Orb feature detector

1. What is ORB feature detector?
2. Is ORB better than SIFT?
3. What is ORB in Opencv?
4. Are ORB features scale invariant?

What is ORB feature detector?

Oriented FAST and rotated BRIEF (ORB) is a fast robust local feature detector, first presented by Ethan Rublee et al. in 2011, that can be used in computer vision tasks like object recognition or 3D reconstruction.

Is ORB better than SIFT?

We showed that ORB is the fastest algorithm while SIFT performs the best in the most scenarios. For special case when the angle of rotation is proportional to 90 degrees, ORB and SURF outperforms SIFT and in the noisy images, ORB and SIFT show almost similar performances.

What is ORB in Opencv?

ORB is basically a fusion of FAST keypoint detector and BRIEF descriptor with many modifications to enhance the performance. First it use FAST to find keypoints, then apply Harris corner measure to find top N points among them. It also use pyramid to produce multiscale-features.

Are ORB features scale invariant?

ORB features are invariant to scale, rotation and limited affine changes. S. Leutenegger et al. put forward Binary Robust Invariant Scalable Keypoints (BRISK) in 2011 [18], which detects corners using AGAST algorithm and filters them with FAST Corner score while searching for maxima in the scale space pyramid.