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

Genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology

A technology of adaptive threshold and genetic algorithm, applied in the direction of genetic law, calculation, image data processing, etc., can solve problems such as limited scope of application

Active Publication Date: 2017-04-26
湖州菱创科技有限公司
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The pose calculation method based on feature extraction can only be applied to point clouds with obvious geometric features, and its scope of application is limited

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
  • Genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology
  • Genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology
  • Genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0019] The present invention preprocesses the initial point cloud to obtain a single-workpiece point cloud without noise, thereby performing rapid pose positioning on the chaotic box workpiece. The entire algorithm flow is mainly composed of point cloud denoising, point cloud segmentation, point cloud screening, Rough pose matching, precise pose positioning, etc.

[0020] Further, the specific implementation steps are:

[0021] (1) Use statistical filtering method to remove outlier noise. The statistical filtering formula is:

[0022]

[0023] Among them, p is the outlier point that needs to be filtered out, and p i Indicates the i-th outlier point that meets the conditions, Represents the Euclidean distance betwe...

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 genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology. The genetic algorithm and adaptive threshold constraint-combined ICP (iterative closest point) pose positioning technology can be applied to the fast six-degree-of-freedom pose positioning of box chaotic workpieces. Statistics filtering and a regional growth segmentation algorithm are adopted to pre-process original point cloud, and therefore, outliers are removed, and the point cloud set of the chaotic workpieces is obtained; a genetic algorithm is adopted to obtain the global optimal solution of a target point set relative to the initial pose of reference point cloud, and the number of iterations of an ICP (iterative closest point) algorithm is decreased; adaptive threshold constraint is adopted to eliminate local large deformation points, and Euclidean distance constraint is adopted to eliminated most large deformation points, normal vector included angle threshold values are adopted to eliminate wrong matching point pairs which satisfy a distance condition but do not satisfy an included angle condition; and therefore, the real-time performance of the algorithm can be ensured, and the accuracy of pose positioning can be improved.

Description

technical field [0001] The invention relates to a machine vision measurement technology, specifically refers to calculating the six-degree-of-freedom pose information of a target workpiece point cloud in a chaotic workpiece by using a point cloud processing technology based on a point cloud image obtained by coded structured light. The invention relates to an ICP algorithm. Background technique [0002] The ability to pick a target with a correct posture from a randomly stacked or unsorted box is called "Random Bin Picking" (Random Bin Picking, RBP). In 1986, MIT professor Berthold K.P. Horn pointed out in the book "Robot Vision" that one of the obstacles to promoting the application of industrial robots is the lack of ability to deal with inaccurately positioned workpieces. An effective method is to apply a template to the scene image. Iterative Closest Point (ICP) uses the least squares method to calculate the pose transformation from one point cloud to another. This meth...

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
IPC IPC(8): G06T7/70G06N3/12
CPCG06N3/126
Inventor 白瑞林石爱军田青华
Owner 湖州菱创科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com