UAV based image splicing method and device

A technology of image stitching and drones, applied in the field of drones, can solve the problems of low stitching speed and low accuracy, and achieve the effects of low hardware requirements, eliminating ghost images, and improving matching speed and stitching speed

Pending Publication Date: 2018-11-30
深圳市易飞方达科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the splicing speed of the existing t

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
  • UAV based image splicing method and device
  • UAV based image splicing method and device
  • UAV based image splicing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] like figure 1 Shown, in the present embodiment, a kind of image mosaic method based on drone, comprises:

[0055] S10. Acquiring images to be spliced, where the images to be spliced ​​include a first image and a second image;

[0056] S20. Extracting feature points of the image to be stitched;

[0057] S30. Perform rough matching on the feature point pairs of the first image and the second image;

[0058] S40. Using an edge detection algorithm to perform edge detection;

[0059] S50. Removing mismatched feature point pairs;

[0060] S60. Stitch the first image and the second image by adopting a gradual-in-and-out fusion mechanism.

[0061] In this embodiment, the extracted image features are matched to estimate the transformation matrix between images, and then the transformation matrix is ​​used to align the images, which effectively eliminates the "ghost" phenomenon of the image, improves the matching speed and splicing speed, and improves In order to improve the...

Embodiment 2

[0083] like Figure 5 Shown, in this embodiment, a kind of image mosaic device based on drone, comprises:

[0084] An image acquisition module 10, configured to acquire an image to be spliced, the image to be spliced ​​includes a first image and a second image;

[0085] Feature point extraction module 20, for extracting the feature points of the image to be stitched;

[0086] A matching module 30, configured to roughly match the feature point pairs of the first image and the second image;

[0087] Edge detection module 40, for adopting edge detection algorithm to carry out edge detection;

[0088] Removal module 50, is used for removing the characteristic point pair of mismatch;

[0089] The splicing module 60 is configured to splice the first image and the second image by adopting an in-and-out fusion mechanism.

[0090] In this embodiment, the extracted image features are matched to estimate the transformation matrix between images, and then the transformation matrix is ...

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 relates to the technical field of UAVs, and discloses a UAV based image splicing method and device. The method comprises: acquiring an image to be spliced, wherein the image to be spliced comprises a first image and a second image; extracting feature points of the image to be spliced; performing rough matching on feature point pairs of the first image and the second image; using theedge detection algorithm to perform edge detection; removing mismatched feature point pairs; and adopting a fade-in and fade-out fusion mechanism to splice the first image and the second image. The extracted image features are matched, a transformation matrix between the images is estimated, and then the transformation matrix is used to align the images, the "ghosting" phenomenon of the images iseffectively eliminated, the matching speed and splicing speed are improved, the splicing accuracy is improved, and hardware requirements are low.

Description

technical field [0001] The present invention relates to the technical field of drones, in particular to an image stitching method and device based on drones. Background technique [0002] Due to the influence of environmental factors during shooting, the images taken by drones cover a limited area, and the image quality is poor, which cannot meet people's needs for high resolution and wide viewing angles, and the hardware equipment for obtaining panoramic images is very expensive. Therefore, it is necessary to splicing images to widen the field of view, increase the amount of information in the image, and improve its clarity. However, the splicing speed of the prior art is low and the accuracy rate is not high. Contents of the invention [0003] The main purpose of the present invention is to propose an image mosaic method and device based on unmanned aerial vehicles, which can estimate the transformation matrix between images by matching the extracted image features, and...

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): G06T3/00G06T3/40G06T7/13
CPCG06T3/0068G06T3/4038G06T7/13
Inventor 不公告发明人
Owner 深圳市易飞方达科技有限公司
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