Product morphology detecting method based on Kinect

A shape detection and product technology, applied in the field of iterative three-dimensional reconstruction, can solve the problems of long measurement distance and low precision, and achieve the effect of reducing the false detection rate, easy layout and fast speed

Inactive Publication Date: 2018-01-26
NANCHANG HANGKONG UNIVERSITY
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has long measurement distance, high precision and fast speed, but the disadvantages are also obvious, and the precision is low when measuring a short distance

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
  • Product morphology detecting method based on Kinect
  • Product morphology detecting method based on Kinect
  • Product morphology detecting method based on Kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention is realized in this way, the Kinect-based assembly line product shape detection method is characterized in that it is composed of three key parts: Kinect-based 4-camera calibration, depth data optimization and three-dimensional reconstruction.

[0028] One based on kinect camera calibration

[0029] Camera calibration has a direct relationship to the accuracy of measurement results. The more precise the calibration, the more accurate the final measurement will generally be. Since each lens has a different degree of distortion when it leaves the factory, a corrected image can be obtained through calibration. Another important reason is for 3D scene reconstruction. The present invention mainly calibrates four Kinect depth cameras.

[0030] For a single Kinect camera, Zhang Zhengyou’s checkerboard calibration method can be used directly, but this paper uses multiple Kinects. Due to the restriction of checkerboard placement, it is difficult for each ...

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 product morphology detecting method based on Kinect. According to the method of the invention, three-dimensional reconstruction is performed on a product in a streamline by means of Kinect deep sensing equipment, and then the reconstructed model is compared with a preset product model for determining whether the product is a qualified method. The product morphology detecting method is advantageous in that a new improvement method is presented for multi-camera calibration, namely a cylinder manner is utilized for calibration; and a rotation translation matrix of the camera can be obtained accurately in higher speed. Compared with a method for performing integral filtering processing on a depth image for eliminating holes, the product morphology detecting method isadvantageous in that a target area is preliminarily selected by means of a rectangular block; and then an improved K-means clustering method is utilized for sufficiently eliminating product backgroundnoise and effectively extracting the product morphology. Compared with a traditional product detecting method, the method according to the invention has advantages of easy configuration, simple structure, high practicability, high speed and remarkable enterprise production cost reduction. Furthermore an error detecting rate of the product is reduced to a certain extent.

Description

technical field [0001] The invention relates to a Kinect product shape detection method, in particular to Kinect-based product depth data positioning and improved iterative three-dimensional reconstruction. Background technique [0002] With the introduction and implementation of Industry 4.0, the intelligentization and automation of manufacturing industry has become the general trend of industrial development, and the acquisition of high-speed and high-precision 3D data of product surface morphology is imminent. The three-dimensional measurement method is one of the key technologies to support intelligent production, realize human-computer interaction, and 3D technology. It is a high-tech integrating optical, mechanical, electrical and computer technologies. It provides the necessary three-dimensional data for intelligent production. [0003] At home and abroad, a series of researches have been done on the theory and application of high-speed three-dimensional measurement o...

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): G06T7/00G06T15/00G06T7/80
Inventor 伏燕军王福伟夏桂锁杨鹏斌徐天义
Owner NANCHANG HANGKONG UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap