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

Mechanical arm real-time tracking method based on binocular vision guidance

A technology of real-time tracking and binocular vision, applied in the field of robot vision, can solve the problems of failure to provide robotic arm vision guidance solutions, poor tracking effect, etc.

Active Publication Date: 2020-12-25
DALIAN UNIV OF TECH
View PDF7 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

"Visual manipulator control device and method based on Camshift visual tracking and D-H modeling algorithm" disclosed by Han Jiuqiang of Xi'an Jiaotong University, patent number 201510394465.4. Although the traditional Camshift algorithm has low algorithm complexity, it is suitable for complex backgrounds or rich textures. Object tracking is poor
Generative algorithms ignore prior background information. Although discriminative algorithms significantly improve tracking performance, they are mainly used in video target tracking, and are rarely used in actual industries. They cannot provide solutions for robotic arm vision guidance.

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
  • Mechanical arm real-time tracking method based on binocular vision guidance
  • Mechanical arm real-time tracking method based on binocular vision guidance
  • Mechanical arm real-time tracking method based on binocular vision guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] specific implementation plan

[0062] The specific implementation manner of the present invention will be described in detail below in conjunction with the accompanying drawings and technical solutions.

[0063] The binocular vision-guided real-time tracking method of the manipulator first performs the calibration, correction and matching of the binocular camera, and the forward and inverse kinematics modeling of the manipulator. Then establish the coordinate transformation relationship between the manipulator and the binocular camera. Finally, the binocular camera is used to quickly collect the image sequence, and the image sequence collected by the left camera C1 is processed by using the linear kernel correlation filter and one-dimensional correlation filter fusion algorithm to obtain the two-dimensional coordinates of the workpiece center and the workpiece scale of each frame of image. At the same time, the images collected by the left and right cameras C1 and C2 a...

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 mechanical arm real-time tracking method based on binocular vision guidance, belongs to the technical field of robot vision, and relates to the field of industrial robots. The method comprises the steps: carrying out binocular stereo vision calibration, correction and matching and mechanical arm forward and reverse kinematics modeling; secondly, establishing a coordinateconversion relationship between the binocular camera and the mechanical arm, and quickly acquiring an image sequence through the binocular camera; processing an image sequence acquired by the camera by utilizing linear kernel correlation filtering, converting the image sequence into a robot base coordinate system {B}, and obtaining mechanical arm motion control parameters through kinematics calculation; finally, enabling the mechanical arm controller, the mechanical arm body and the actuator to complete related operation tasks. The tracking method provided by the invention can adapt to the change of the workpiece scale, considers the instantaneity and robustness, greatly weakens the influence of uncertainty factors on the system, and has the characteristics of high intelligence and high systematization degree.

Description

technical field [0001] The invention belongs to the technical field of robot vision, and relates to a real-time tracking method of a manipulator based on binocular vision guidance in the field of industrial robots. Background technique [0002] At present, the intelligent manufacturing model represented by robot technology is developing rapidly. Machine vision perception is a high-precision, non-contact and widely used technology, which can greatly improve the automation and intelligence of production. However, the traditional manipulator uses trial teaching or offline programming to control the manipulator to complete processing, assembly, handling, grasping and other tasks in accordance with the prescribed actions. In a complex and changeable environment, the position and posture of the workpiece cannot be determined. It is impossible to locate in real time. Provide the position and orientation of the workpiece to the robotic arm according to the visual information and gu...

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): G06T7/73G06T7/593G06T7/80G06T1/00B25J9/16
CPCG06T7/74G06T7/593G06T7/85G06T1/0014B25J9/1664B25J9/1697G06T2207/10012G06T2207/20056G06T2207/30164
Inventor 马建伟吕琦高松闫惠腾贾振元刘巍刘冬
Owner DALIAN UNIV OF TECH
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