Object recognition from local scale-invariant features
Citations
135 citations
Cites background from "Object recognition from local scale..."
...Some notable local features are SIFT [28], SURF [13] and ORB [34]....
[...]
135 citations
135 citations
134 citations
134 citations
Cites background from "Object recognition from local scale..."
...For higher order feature descriptors —such as ORB, SIFT, or SURF—the L1-norm, the L2-norm, or Hamming distances may be used; however, establishing matches using these measures is computationally intensive and may, if not carefully applied, degrade real-time performance....
[...]
...While the KD-tree is meant to accelerate SIFT feature matching, updating it with new features is computationally intensive....
[...]
...The system extracts phonySIFT descriptors as described in Wagner et al. (2010) and establishes feature correspondences using an accelerated matching method through hierarchical k-means....
[...]
...The first step is an offline procedure during which, SIFT features are780 extracted and triangulated using SfM methods into 3D landmarks....
[...]
...In the first pass, SIFT features from the current frame are matched to the selected keyframes, using the offline-generated vocabulary790 tree....
[...]
References
[...]
5,672 citations
4,310 citations
2,037 citations
1,756 citations
"Object recognition from local scale..." refers background or methods in this paper
...This allows for the use of more distinctive image descriptors than the rotation-invariant ones used by Schmid and Mohr, and the descriptor is further modified to improve its stability to changes in affine projection and illumination....
[...]
...For the object recognition problem, Schmid & Mohr [19] also used the Harris corner detector to identify interest points, and then created a local image descriptor at each interest point from an orientation-invariant vector of derivative-of-Gaussian image measurements....
[...]
..., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
...However, recent research on the use of dense local features (e.g., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
1,574 citations
"Object recognition from local scale..." refers methods in this paper
...[23] used the Harris corner detector to identify feature locations for epipolar alignment of images taken from differing viewpoints....
[...]