SURF-based aerial photography image stitching algorithm for fast unmanned aerial vehicle

An image stitching and algorithm technology, applied in the field of image processing, can solve problems such as easy loss

Inactive Publication Date: 2017-07-11
EAST CHINA NORMAL UNIV
View PDF2 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional image stitching algorithms such as the UAV image stitching method based on SIFT feature points need to be improved in accuracy and speed in the process of high-precision, high-resolution image stitching, and are prone to loss of details

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
  • SURF-based aerial photography image stitching algorithm for fast unmanned aerial vehicle
  • SURF-based aerial photography image stitching algorithm for fast unmanned aerial vehicle
  • SURF-based aerial photography image stitching algorithm for fast unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] The hardware environment of the simulation experiment is DELL desktop, the hardware configuration is Intel Core i5-4590CPU, the main frequency is 3.30GHz, the memory is 8G, and the software environment is Visual Studio 2013.

[0063] In the simulation test, the input pictures are the actual pictures taken by the drone, the picture resolution is 4000*3000, and the adjacent pictures have some overlapping scenes. First, the two input images are stitched together, and the stitching result is as follows Figure 5 shown. Figure 5 (a) is the splicing result of the method proposed by the present invention, Figure 5 (b) is the splicing result map of the UAV image splicing method based on SIFT feature points for the comparison method, such as Figure 5 As shown in the white frame, the present invention has better completed the seamless splicing of images, and the transition at the edges of the images is smooth.

[0064] The stitching results of multiple input images are as f...

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 SURF-based aerial photography image stitching algorithm for a fast unmanned aerial vehicle. According to the algorithm, firstly, an image is pre-processed. Due to the fact that images shot by an unmanned aerial vehicle are too large is size, all images are down-sampled to a certain size. Based on the SURF algorithm, a 64-dimension feature vector is generated. After that, based on the distance ratio of a nearest neighbor distance and a secondary neighbor distance, coarsely matched pairs are obtained. After that, based on RANSAC, mistakenly matched pairs are removed, and a perspective transformation matrix among images is solved out. Along with the changing of the view angle of the unmanned aerial vehicle, the perspective transformation matrix is adjusted and matched images are converted. Finally, based on the multi-band fusion algorithm, the seamless splicing of images is realized. According to the invention, high-precision and high-resolution images, shot by the unmanned aerial vehicle, can be quickly spliced. Meanwhile, spliced edges are smooth in transition and more details are reserved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a SURF-based fast unmanned aerial vehicle image stitching algorithm, which is mainly aimed at high-resolution and high-precision image sequences captured by unmanned aerial vehicles, and quickly splicing them to form a large scene Intuitive and easy-to-understand graphics. Background technique [0002] Image stitching refers to the process of splicing a group of image sequences with partially overlapping areas into a more comprehensive and detailed panoramic image. intuitive information. Image stitching has a wide range of applications in various fields. For aerial photography sequences taken by drones, the image scale is large, the details are rich, and the angle changes greatly. It is extremely complicated to stitch them together to form an intuitive and easy-to-understand image of a large scene. task. [0003] Image stitching mainly includes two parts: imag...

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): G06T3/00G06T3/40G06T5/50
CPCG06T3/0068G06T3/4038G06T5/50
Inventor 文颖张乐
Owner EAST CHINA NORMAL UNIV
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