What exactly is the scale attribute that is calculated by detectSURFFeatures()?
1 回表示 (過去 30 日間)
古いコメントを表示
Title says it all. I'm aware that a higher scale means a "larger" feature, but I'm confused by the number of different scales. Consider this snippet, which is a slightly modified version of the example in the documentation to detect as much points as possible:
K>> I = imread('cameraman.tif');
K>> points = detectSURFFeatures(I, 'MetricThreshold',0);
K>> length(unique(points.Scale))
ans =
54
With default parameters detectSURFFeatures() uses 3 octaves and 4 scale levels. If I understood the SURF algorithm correctly this should limit the number of different scales to 3*4=12. Can someone help me out here?
0 件のコメント
回答 (1 件)
Jalaj Gambhir
2019 年 8 月 5 日
Hi,
You are confusing the 'scales' here. Each octave has fixed number of scale levels. detectSURFFeatures() does not return that value. This function returns the scale that is dependent on size of the image. You can verify this by resizing the image and then checking the unique scales returned. It would be different from 54.
参考
カテゴリ
Help Center および File Exchange で Computer Vision Toolbox についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!