Aerial image splicing method for an unmanned aerial vehicle
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An image stitching and aviation technology, applied in the field of image processing, can solve the problems of low stitching efficiency and low robustness, and achieve the effects of improving robustness and stitching efficiency, simple calculation, and improving accuracy and precision.
Active Publication Date: 2019-05-31
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF15 Cites 12 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] The purpose of the present invention is: in order to solve the problems of low robustness and low splicing efficiency of the existing unmanned aerial vehicle image splicing method, the present invention provides a Stitching Method of UAV Aerial Images
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0061] Such as figure 1 As shown, the present embodiment provides a method for splicing aerial images of drones, including the following steps:
[0062] S1: if figure 2 and image 3 As shown in , input two unmanned aerial vehicle images to be spliced as reference images f 1 (x,y) and the image to be registered f 2 (x,y);
[0063] S2: Using the FAST feature point detection algorithm for the reference image f 1 (x,y) and the image to be registered f 2 (x, y) are processed to obtain the reference image f respectively 1 (x,y) and the image to be registered f 2 FAST feature points of (x,y), such as Figure 4 and Figure 5 shown;
[0064] S3: Extract the reference image f respectively 1 (x,y) and the image to be registered f 2 (x, y) BRISK feature and FREAK feature at the FAST feature point;
[0065] S4: Use the HAMMING distance measure criterion and the BF search strategy to search the reference image f 1 (x,y) and the image to be registered f 2 Match the BRISK an...
Embodiment 2
[0069] This embodiment is further optimized on the basis of Embodiment 1, specifically:
[0070] Said S2 specifically includes the following steps:
[0071] S2.1: For the reference image f 1 (x,y) and the image to be registered f 2 For each pixel on (x, y), calculate the gray value difference between it and the gray value of w pixels on a circle with a radius of r and the pixel as the center in the surrounding z×z neighborhood;
[0072] S2.2: Judging the difference between the gray values, if there are at least continuous If the absolute value of the difference between gray values exceeds the preset threshold, the pixel is a FAST feature point, and then the non-maximum value suppression algorithm is used to remove the redundant FAST feature points, and the FAST of the reference image and the image to be registered is obtained. feature point set P 1 and P 2 ;
[0073] Extracting the reference image f in the S3 1 (x,y) and the image to be registered f 2 (x,y) The BRIS...
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
Login to view more
Abstract
The invention, which relates to the technical field of image processing, discloses an aerial image splicing method for an unmanned aerial vehicle comprising the following steps: S1, inputting two unmanned aerial vehicle aerial images to be spliced as a reference image and an image to be registered respectively; S2, processing the reference image and the to-be-registered image by using a FAST feature point detection algorithm to obtain FAST feature points of the reference image and the to-be-registered image; S3, extracting BRISK features and FREAK features at FAST feature points of the reference image and the to-be-registered image; S4, utilizing an HAMMING distance measurement criterion and a BF search strategy to respectively match the BRISK feature and the FREAK feature to obtain M optimal feature point pairs; S5, screening the feature point pairs by using an RANSAC algorithm, and calculating to obtain a coordinate transformation matrix between the feature point pairs; And S6, carrying out coordinate transformation on the to-be-registered image by using the coordinate transformation matrix, and carrying out weighted fusion on the to-be-registered image and the reference image toobtain a spliced image, The method has the advantages of high efficiency, high robustness and accurate splicing result.
Description
technical field [0001] The present invention relates to the technical field of image processing, and more specifically relates to a method for splicing aerial images of unmanned aerial vehicles. Background technique [0002] In recent years, with the development of UAV technology, UAVs have been widely used in various aerial photography and remote sensing scenarios. Wide field of view and high-resolution aerial images play an important role in military fields such as intelligence analysis, pre-war reconnaissance, and combat assessment. However, limited by the size of the aerial camera sensor, there is a contradiction between the field of view and the resolution. The coverage of a single UAV aerial image is small and cannot meet the needs of practical applications. Therefore, how to stitch multiple UAV aerial images into a seamless picture with a natural transition has become a research hotspot in recent years. [0003] Image registration is the key to image stitching. Image...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more