OpenCV  3.0.0-dev
Open Source Computer Vision
Public Types | Public Member Functions | Public Attributes | List of all members
cv::cuda::SURF_CUDA Class Reference

Class used for extracting Speeded Up Robust Features (SURF) from an image. : More...

#include "cuda.hpp"

Public Types

enum  KeypointLayout {
  X_ROW = 0,
  Y_ROW,
  LAPLACIAN_ROW,
  OCTAVE_ROW,
  SIZE_ROW,
  ANGLE_ROW,
  HESSIAN_ROW,
  ROWS_COUNT
}
 

Public Member Functions

 SURF_CUDA ()
 the default constructor More...
 
 SURF_CUDA (double _hessianThreshold, int _nOctaves=4, int _nOctaveLayers=2, bool _extended=false, float _keypointsRatio=0.01f, bool _upright=false)
 the full constructor taking all the necessary parameters More...
 
int defaultNorm () const
 returns the default norm type More...
 
int descriptorSize () const
 returns the descriptor size in float's (64 or 128) More...
 
void downloadDescriptors (const GpuMat &descriptorsGPU, std::vector< float > &descriptors)
 download descriptors from device to host memory More...
 
void downloadKeypoints (const GpuMat &keypointsGPU, std::vector< KeyPoint > &keypoints)
 download keypoints from device to host memory More...
 
void operator() (const GpuMat &img, const GpuMat &mask, GpuMat &keypoints)
 
void operator() (const GpuMat &img, const GpuMat &mask, GpuMat &keypoints, GpuMat &descriptors, bool useProvidedKeypoints=false)
 
void operator() (const GpuMat &img, const GpuMat &mask, std::vector< KeyPoint > &keypoints)
 
void operator() (const GpuMat &img, const GpuMat &mask, std::vector< KeyPoint > &keypoints, GpuMat &descriptors, bool useProvidedKeypoints=false)
 
void operator() (const GpuMat &img, const GpuMat &mask, std::vector< KeyPoint > &keypoints, std::vector< float > &descriptors, bool useProvidedKeypoints=false)
 
void releaseMemory ()
 
void uploadKeypoints (const std::vector< KeyPoint > &keypoints, GpuMat &keypointsGPU)
 upload host keypoints to device memory More...
 

Public Attributes

GpuMat det
 
bool extended
 
double hessianThreshold
 
float keypointsRatio
 max keypoints = min(keypointsRatio * img.size().area(), 65535) More...
 
GpuMat mask1
 
GpuMat maskSum
 
GpuMat maxPosBuffer
 
int nOctaveLayers
 
int nOctaves
 
GpuMat sum
 
GpuMat trace
 
bool upright
 

Detailed Description

Class used for extracting Speeded Up Robust Features (SURF) from an image. :

The class SURF_CUDA implements Speeded Up Robust Features descriptor. There is a fast multi-scale Hessian keypoint detector that can be used to find the keypoints (which is the default option). But the descriptors can also be computed for the user-specified keypoints. Only 8-bit grayscale images are supported.

The class SURF_CUDA can store results in the GPU and CPU memory. It provides functions to convert results between CPU and GPU version ( uploadKeypoints, downloadKeypoints, downloadDescriptors ). The format of CPU results is the same as SURF results. GPU results are stored in GpuMat. The keypoints matrix is \(\texttt{nFeatures} \times 7\) matrix with the CV_32FC1 type.

The descriptors matrix is \(\texttt{nFeatures} \times \texttt{descriptorSize}\) matrix with the CV_32FC1 type.

The class SURF_CUDA uses some buffers and provides access to it. All buffers can be safely released between function calls.

