Distinctive Image Features from Scale-Invariant Keypoints
Citations
410 citations
410 citations
409 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...The latter is first extracted using 2D image descriptors (such as SIFT [13]), and subsequently backprojected onto the mesh....
[...]
...Currently, SIFT [13] and HOG (histogram of oriented gradients) [3] are among the most widely used descriptors for their robustness to the transformations just cited....
[...]
...As proposed in [13] this can be done using the Hessian operator: :...
[...]
...MeshDOG is a generalization of the DOG operator [14, 13] and it seeks the extrema of the Laplacian of a scale-space representation of any scalar function defined on a discrete manifold....
[...]
408 citations
408 citations
Cites methods from "Distinctive Image Features from Sca..."
...While we could use a scale invariant feature detector such as SIFT [9] or SURF [2], these would significantly reduce ur real-time performance; the current corner detector can...
[...]
...While we could use a scale invariant feature detector such as SIFT [9] or SURF [2], these would significantly reduce our real-time performance; the current corner detector can process a 640x480 image in a few milliseconds, versus tens or hundreds of milliseconds for scale invariant detectors....
[...]
References
16,989 citations
"Distinctive Image Features from Sca..." refers background or methods in this paper
...The initial implementation of this approach (Lowe, 1999) simply located keypoints at the location and scale of the central sample point....
[...]
...Earlier work by the author (Lowe, 1999) extended the local feature approach to achieve scale invariance....
[...]
...More details on applications of these features to recognition are available in other pape rs (Lowe, 1999; Lowe, 2001; Se, Lowe and Little, 2002)....
[...]
...To efficiently detect stable keypoint locations in scale space, we have proposed (Lowe, 1999) using scalespace extrema in the difference-of-Gaussian function convolved with the image, D(x, y, σ ), which can be computed from the difference of two nearby scales separated by a constant multiplicative…...
[...]
...More details on applications of these features to recognition are available in other papers (Lowe, 1999, 2001; Se et al., 2002)....
[...]
15,558 citations
14,282 citations
"Distinctive Image Features from Sca..." refers background in this paper
...A more general solution would be to solve for the fundamental matrix (Luong and Faugeras, 1996; Hartley and Zisserman, 2000)....
[...]
13,993 citations
3,422 citations