problem with image registration using BRISK
2 views (last 30 days)
Show older comments
i am using BRISK to extract feature from remote sensing images but the extracted feature are not right
the code used is as follows:
original1 = imread('im1.tif');
ptsOriginalBRISK1 = detectBRISKFeatures(original1,'MinContrast',0.01,'MinQuality',0.7);
[featuresO1,validPtsO1] = extractFeatures(original1,ptsOriginalBRISK1);
distorted1 = imread('im2.tif');
ptsDistortedBRISK1 = detectBRISKFeatures(distorted1,'MinContrast',0.01,'MinQuality',0.7);
[featuresD1,validPtsD1] = extractFeatures(distorted1,ptsDistortedBRISK1);
Pairs11 = matchFeatures(featuresO1,featuresD1,'MatchThreshold',90,'MaxRatio',0.9);
matchedO = validPtsO1(Pairs11(:,1));
matchedD = validPtsD1(Pairs11(:,2));
[tform, inlierDistorted,inlierOriginal] = estimateGeometricTransform(matchedD,matchedO,'similarity');
figure
showMatchedFeatures(original1,distorted1,inlierOriginal,inlierDistorted,'montage')
title('Matching points (inliers only)')
legend('im1','im2')
1 Comment
Image Analyst
on 15 Jan 2024
How could we possibly know that?
If you have any more questions, then attach your data and code to read it in with the paperclip icon after you read this:
Answers (1)
Udit06
on 17 Jan 2024
Edited: Udit06
on 17 Jan 2024
Hi Asmaa,
You can try to reduce the MetricThreshold parameter of the detectSURFFeatures function. Reducing the value of MetricThreshold parameter increases the number of blobs which may in turn increase the number of features.
Refer to the Name-Value arguments section of the following documentation for more details:
I hope this helps.
See Also
Categories
Find more on Computer Vision Toolbox in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!