Robust elastic model unmanned aerial vehicle image splicing method with locality preserving registration

An elastic model and image stitching technology, applied in the field of image processing, can solve problems such as tree occlusion and distortion, and achieve the effect of eliminating parallax

Inactive Publication Date: 2019-08-16
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, UAV imagery is somewhat different from other visible light images because it involves ground changes caused by image point changes, tree occlusions, and local distortions.

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
  • Robust elastic model unmanned aerial vehicle image splicing method with locality preserving registration
  • Robust elastic model unmanned aerial vehicle image splicing method with locality preserving registration
  • Robust elastic model unmanned aerial vehicle image splicing method with locality preserving registration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0039] Traditional stitching methods For robustness, people often use global deformations such as similarity, affine, and homography to register seamless stitching. Clearly, although a single global warp is robust, it cannot flexibly cope with image stitching of two or more scenes with large parallax. Gao et al. proposed dual homography warping, the main idea of ​​which is to divide the scene into a background plane and a foreground plane, and use two homography weights to align the two planes. Simple global deformations are often not flexible enough, e.g., parallax images caused by changes in the drone's viewpoint cannot be precisely aligned.

[0040] In order to achieve higher alignment accuracy, suturing methods hav...

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 robust elastic model unmanned aerial vehicle image splicing method with locality preserving registration. The present invention uses guided locality preserving matching (GLPM) to effectively remove anomalous values and retain localized features, then applies a thin plate spline (TPS) model with a simple radial distortion function (RBF), and then is projected onto a deformed image as a source image of a global similarity transform by global homography. Experimental results show that the method is steady and universal, parallax can be effectively eliminated, and complexlocal distortion can be processed.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a method for mosaicing UAV images, and more specifically, the present invention relates to a method for mosaicing images of UAVs with a robust elastic model that maintains local registration. Background technique [0002] Image stitching remains a subject of long-standing research and an ongoing challenge in machine vision. With the increasing popularity of UAV imaging devices in recent years, efficient processing of UAV images has become a hot topic. UAV image stitching is widely used in terrain reconstruction, environmental monitoring and urban planning. The traditional image stitching process is generally divided into three stages. The first step is to use the image pixels or their features to extract the correct image registration, then determine the reference and target images while warping them to the final composite plane. The final selection step utilizes releva...

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): G06T5/50G06T5/00G06T3/40
CPCG06T3/4038G06T5/009G06T5/50G06T2207/20221
Inventor 罗林波万祁陈珺龚文平罗大鹏魏龙生
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
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