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

A positioning method of engine cylinder block casting based on machine vision

A technology of engine cylinder and machine vision, applied in instruments, image analysis, image enhancement and other directions, can solve the problems of obtaining image shadows, rough casting surface, through hole deformation, etc., to avoid local distortion, heavy weight, and avoid shadows. Effect

Active Publication Date: 2020-11-03
JIANGSU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of large volume of casting cylinder, rough surface of casting, many shadows in acquired images, serious deformation of through holes, etc., the present invention uses the middle two through holes of cylinder casting as grabbing targets, and provides a method for large cylinder castings. A set of methods for identification and positioning, including acquisition of casting images, image preprocessing, image feature extraction, identification of regions of interest and positioning of regions of interest, serving the subsequent robot automatic loading and unloading system

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
  • A positioning method of engine cylinder block casting based on machine vision
  • A positioning method of engine cylinder block casting based on machine vision
  • A positioning method of engine cylinder block casting based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0033] Such as figure 1 As shown, the method of the present invention includes the following steps:

[0034] (1) Collect engine cylinder block images: the cylinder block has a large volume, rough surface, and the cylinder block itself has deep through holes. The images obtained by ordinary methods have a lot of shadows around the through holes, which are not conducive to the positioning of the through holes, such as Figure 4 Shown. Pass as figure 2 The visual positioning system shown selects the appropriate light source, lighting method, camera and lens to obtain the original image highlighting the grasping characteristics of the large casting cylinder. Specifically: a bar-type LED light source 4 is used for surface illumination of a larger detected object. The lighting method is double-sided low-angle lighting. The light source angle is adjusted by the light ...

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 machine vision-based engine cylinder block casting locating method. The method comprises the steps of obtaining a cylinder block image, processing the cylinder block image, identifying and locating a cylinder block, and the like. Two through holes in the middle of a cylinder block casting serve as capture targets, so that a locating error caused by camera distortion can be effectively avoided; for the relatively deep through holes of the cylinder block, strip-shaped light sources on two sides are adopted for lighting at a low angle, and a camera with the low resolution and the long focal distance is adopted to obtain an ideal initial image; for burrs and pits on the surface of the casting, a processing method suitable for the cylinder block image is proposed and comprises the steps of graying, binarization, color reversion processing, regional threshold segmentation, opening-closing operation and regional filling, an ideal image segmentation effect is achieved, and the through holes are smooth and non-sticking in edge and complete in shape; and for the specific shapes of the through holes, the circularity is taken as a judgment index, the regional centroid is taken as a locating object, and a simple locating method that meets the precision requirement is obtained.

Description

Technical field [0001] The invention belongs to the field of machine vision, and particularly relates to a method for identifying and positioning engine cylinder block castings. Background technique [0002] At present, in the post-processing processing line of castings, large castings, such as engine cylinders, often require manual loading and unloading and clamping, resulting in low efficiency and increased labor costs. Machine vision technology can improve the degree of automation of the production line, and can be used in workpiece loading and unloading, defect detection and visual measurement. It can not only reduce labor costs, but also replace humans in complex and dangerous industrial environments. The method of identifying and positioning the target workpiece varies with the change of the workpiece. [0003] Due to the large volume of the engine cylinder, the rough surface of the castings, the shadows of the acquired images, and the serious deformation of the through-hole...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/73
CPCG06T7/0004G06T2207/10004G06T2207/10024G06T2207/30164
Inventor 顾寄南丁卫尚正阳唐仕喜高国伟张丽鹏
Owner JIANGSU UNIV
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