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

Large-scene image splicing method for AGV (Automatic Guided Vehicle) application

A technology of image stitching and large scenes, which is applied in the field of image processing, can solve the problems that are difficult to apply to real-time scenes and huge memory, and achieve the effects of reducing the number of registrations, ensuring accuracy, and reducing cumulative errors

Pending Publication Date: 2022-05-10
HEBEI UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for portable devices, the memory required by SIFT and SURF is too large to be applied to real-time scenarios, so the ORB algorithm came into being

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
  • Large-scene image splicing method for AGV (Automatic Guided Vehicle) application
  • Large-scene image splicing method for AGV (Automatic Guided Vehicle) application
  • Large-scene image splicing method for AGV (Automatic Guided Vehicle) application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The invention requires that the optical center of the photographed camera is on a plane, and the camera can automatically generate a panoramic view with a large field of view from multiple images photographed along the two degrees of freedom of the plane, which is convenient for subsequent image processing and fulfills specific requirements.

[0039] The realization of the present invention is as flow process figure 1 shown. Specific steps are as follows:

[0040] Step 1: Input the image to be stitched.

[0041]Step 2: Use the ORB algorithm to detect feature points on each image, and obtain information such as coordinates, scales, and descriptors of each feature point in the image.

[0042] The ORB algorithm is composed of the combination of FAST and BRIEF. Among them, in order to remove some edge abnormal points, the FAST algorithm often needs to use the Harris method to calculate again after the feature point detection, in which the Sobel operator is used to calcula...

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 provides a large-scene image splicing method for AGV (Automatic Guided Vehicle) application. The method comprises the following steps: 1, inputting an image to be spliced; 2, carrying out feature point detection on each image by using an ORB algorithm; 3, matching the images; 4, using RANSAC to obtain an accurate conversion matrix; 5, horizontal offset and vertical offset are obtained; 6, performing preliminary fusion on the image and determining a mask; and 7, performing image multi-band fusion and superposition to realize image splicing. According to the method, a mask part in a more suitable image fusion part is designed for construction of an AGV scene, the precision is ensured, the mask generation speed is improved, the image fusion time is shortened, and automatic splicing of multiple images along two degrees of freedom is expanded. Meanwhile, the conversion matrix between the target image and the reference image is directly used, the number of registration times of the images is reduced, accumulative errors caused by multiple images in an existing one-way splicing algorithm are effectively reduced, and the panoramic imaging effect is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a large-scene image stitching method for AGV applications. Background technique [0002] AGV (Automatic Guidance Vehicle) is a transport vehicle equipped with automatic guidance devices such as electromagnetic or optical, capable of driving along a prescribed guidance path, and has safety protection and various transfer functions. Aiming at the construction of AGV application scenarios, it can lay a solid foundation for car map construction, path planning and car positioning. However, since the viewing angle of a single camera is limited or the resolution of a large field of view cannot meet the requirements, it is necessary to adopt an image stitching method to meet the requirements of large scenes and high resolution. [0003] Image stitching refers to two or more images with overlapping areas, through steps such as image registration, image reprojection, and image fu...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06T5/50G06T7/33
CPCG06T3/4038G06T5/50G06T7/337G06T2207/20221
Inventor 肖金壮孙可可余雪乐周刚周振
Owner HEBEI UNIVERSITY