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

Conveyor belt surface object image splicing method based on SIFT features

A technology of object images and conveyor belts, which is applied in the field of image processing, can solve problems such as pixel loss, time-consuming, and inability to meet industrial production inspection requirements, and achieve the effect of increasing calculation speed and reducing calculation amount

Active Publication Date: 2021-06-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method takes a long time, and it is easy to cause the loss of pixels, which cannot meet the detection requirements in industrial production

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
  • Conveyor belt surface object image splicing method based on SIFT features
  • Conveyor belt surface object image splicing method based on SIFT features
  • Conveyor belt surface object image splicing method based on SIFT features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] The preferred embodiment of the present invention provides a surface object image stitching method based on a SIFT feature, the method comprising: when the movement of the object is tested on the conveyor belt, the same camera is tested for the object to continuously shoot a multi-screening picture, the splicing method includes The following steps, through the speed of the conveyor, the coincident region of the adjacent two detection picture; provide feedback information to the conveyor belt, to adjust the size of the overlap region by adjusting the speed of the conveyor belt.

[0056] The extraction of the feature point is performed by the SIFT algorithm, and matches the knn algorithm to obtain a matching set m, and the bad point is removed for m using the coordinate consistency; seeking a translational distance, using a translation variable coefficient method Fusion, complete image stitching, overall steps figure 1 Indicated.

[0057] Among them, in step 1, the acquisitio...

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 conveyor belt surface object image splicing method based on SIFT features, and the method comprises the steps: enabling a same camera to continuously shoot a plurality of detected images of a to-be-detected object when the to-be-detected object moves on a conveyor belt, and obtaining an overlapping region of two adjacent detected images through the speed of the conveyor belt; providing the feedback information for the conveying belt, and adjusting the size of the overlapping area by adjusting the speed of the conveying belt; extracting feature points from the overlapped area by using an SIFT algorithm, matching by using a KNN algorithm to obtain a matching set M, and removing dead pixels from the M by using a coordinate consistency method to complete image registration; solving a translation distance between two adjacent detected pictures, and fusing the pictures by using a translation variable coefficient method to complete image splicing. According to the method, the calculated amount of SIFT is reduced, feedback is provided to the conveyor belt to ensure the size of an overlapping area, the calculation speed is increased, the number of calculated feature points is ensured, and the characteristic that coordinates of an object in the direction perpendicular to the speed are not changed in the moving process of the object on the conveyor belt is achieved.

Description

Technical field [0001] The present invention belongs to the field of image processing, and is related to a surface object image stitching method based on a SIFT feature. Background technique [0002] Image splicing techniques are panoramic view techniques that spliced ​​a set of images with coincidence information into a wide viewing angle, large scale. The image stitching technology is widely used, and it is generally used in military, medical, industrial processing and other fields. [0003] In the field of industrial processing, the testing of quality problems with the surface of the processed object has always been research hotspots in the field of image processing. As the industrial level continues to improve the surface quality of the object, the traditional machine visual detection method can only improve the camera's pixels to improve the accuracy of the test, which greatly increases the cost of surface quality testing of objects. The image stitching technology is very go...

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): G06T3/40G06T7/30G06K9/62G06K9/46
CPCG06T3/4038G06T7/30G06T2207/10016G06V10/462G06F18/241Y02P90/30
Inventor 徐尚龙颛孙壮志叶鑫龙郑师晨
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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