Unlock instant, AI-driven research and patent intelligence for your innovation.

Bee colony algorithm based trinocular vision calibration for optimizing BP neural network

A technology of BP neural network and bee colony algorithm, which is applied in the field of trinocular vision calibration based on bee colony algorithm to optimize BP neural network, can solve the problems of large amount of calculation and low calibration accuracy, and achieve the effect of accuracy and rapidity

Inactive Publication Date: 2019-07-12
HARBIN UNIV OF SCI & TECH
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the usual large-scale structural visual calibration research, the research focus is mainly on the theory of building complex mathematical models, and the essence of camera calibration is to make pixels correspond to object points, and the internal parameters in the calibration process are nonlinear functions. When solving nonlinear functions, the method of using mathematical models has a large amount of calculation and the calibration accuracy is not high

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
  • Bee colony algorithm based trinocular vision calibration for optimizing BP neural network
  • Bee colony algorithm based trinocular vision calibration for optimizing BP neural network
  • Bee colony algorithm based trinocular vision calibration for optimizing BP neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0029] In this embodiment, based on the bee colony algorithm, the BP neural network trinocular vision calibration method is optimized, and the flow chart is as follows figure 1 As shown, the method includes the following steps:

[0030] Step a: Determine the number of hidden layers, input and output nodes of the BP neural network;

[0031] Step b: use the artificial bee colony algorithm to select the optimal value for the weight and bias of the BP neural network;

[0032] Step c: Determine the parameter values ​​of the BP neural network structure, make the pixel point data distribution learn the object space point data distribution, and complete the calibration.

specific Embodiment 2

[0034] In this example, based on the bee colony algorithm to optimize the BP neural network trinocular vision calibration method, on the basis of the specific embodiment 1, the specific operation steps of step a, step b, step c, and step d are further limited. in:

[0035] Described step a is specifically:

[0036] Four kinds of BP neural network binocular vision models with different layers were established, and the best hidden layer number of BP neural network was determined to be 3 by experimental method. According to the binocular vision calibration model, as shown below, it is determined that there are 6 pixel points and 3 object space points during trinocular vision calibration.

[0037]

[0038] In the above formula, i is the number of cameras, 1≤i≤3, i∈Z+, f is the focal length of the camera, r i , T i Rotation matrix and translation matrix for conversion from the world coordinate system to the two camera coordinate systems, u 0i , v 0i is the coordinates of th...

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 visual measurement trinocular vision calibration method, and belongs to the field of optical measurement and visual detection. The method comprises the following steps: determining initial parameters such as the number of hidden layers of the BP neural network, input and output nodes and the like; carrying out optimal selection on the weight and the bias of the BP neuralnetwork by utilizing an artificial bee colony algorithm, and determining an optimal weight and a bias value; and determining each parameter value of the BP neural network structure, enabling pixel point data distribution to learn object space point data distribution, and completing calibration. According to the method, errors generated on a neural network training set in calibration are used as afitness function of the artificial bee colony algorithm; by utilizing the characteristics of simplicity in operation, few control parameters, high search precision and high robustness of the artificial bee colony algorithm, the optimal initial weight and bias are selected, and the problems that the current BP neural network calibration method is liable to be caught in local optimum and low in convergence speed are solved.

Description

technical field [0001] The invention belongs to the field of optical measurement and visual detection, and in particular relates to a three-eye visual calibration based on a bee colony algorithm to optimize a BP neural network. Background technique [0002] In recent years, machine vision and visual inspection technology have been applied in many fields, such as large-scale parts measurement, industrial assembly line inspection and other fields. Visual inspection can not only reduce labor costs, but also improve detection accuracy, avoiding problems caused by inspection personnel negligent error. [0003] In the usual large-scale structural visual calibration research, the research focus is mainly on the theory of building complex mathematical models, and the essence of camera calibration is to make pixels correspond to object points, and the internal parameters in the calibration process are nonlinear functions. When solving nonlinear functions, the method of using mathema...

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): G06T7/80G06N3/04G06N3/08
CPCG06T7/85G06N3/084G06T2207/10012G06T2207/20081G06T2207/20084G06T2207/20088G06T2207/30244G06N3/044G06N3/045
Inventor 乔玉晶赵宇航张思远
Owner HARBIN UNIV OF SCI & TECH