Rapid image splicing method based on optimized three-dimensional reconstruction

A technology of image stitching and 3D reconstruction, which is applied in graphics and image conversion, image data processing, 3D modeling, etc., to achieve the effect of increasing calculation speed and simplifying cumbersome calculations

Active Publication Date: 2020-08-18
NANJING UNIV OF POSTS & TELECOMM
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the decision about the next view selection after the initial value is selected is also very important, and the selection error will bring a huge time cost

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
  • Rapid image splicing method based on optimized three-dimensional reconstruction
  • Rapid image splicing method based on optimized three-dimensional reconstruction
  • Rapid image splicing method based on optimized three-dimensional reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0049] Such as figure 1 A fast image mosaic method based on optimized 3D reconstruction is shown, including the following steps:

[0050] Step 1. Extract grayscale images of n input images. In this example, 60 grayscale images of drone aerial images of 1280 pixels by 1280 pixels are extracted.

[0051] Step 2. Use the fast robust feature algorithm (SURF) to detect the feature points of each image, and generate an image descriptor X, where X=(x 1 ,x 2 ..., x 64 ); The image descriptor is a 64-dimensional vector, and the generation steps are as follows:

[0052] Step 2.1, select the pixel point l(x,y,σ) and construct the Hessian matrix as follows:

[0053]

[0054] Where σ is the pixel scale, L xx (x,σ), L xy (x,σ), L yy (x,σ) is the two-dimensional convolution of the second-order partial derivative of the Gaussian function at point x...

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 rapid image splicing method based on optimized three-dimensional reconstruction, and the method comprises the steps: constructing dense point clouds of a photographing regionthrough employing a motion recovery structure and a multi-view stereo technology, and achieving the splicing of an image through the dense point clouds; optimized feature descriptors are adopted in image feature point extraction to perform optimization adjustment, and when error accumulation is eliminated, an optimization strategy of how to select a next optimal view after initialization is completed is proposed, so that the accuracy of point cloud generation is ensured, and the possibility of failure of a bundle adjustment method is reduced.

Description

technical field [0001] The invention relates to the technical field of image three-dimensional reconstruction, and mainly relates to a fast image splicing method based on optimized three-dimensional reconstruction. Background technique [0002] 3D reconstruction technology is an important technology for fully automatic image stitching. Because of the characteristics of no manual intervention and no need for auxiliary reference images, scholars have proposed that image-based 3D reconstruction technology can be used to fully automatically reconstruct the shooting area. [0003] At present, the image-based 3D reconstruction technology mainly uses geometric projection and deep learning to reconstruct a single image, but this method is greatly affected by the geometric conditions and lighting conditions of the graphics in the image, and is not suitable for large outdoor scenes. Use; there are RGB-D-based depth cameras, such as Microsoft's Kinect, etc. [0004] Among these theor...

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): G06T3/40G06T17/00
CPCG06T3/4038G06T17/00Y02T10/40
Inventor 张佳煜陈志陈锐郑博文岳文静
Owner NANJING UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap