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

Robot dynamic capture method and system

A robotic and dynamic technology, applied in the field of robot visual servoing, can solve the problems of inability to judge the type of objects and affine transformation, difficult to achieve high frame rate real-time recognition, affecting the accuracy of visual servoing, etc., to achieve real-time frame rate recognition, high frame rate The effect of real-time identification, improving running speed and accuracy

Pending Publication Date: 2018-05-04
SHENZHEN CAS DERUI INTELLIGENT TECH CO LTD
View PDF0 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) For the industrial sorting line, the foreground moving target extraction based on background modeling is adopted. The algorithm has low complexity and can efficiently determine the moving target, but cannot judge the category and affine transformation of the object;
[0006] 2) The two-dimensional template matching algorithm based on feature modeling can accurately classify objects in the image and calculate their position and rotation angle. For grasping problems, the computational consumption of the algorithm is extremely high. With limited computing resources, it is difficult to achieve high frame rate real-time recognition, which affects the accuracy of visual servoing

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
  • Robot dynamic capture method and system
  • Robot dynamic capture method and system
  • Robot dynamic capture method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 , figure 2 As shown, the present invention provides a kind of robot dynamic grasping method, comprises the steps:

[0047] S1. Receive the captured image transmitted by the industrial camera in real time, and preprocess the obtained image;

[0048] The upper computer (generally a PC) receives the collected images transmitted by the industrial camera in real time, and performs preprocessing on the obtained images, including image denoising and building image pyramids to improve the operation speed of the algorithm.

[0049] S2. Using a template tracking algorithm based on multiple clues to determine the foreground target area;

[0050]For the top image of the collected image pyramid, the multi-cue codebook model is modeled. "Multi-cue" specifically refers to the clues of image area texture, color, area contour distance, and area characteristics; firstly, the codebook model of texture clues is used to establish candidate region, and then screen the ca...

Embodiment 2

[0058] Such as image 3 As shown, the present invention also provides a dynamic grabbing system for a robot, including an image acquisition preprocessing module, a multi-cue target tracking module, a target recognition and precise positioning module, a motion information modeling module, and a robot dynamic grabbing module connected in sequence;

[0059] The image acquisition preprocessing module is used to receive the acquired image transmitted by the industrial camera in real time, and preprocess the obtained image;

[0060] The upper computer (generally a PC) receives the collected images transmitted by the industrial camera in real time, and performs preprocessing on the obtained images, including image denoising and building image pyramids to improve the operation speed of the algorithm.

[0061] The multi-cue target tracking module is used to determine the foreground target area using a multi-cue based template tracking algorithm;

[0062] For the top image of the colle...

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 robot dynamic capture method and system. The method comprises the steps that S1, a collected image transmitted from an industrial camera is received in real time, and the obtained image is preprocessed; S2, a template tracking algorithm based on multiple clues is utilized to determine a foreground target region; S3, a template matching algorithm based on an edge gradientis adopted to precisely recognize a foreground target; S4, a random sampling consensus algorithm is adopted to perform modeling on motion information of an object in a view field; and S5, the information is fed back to a robot in real time for dynamic capture in combination with camera calibration and hand-eye calibration parameters. According to the robot dynamic capture method and system, by theadoption of a target tracking algorithm based on multiple clues, the motion target foreground region can be extracted efficiently and accurately; and under the application scene of robot sorting, therunning speed of a visual motion target tracking algorithm can be effectively increased, high-frame-rate real-time recognition is realized, and therefore the precision of visual servo is improved.

Description

technical field [0001] The invention relates to the technical field of robot visual servoing, in particular to a dynamic grabbing method and system for a robot. Background technique [0002] The sorting process in the food, pharmaceutical and electronics manufacturing industries is labor-intensive. In recent years, with the increase in labor costs and the reduction in the cost of industrial robots, more and more robots have been applied to the sorting process on the assembly line. Robot visual servo and dynamic grasping technology refers to real-time acquisition of images of real objects through industrial cameras, tracking and modeling of motion information of objects to be grasped through target tracking or pattern recognition technology, and feedback to the robot system for further motion control and path planning to successfully grasp objects. [0003] At present, the moving target tracking methods in the field of computer vision mainly include optical flow method, fram...

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): G06K9/62G06T7/80B25J9/16
CPCG06T7/80B25J9/16B25J9/1679G06T2207/20016G06F18/22
Inventor 李友浩张弓王卫军韩彰秀蔡君义
Owner SHENZHEN CAS DERUI INTELLIGENT TECH CO LTD
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