See also
SURF
Note
  • An example for using the SURF keypoint matcher on GPU can be found at opencv_source_code/samples/gpu/surf_keypoint_matcher.cpp

Constructor & Destructor Documentation

cv::cuda::SURF_CUDA::SURF_CUDA ( )

the default constructor

cv::cuda::SURF_CUDA::SURF_CUDA ( double  _hessianThreshold,
int  _nOctaves = 4,
int  _nOctaveLayers = 2,
bool  _extended = false,
float  _keypointsRatio = 0.01f,
bool  _upright = false 
)
explicit

the full constructor taking all the necessary parameters

Member Function Documentation

int cv::cuda::SURF_CUDA::defaultNorm ( ) const

returns the default norm type

int cv::cuda::SURF_CUDA::descriptorSize ( ) const

returns the descriptor size in float's (64 or 128)

void cv::cuda::SURF_CUDA::downloadDescriptors ( const GpuMat descriptorsGPU,
std::vector< float > &  descriptors 
)

download descriptors from device to host memory

void cv::cuda::SURF_CUDA::downloadKeypoints ( const GpuMat keypointsGPU,
std::vector< KeyPoint > &  keypoints 
)

download keypoints from device to host memory

void cv::cuda::SURF_CUDA::operator() ( const GpuMat img,
const GpuMat mask,
GpuMat keypoints 
)

finds the keypoints using fast hessian detector used in SURF supports CV_8UC1 images keypoints will have nFeature cols and 6 rows keypoints.ptr<float>(X_ROW)[i] will contain x coordinate of i'th feature keypoints.ptr<float>(Y_ROW)[i] will contain y coordinate of i'th feature keypoints.ptr<float>(LAPLACIAN_ROW)[i] will contain laplacian sign of i'th feature keypoints.ptr<float>(OCTAVE_ROW)[i] will contain octave of i'th feature keypoints.ptr<float>(SIZE_ROW)[i] will contain size of i'th feature keypoints.ptr<float>(ANGLE_ROW)[i] will contain orientation of i'th feature keypoints.ptr<float>(HESSIAN_ROW)[i] will contain response of i'th feature

void cv::cuda::SURF_CUDA::operator() ( const GpuMat img,
const GpuMat mask,
GpuMat keypoints,
GpuMat descriptors,
bool  useProvidedKeypoints = false 
)

finds the keypoints and computes their descriptors. Optionally it can compute descriptors for the user-provided keypoints and recompute keypoints direction

void cv::cuda::SURF_CUDA::operator() ( const GpuMat img,
const GpuMat mask,
std::vector< KeyPoint > &  keypoints 
)
void cv::cuda::SURF_CUDA::operator() ( const GpuMat img,
const GpuMat mask,
std::vector< KeyPoint > &  keypoints,
GpuMat descriptors,
bool  useProvidedKeypoints = false 
)
void cv::cuda::SURF_CUDA::operator() ( const GpuMat img,
const GpuMat mask,
std::vector< KeyPoint > &  keypoints,
std::vector< float > &  descriptors,
bool  useProvidedKeypoints = false 
)
void cv::cuda::SURF_CUDA::releaseMemory ( )
void cv::cuda::SURF_CUDA::uploadKeypoints ( const std::vector< KeyPoint > &  keypoints,
GpuMat keypointsGPU 
)

upload host keypoints to device memory

Member Data Documentation

GpuMat cv::cuda::SURF_CUDA::det
bool cv::cuda::SURF_CUDA::extended
double cv::cuda::SURF_CUDA::hessianThreshold
float cv::cuda::SURF_CUDA::keypointsRatio

max keypoints = min(keypointsRatio * img.size().area(), 65535)

GpuMat cv::cuda::SURF_CUDA::mask1
GpuMat cv::cuda::SURF_CUDA::maskSum
GpuMat cv::cuda::SURF_CUDA::maxPosBuffer
int cv::cuda::SURF_CUDA::nOctaveLayers
int cv::cuda::SURF_CUDA::nOctaves
GpuMat cv::cuda::SURF_CUDA::sum
GpuMat cv::cuda::SURF_CUDA::trace
bool cv::cuda::SURF_CUDA::upright

The documentation for this class was generated from the following file: