Why do SURF feature points have floating point coordinates?
I have just written the C++ OpenCV 2.4.7 code to extract feature points in stereo images using SurfFeatureDetector. It worked well but I got confused when I realized that the point coordinates are floating points, say for example it found coordinates [283.23 123.424] as one of the features in left image. Here is a part of the code (simply extracting features): int minHessian = 400; SurfFeatureDetector detector(minHessian); vector<KeyPoint> featuresLeft, featuresRight; detector.detect(leftImg, featuresLeft); detector.detect(rightImg, featuresRight); Can anyone please tell me how this could be happening? Is there any interpolation involved in the built-in functions?
number of keypoints by SIFT openCV?
finding the real world coordinates of an image point
Correlation audio opencv
Find longevity of contours in opencv
When using SVD how do I unsort the scale factors along Sigma's diagonal?
Javacv Face Recognition
Unabe to create samples using opencv_createsamples.exe
Face recognition Using EigenObjectRecognizer
Facing an error in program of image capturing and processing using opencv(cv2) and python
OpenCV 2.4.6 crash at program runtime
opencv 2.4.5 unable to load tif image file properly in windows
What is the best method to template match a image with noise?
how to track object in scene from far to near in opencv
detect and follow a face by opencv
Can OpenCV .vec files be used by scikit-learn?
Detect objects similar to circles