Wrapper classes and functions for the GPU implementation of SIFT.
More...
Functions |
const QList< QVSiftFeature > | getSiftGPUFeatures (const QVImage< uChar > &image, nvidia_method method=CUDA_METHOD, bool computeDescriptors=FALSE, double filterWidthFactor=4.0, double orientationSampleWindow=2.0, double descriptorGridSize=3.0, int firstOctave=0, double thresholdDoG=0.02/3, double thresholdEdge=10.0, int d=3, int v=0) |
| Find SIFT features in an image using user-specified parameter values, using NVIDIA CUDA.
|
QList< QPair< int, int > > | matchSiftGPUFeatures (const QList< QVSiftFeature > img1features, const QList< QVSiftFeature > img2features, const float distmax=0.7, const float ratiomax=0.8, const bool mutual_best_match=true) |
| Match SIFT features between a pair of images using using NVIDIA CUDA.
|
Detailed Description
Wrapper classes and functions for the GPU implementation of SIFT.
This group contains wrapper functions for the SIFT GPU implementation of Changchang Wu. You can enable the QVision compatibility with this software in the config.pri file.
Function Documentation
const QList<QVSiftFeature> getSiftGPUFeatures |
( |
const QVImage< uChar > & |
image, |
|
|
nvidia_method |
method = CUDA_METHOD , |
|
|
bool |
computeDescriptors = FALSE , |
|
|
double |
filterWidthFactor = 4.0 , |
|
|
double |
orientationSampleWindow = 2.0 , |
|
|
double |
descriptorGridSize = 3.0 , |
|
|
int |
firstOctave = 0 , |
|
|
double |
thresholdDoG = 0.02/3 , |
|
|
double |
thresholdEdge = 10.0 , |
|
|
int |
d = 3 , |
|
|
int |
v = 0 | |
|
) |
| | |
Find SIFT features in an image using user-specified parameter values, using NVIDIA CUDA.
- Parameters:
-
| image | The image in which to detect features. |
| method | 0=CUDA, 1=GLSL, 2=CG |
| computeDescriptors | Skip descriptor computation if TRUE (not modifiable after initialization) |
| filterWidthFactor | Factor for filter width (2*factor*sigma+1). |
| orientationSampleWindow | Factor for orientation sample window (2*factor*sigma). |
| descriptorGridSize | Factor for descriptor grid size (4*factor*sigma). |
| firstOctave | First octave to start detection. |
| thresholdDoG | DoG threshold. |
| thresholdEdge | Edge threshold. |
- Returns:
- Returns the list of obtained keypoints (with descriptors if sd is not TRUE).
Definition at line 44 of file qvsiftgpu.cpp.
QList< QPair<int, int> > matchSiftGPUFeatures |
( |
const QList< QVSiftFeature > |
img1features, |
|
|
const QList< QVSiftFeature > |
img2features, |
|
|
const float |
distmax = 0.7 , |
|
|
const float |
ratiomax = 0.8 , |
|
|
const bool |
mutual_best_match = true | |
|
) |
| | |
Match SIFT features between a pair of images using using NVIDIA CUDA.
- Parameters:
-
| img1features | List of SIFT features from image 1. |
| img2features | List of SIFT features from image 2. |
| distmax | Maximum distance of SIFT descriptor. |
| ratiomax | Maximum distance ratio. |
| mutualBestMatch | Mutual best match or one way. |
- Returns:
- Returns set of matchings. Each matching contains two index references, one for the feature in each input feature list.
Definition at line 154 of file qvsiftgpu.cpp.
|