Multi-resolution image stitching method based on control points

A low-resolution image, high-resolution image technology, applied in the field of multi-resolution image stitching based on control points, can solve the problems of low image matching efficiency and inability to stitch aerial sequence images in real time.

Inactive Publication Date: 2015-06-24
NO 63655 TROOPS OF THE CHINESE PEOPLES LIBERATION ARMY
View PDF6 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above deficiencies, the present invention proposes a method for multi-resolution image matching using ground control points, which aims 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
  • Multi-resolution image stitching method based on control points
  • Multi-resolution image stitching method based on control points
  • Multi-resolution image stitching method based on control points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0064] The technical scheme adopted by the present invention is as follows, and the multi-resolution image mosaic method based on control points includes the following steps:

[0065] (1) The aerial sequence images are divided into high-resolution image collection and low-resolution image collection. The high-resolution image is characterized by a small field of view and the shooting range is limited, and the low-resolution image is characterized by the ability to obtain images with a large field of view. High-resolution images have 10 times the resolution of low-resolution images. Firstly, usi...

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 multi-resolution image stitching method based on control points. The multi-resolution image stitching method includes the steps that 1, unmanned-aerial-vehicle aerial photography sequence images are obtained, wherein rotation and transverse-movement transformation relations of the images are obtained through two sets of ground control point pairs in overlapped areas of the adjacent frames of low-resolution images, and finally the low-resolution sequence images are stitched and fused; 2, the stitching result of the low-resolution sequence images serves as a high-accuracy matching template, and final integral image matching is completed from coarse to fine; 3, the high-resolution sequence images matched to the template serve as growing points, the high-resolution sequence images of four adjacent regions of the growing points are stitched and fused through region growing, and the corresponding low-resolution images are replaced; then the high-resolution images of four adjacent regions serve as new region growing points for continuous growing till all the sequence images are matched to the template. By means of the multi-resolution image stitching method, the technical problems that in the existing image stitching technology, the image matching efficiency is low, and the aerial photography sequence images can not be stitched in real time are solved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a multi-resolution image splicing method based on control points. Background technique [0002] A single image cannot meet the practical requirements due to the limited viewing angle range. At this time, it is necessary to spatially register the image sequences with overlapping areas to form a panoramic image with a wide viewing angle and a large range. Image stitching is mainly realized based on the similarity of overlapping areas between two images. This technology has been widely used in digital map stitching, urban planning, geographic information systems and other fields. The range of applications for splicing ground image sequences captured by aerial photography into ground panoramic images is also becoming wider and wider. [0003] Image registration is the key technology of image mosaic. At present, commonly used image registration methods are mainly...

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): G06T3/40G06T5/50
Inventor 谢永杰焦姣徐欢张文明唐佩佳伊凯
Owner NO 63655 TROOPS OF THE CHINESE PEOPLES LIBERATION ARMY
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