Typical parts recognition and location method based on kinect

A positioning method and technology for parts, applied in computer parts, character and pattern recognition, instruments, etc., can solve the problem of difficult to directly determine the spatial position of parts, and achieve the effect of low cost, fast identification and positioning

Active Publication Date: 2019-09-06
SHENYANG POLYTECHNIC UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problem that image recognition methods are often used in the existing parts recognition, it is difficult to directly determine the spatial position of the parts, the present invention provides a typical parts recognition and positioning method based on Kinect, using the Kinect device It can provide the depth image and color image of the target, and determine the spatial position of the component in the process of component recognition

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
  • Typical parts recognition and location method based on kinect
  • Typical parts recognition and location method based on kinect
  • Typical parts recognition and location method based on kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The invention relates to a Kinect-based typical component recognition and positioning method, which is a convenient and effective component recognition and positioning method. First, the affine transformation matrix between the color and depth images obtained by the Kinect sensor is used to extract the affine transformation matrix between the two to realize the correction of the color image; then the correlation coefficient matching method is used to realize the parts recognition of the corrected color image; finally, the color and depth images are used Position the components according to the corresponding relationship.

[0035] Using the Kinect sensor to identify and locate parts, the specific steps are:

[0036] (1) Correct the image: the depth image obtained by the Kinect device is inconsistent with the size of the object in the color image, and the characters in the color image are too small, so the color image is corrected by using affine transformation, so that 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 relates to a Kinect-based typical component identification and positioning method. First, the affine transformation matrix between the color and depth images obtained by the Kinect sensor is used to extract the affine transformation matrix between the two to realize the correction of the color image; and then the correlation coefficient matching method is used to realize the correction. The final color image component recognition; finally use the corresponding relationship between color and depth image to locate the component. The invention can not only identify typical components, but also determine the spatial position of the components.

Description

[0001] Technical field: [0002] The invention relates to a method for identifying and locating typical parts, in particular to a method for identifying and locating typical parts based on Kinect. [0003] Background technique: [0004] In recent years, with its advantages of non-contact, wide spectral response range, positioning, measurement and defect detection, machine vision has been widely used in military affairs, crop quality inspection, face recognition, fingerprint recognition, invoice number recognition, and medical image detection. Wide range of applications. [0005] In automated disassembly, machine vision is a more feasible technical method to automatically obtain feature information and feature parameters of parts. For some high-demand, high-load repetitive and intelligent tasks, such as subtle defect detection and component measurement, it is difficult for human eyes to complete continuously and stably. Machine vision can complete detection tasks efficiently an...

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): G06K9/32G06K9/46G06K9/62
CPCG06V10/245G06V10/462G06V10/751
Inventor 张志佳魏信张云飞贾梦思
Owner SHENYANG POLYTECHNIC UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products