensional reconstruction method based on uncalibrated photometric stereoscopic vision. Aiming at the three-dimensional reconstruction problem of the glue point, an uncalibrated photometric stereoscopic vision solving method is provided, and a general bas-relief (GBR) parameter is solved by combining a diffuse reflection-based method and a mirror reflection-based method. The glue point three-dimensional reconstruction method comprises the following steps: carrying out picture shooting on a glue point under multiple light sources, carrying out diffuse reflection image and mirror reflection image separation on an image of the glue point, finding a Lambert reflection maximum value of the diffuse reflection image, considering half-vector symmetry in mirror reflection by using a bidirectional reflection distribution function (BRDF), finally solving a parameter value of GBR by combining the two images, and recovering a surface normal and reconstructing a three-dimensional surface through integration. According to the method, the three-dimensional reconstruction problem of the glue points is solved by adopting an integral method, so that the reconstruction result has higher accuracy. The method is suitable for a precision assembly system which has high requirements on the gluing process and strict precision requirements on the assembly performance.

Description

technical field [0001] The invention belongs to the field of three-dimensional measurement, in particular to a method for three-dimensional reconstruction of glue dots based on uncalibrated photometric stereo vision. Background technique [0002] Glue dispensing technology is a very important technology in the advanced electronics manufacturing industry, and it is widely used in the field of micro-assembly technology and integrated circuit equipment. In the dispensing process, the amount of glue dispensed and the three-dimensional shape of the glue point have an important impact on the assembly performance of the parts to be bonded. Accurate measurement of glue points is of great significance to micro-assembly technology. Existing methods for measuring the amount of glue dispensed can be divided into weighing methods and two-dimensional visual online measurement methods. For the weighing method, if the weight is directly weighed, it will be submerged because the mass of th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): B05C5/02B05C11/10
CPCB05C5/02B05C11/10
Inventor 张之敬王磊朱东升金鑫李奕豪
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products