|
|
VlSiftFilt * | vl_sift_new (int width, int height, int noctaves, int nlevels, int o_min) |
| Create a new SIFT filter. More...
|
|
void | vl_sift_delete (VlSiftFilt *f) |
| Delete SIFT filter. More...
|
|
|
int | vl_sift_process_first_octave (VlSiftFilt *f, vl_sift_pix const *im) |
| Start processing a new image. More...
|
|
int | vl_sift_process_next_octave (VlSiftFilt *f) |
| Process next octave. More...
|
|
void | vl_sift_detect (VlSiftFilt *f) |
| Detect keypoints. More...
|
|
int | vl_sift_calc_keypoint_orientations (VlSiftFilt *f, double angles[4], VlSiftKeypoint const *k) |
| Calculate the keypoint orientation(s) More...
|
|
void | vl_sift_calc_keypoint_descriptor (VlSiftFilt *f, vl_sift_pix *descr, VlSiftKeypoint const *k, double angle) |
| Compute the descriptor of a keypoint. More...
|
|
void | vl_sift_calc_raw_descriptor (VlSiftFilt const *f, vl_sift_pix const *image, vl_sift_pix *descr, int widht, int height, double x, double y, double s, double angle0) |
| Run the SIFT descriptor on raw data. More...
|
|
void | vl_sift_keypoint_init (VlSiftFilt const *f, VlSiftKeypoint *k, double x, double y, double sigma) |
| Initialize a keypoint from its position and scale. More...
|
|
|
int | vl_sift_get_octave_index (VlSiftFilt const *f) |
| Get current octave index. More...
|
|
int | vl_sift_get_noctaves (VlSiftFilt const *f) |
| Get number of octaves. More...
|
|
int | vl_sift_get_octave_first (VlSiftFilt const *f) |
| Get first octave. More...
|
|
int | vl_sift_get_octave_width (VlSiftFilt const *f) |
| Get current octave width. More...
|
|
int | vl_sift_get_octave_height (VlSiftFilt const *f) |
| Get current octave height. More...
|
|
int | vl_sift_get_nlevels (VlSiftFilt const *f) |
| Get number of levels per octave. More...
|
|
int | vl_sift_get_nkeypoints (VlSiftFilt const *f) |
| Get number of keypoints. More...
|
|
double | vl_sift_get_peak_thresh (VlSiftFilt const *f) |
| Get peaks treashold. More...
|
|
double | vl_sift_get_edge_thresh (VlSiftFilt const *f) |
| Get edges threshold. More...
|
|
double | vl_sift_get_norm_thresh (VlSiftFilt const *f) |
| Get norm threshold. More...
|
|
double | vl_sift_get_magnif (VlSiftFilt const *f) |
| Get the magnification factor. More...
|
|
double | vl_sift_get_window_size (VlSiftFilt const *f) |
| Get the Gaussian window size. More...
|
|
vl_sift_pix * | vl_sift_get_octave (VlSiftFilt const *f, int s) |
| Get current octave data. More...
|
|
VlSiftKeypoint const * | vl_sift_get_keypoints (VlSiftFilt const *f) |
| Get keypoints. More...
|
|
|
void | vl_sift_set_peak_thresh (VlSiftFilt *f, double t) |
| Set peaks threshold. More...
|
|
void | vl_sift_set_edge_thresh (VlSiftFilt *f, double t) |
| Set edges threshold. More...
|
|
void | vl_sift_set_norm_thresh (VlSiftFilt *f, double t) |
| Set norm threshold. More...
|
|
void | vl_sift_set_magnif (VlSiftFilt *f, double m) |
| Set the magnification factor. More...
|
|
void | vl_sift_set_window_size (VlSiftFilt *f, double x) |
| Set the Gaussian window size. More...
|
|
void vl_sift_calc_raw_descriptor |
( |
VlSiftFilt const * |
f, |
|
|
vl_sift_pix const * |
grad, |
|
|
vl_sift_pix * |
descr, |
|
|
int |
width, |
|
|
int |
height, |
|
|
double |
x, |
|
|
double |
y, |
|
|
double |
sigma, |
|
|
double |
angle0 |
|
) |
| |
- Parameters
-
f | SIFT filter. |
grad | image gradients. |
descr | SIFT descriptor (output). |
width | image width. |
height | image height. |
x | keypoint x coordinate. |
y | keypoint y coordinate. |
sigma | keypoint scale. |
angle0 | keypoint orientation. |
The function runs the SIFT descriptor on raw data. Here image is a 2 x width x height array (by convention, the memory layout is a s such the first index is the fastest varying one). The first width x height layer of the array contains the gradient magnitude and the second the gradient angle (in radians, between 0 and \( 2\pi \)). x, y and sigma give the keypoint center and scale respectively.
In order to be equivalent to a standard SIFT descriptor the image gradient must be computed at a smoothing level equal to the scale of the keypoint. In practice, the actual SIFT algorithm makes the following additional approximation, which influence the result:
- Scale is discretized in
S
levels.
- The image is downsampled once for each octave (if you do this, the parameters x, y and sigma must be scaled too).
- Parameters
-
f | SIFT filter. |
k | SIFT keypoint (output). |
x | x coordinate of the keypoint center. |
y | y coordinate of the keypoint center. |
sigma | keypoint scale. |
The function initializes a keypoint structure k from the location x and y and the scale sigma of the keypoint. The keypoint structure maps the keypoint to an octave and scale level of the discretized Gaussian scale space, which is required for instance to compute the keypoint SIFT descriptor.
- Algorithm
The formula linking the keypoint scale sigma to the octave and scale indexes is
\[ \sigma(o,s) = \sigma_0 2^{o+s/S} \]
In addition to the scale index s (which can be fractional due to scale interpolation) a keypoint has an integer scale index is too (which is the index of the scale level where it was detected in the DoG scale space). We have the constraints (Detector see also the "SIFT detector"):
- o is integer in the range \( [o_\mathrm{min}, o_{\mathrm{min}}+O-1] \).
- is is integer in the range \( [s_\mathrm{min}+1, s_\mathrm{max}-2] \). This depends on how the scale is determined during detection, and must be so here because gradients are computed only for this range of scale levels and are required for the calculation of the SIFT descriptor.
- \( |s - is| < 0.5 \) for detected keypoints in most cases due to the interpolation technique used during detection. However this is not necessary.
Thus octave o represents scales \( \{ \sigma(o, s) : s \in [s_\mathrm{min}+1-.5, s_\mathrm{max}-2+.5] \} \). Note that some scales may be represented more than once. For each scale, we select the largest possible octave that contains it, i.e.
\[ o(\sigma) = \max \{ o \in \mathbb{Z} : \sigma_0 2^{\frac{s_\mathrm{min}+1-.5}{S}} \leq \sigma \} = \mathrm{floor}\,\left[ \log_2(\sigma / \sigma_0) - \frac{s_\mathrm{min}+1-.5}{S}\right] \]
and then
\[ s(\sigma) = S \left[\log_2(\sigma / \sigma_0) - o(\sigma)\right], \quad is(\sigma) = \mathrm{round}\,(s(\sigma)) \]
In practice, both \( o(\sigma) \) and \( is(\sigma) \) are clamped to their feasible range as determined by the SIFT filter parameters.