Object recognition from local scale-invariant features
Citations
621 citations
Cites background from "Object recognition from local scale..."
...In particular, it is now possible to recognize instances of highly textured objects, such as magazine covers or toys, despite clutter, occlusion and affine transformations, by using object-specific features [ 12 , 19]....
[...]
616 citations
Cites methods from "Object recognition from local scale..."
...Our experiments demonstrate that the technique accurately detects actions on real-world sequences and is robust to changes in viewpoint, scale and action speed....
[...]
614 citations
Cites methods from "Object recognition from local scale..."
...The FV model pipeline consists of a local feature extraction step, computing dense SIFT descriptors [143] from an input image, which are then mapped to Fisher Vector representations via a Gaussian mixture model (GMM) fit to the set of local descriptors of the whole training set....
[...]
612 citations
Cites methods from "Object recognition from local scale..."
...Motivated by the recent success of object recognition using local features such as SIFT descriptors [7], these approaches model a human activity as a set of sparse local descriptors directly extracted from a 3-D XYT volume (i....
[...]
610 citations
Cites background or methods from "Object recognition from local scale..."
...[16, 17]....
[...]
...The field of object recognition has seen tremendous progress over the past years, both for specific domains such as face detection [26, 30], and for more general object domains [16, 32, 8, 25, 24]....
[...]
...Note that for relative object sizes > 5%, learning and recognition done on the entire image (red dashed line) works well, as reported in [16, 17]....
[...]
...For object recognition we use Lowe’s algorithm, which uses local scale-invariant features [16], as an example for a state-of-the-art general purpose recognition system with one-shot learning capability....
[...]
...Has the patch at least three keypoints? (A minimum of three keypoints are necessary for model learning [16]....
[...]
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....
[...]