Mechanical arm pose real-time detection method based on perspective multi-point projection

A technology of real-time detection and robotic arm, which is applied in image analysis, instruments, complex mathematical operations, etc. It can solve the problems of narrow field of view affected by light, high cost of binocular vision system, and poor system robustness, etc. , to achieve the effects of improving detection accuracy and efficiency, good recognition effect, and improving execution efficiency

Pending Publication Date: 2021-03-23
SHENZHEN XINJUNTE SMART MEDICAL EQUIP CO LTD
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to obtain the position of the object in the three-dimensional space, but due to the high cost of the binocular vision system, and the two camer

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 pose real-time detection method based on perspective multi-point projection
  • Mechanical arm pose real-time detection method based on perspective multi-point projection
  • Mechanical arm pose real-time detection method based on perspective multi-point projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Since the direct control of the displacement operation of the mechanical arm cannot meet the precision requirements, the present invention uses two acrylic cubes to simplify the representation of the base of the mechanical arm and the coordinate system of the working end (the working end is the sixth joint of the six-degree-of-freedom mechanical arm), where A cube simulates the base of the robot arm and is fixed. The coordinate system it is in is called the base coordinate system. Another block simulates the sixth joint of the robotic arm, which can move freely, and its coordinate system is called the mobile coordinate system. The schematic diagram of the real-time detection system of the position and posture of the manipulator based on perspective multi-point projection is as follows: figure 1 As shown, the "moving object" and "reference object" used to represent the base of the manipulator and the tip of the operation are placed on the test platform, and the monocular...

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 pose real-time detection method based on perspective multi-point projection. The method comprises the steps of conducting internal and external parameter calibration on a monocular camera; generating and detecting a mark code; and calculating relative coordinates and converting a coordinate system by using a PnP algorithm. According to the method, a calibrated monocular camera is used for detecting a mark code on the surface of a mechanical arm, three-dimensional coordinates and two-dimensional coordinates in space are matched, under the condition thatinternal parameters of the camera are known, external parameters of the camera are obtained by solving a minimized reprojection error, a rotation matrix of an object coordinate system relative to a standard coordinate system is obtained, and an Euler angle of the object is solved; meanwhile, multiple experiments prove that the algorithm used for solving the minimized reprojection error can achievebetter balance precision and execution efficiency.

Description

technical field [0001] The invention relates to the fields of numerical optimization and image processing, in particular to a method for real-time detection of the pose of a mechanical arm based on perspective multi-point projection. Background technique [0002] When performing surgery or other non-cooperative operations, the robotic arm often needs accurate pose information. At the same time, it is not suitable to install other target tools in the six-axis robotic arm when performing surgery or other operations that require high precision error control, and It is too difficult to extract surface features directly from the tool end of the manipulator. The pose detection of the manipulator is mainly to detect the six degrees of freedom of the tool at the tip of the manipulator, that is, three Euler angles pitch (pitch angle), yaw (yaw angle), roll (roll angle) and X, Y The displacement relative to the origin of the basic coordinate system in the three directions of , and Z....

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): G06T7/73G06T7/80G06F17/16
CPCG06T7/73G06T7/80G06F17/16
Inventor 李若尘龙仕强李楠楠张世雄安欣赏李革张伟民
Owner SHENZHEN XINJUNTE SMART MEDICAL EQUIP CO LTD
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