mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-27 20:50:25 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

added DenseFeatureDetector

Browse Source
This commit is contained in:
Maria Dimashova 2010-09-24 16:55:12 +00:00
parent a5910ac068
commit 98763247d9
2 changed files with 89 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
modules/features2d/include/opencv2/features2d/features2d.hpp
View File

@ -1356,6 +1356,32 @@ protected:
CV_EXPORTS Ptr<FeatureDetector> createFeatureDetector( const string& detectorType );
class DenseFeatureDetector : public FeatureDetector
{
public:
DenseFeatureDetector() : initFeatureScale(1), featureScaleLevels(1), featureScaleMul(0.1f),
initXyStep(6), initImgBound(0), varyXyStepWithScale(true), varyImgBoundWithScale(false) {}
DenseFeatureDetector( float _initFeatureScale, int _featureScaleLevels=1, float _featureScaleMul=0.1f,
int _initXyStep=6, int _initImgBound=0, bool _varyXyStepWithScale=true, bool _varyImgBoundWithScale=false ) :
initFeatureScale(_initFeatureScale), featureScaleLevels(_featureScaleLevels), featureScaleMul(_featureScaleMul),
initXyStep(_initXyStep), initImgBound(_initImgBound), varyXyStepWithScale(_varyXyStepWithScale), varyImgBoundWithScale(_varyImgBoundWithScale) {}
protected:
virtual void detectImpl( const Mat& image, const Mat& mask, vector<KeyPoint>& keypoints ) const = 0;
float initFeatureScale;
int featureScaleLevels;
float featureScaleMul;
int initXyStep;
int initImgBound;
bool varyXyStepWithScale;
bool varyImgBoundWithScale;
};
/*
* Adapts a detector to partition the source image into a grid and detect
* points in each cell.

98
modules/features2d/src/detectors.cpp
View File

@ -334,44 +334,32 @@ void SurfFeatureDetector::detectImpl( const Mat& image, const Mat& mask,
surf(grayImage, mask, keypoints);
}
Ptr<FeatureDetector> createFeatureDetector( const string& detectorType )
/*
* GridAdaptedFeatureDetector
*/
void DenseFeatureDetector::detectImpl( const Mat& image, const Mat& mask, vector<KeyPoint>& keypoints ) const
{
FeatureDetector* fd = 0;
if( !detectorType.compare( "FAST" ) )
keypoints.clear();
float curScale = initFeatureScale;
int curStep = initXyStep;
int curBound = initImgBound;
for( int curLevel = 0; curLevel < featureScaleLevels; curLevel++ )
{
fd = new FastFeatureDetector( 10/*threshold*/, true/*nonmax_suppression*/ );
for( int x = curBound; x < image.cols - curBound; x += curStep )
{
for( int y = curBound; y < image.rows - curBound; y += curStep )
{
keypoints.push_back( KeyPoint(static_cast<float>(x), static_cast<float>(y), curScale) );
}
}
curScale = curScale * featureScaleMul;
if( varyXyStepWithScale ) curStep = static_cast<int>( curStep * featureScaleMul + 0.5f );
if( varyImgBoundWithScale ) curBound = static_cast<int>( curBound * featureScaleMul + 0.5f );
}
else if( !detectorType.compare( "STAR" ) )
{
fd = new StarFeatureDetector( 16/*max_size*/, 5/*response_threshold*/, 10/*line_threshold_projected*/,
8/*line_threshold_binarized*/, 5/*suppress_nonmax_size*/ );
}
else if( !detectorType.compare( "SIFT" ) )
{
fd = new SiftFeatureDetector(SIFT::DetectorParams::GET_DEFAULT_THRESHOLD(),
SIFT::DetectorParams::GET_DEFAULT_EDGE_THRESHOLD());
}
else if( !detectorType.compare( "SURF" ) )
{
fd = new SurfFeatureDetector( 400./*hessian_threshold*/, 3 /*octaves*/, 4/*octave_layers*/ );
}
else if( !detectorType.compare( "MSER" ) )
{
fd = new MserFeatureDetector( 5/*delta*/, 60/*min_area*/, 14400/*_max_area*/, 0.25f/*max_variation*/,
0.2/*min_diversity*/, 200/*max_evolution*/, 1.01/*area_threshold*/, 0.003/*min_margin*/,
5/*edge_blur_size*/ );
}
else if( !detectorType.compare( "GFTT" ) )
{
fd = new GoodFeaturesToTrackDetector( 1000/*maxCorners*/, 0.01/*qualityLevel*/, 1./*minDistance*/,
3/*int _blockSize*/, false/*useHarrisDetector*/, 0.04/*k*/ );
}
else if( !detectorType.compare( "HARRIS" ) )
{
fd = new GoodFeaturesToTrackDetector( 1000/*maxCorners*/, 0.01/*qualityLevel*/, 1./*minDistance*/,
3/*int _blockSize*/, true/*useHarrisDetector*/, 0.04/*k*/ );
}
return fd;
removeInvalidPoints( mask, keypoints );
}
/*
@ -468,4 +456,44 @@ void PyramidAdaptedFeatureDetector::detectImpl( const Mat& image, const Mat& mas
}
}
Ptr<FeatureDetector> createFeatureDetector( const string& detectorType )
{
FeatureDetector* fd = 0;
if( !detectorType.compare( "FAST" ) )
{
fd = new FastFeatureDetector( 10/*threshold*/, true/*nonmax_suppression*/ );
}
else if( !detectorType.compare( "STAR" ) )
{
fd = new StarFeatureDetector( 16/*max_size*/, 5/*response_threshold*/, 10/*line_threshold_projected*/,
8/*line_threshold_binarized*/, 5/*suppress_nonmax_size*/ );
}
else if( !detectorType.compare( "SIFT" ) )
{
fd = new SiftFeatureDetector(SIFT::DetectorParams::GET_DEFAULT_THRESHOLD(),
SIFT::DetectorParams::GET_DEFAULT_EDGE_THRESHOLD());
}
else if( !detectorType.compare( "SURF" ) )
{
fd = new SurfFeatureDetector( 400./*hessian_threshold*/, 3 /*octaves*/, 4/*octave_layers*/ );
}
else if( !detectorType.compare( "MSER" ) )
{
fd = new MserFeatureDetector( 5/*delta*/, 60/*min_area*/, 14400/*_max_area*/, 0.25f/*max_variation*/,
0.2/*min_diversity*/, 200/*max_evolution*/, 1.01/*area_threshold*/, 0.003/*min_margin*/,
5/*edge_blur_size*/ );
}
else if( !detectorType.compare( "GFTT" ) )
{
fd = new GoodFeaturesToTrackDetector( 1000/*maxCorners*/, 0.01/*qualityLevel*/, 1./*minDistance*/,
3/*int _blockSize*/, false/*useHarrisDetector*/, 0.04/*k*/ );
}
else if( !detectorType.compare( "HARRIS" ) )
{
fd = new GoodFeaturesToTrackDetector( 1000/*maxCorners*/, 0.01/*qualityLevel*/, 1./*minDistance*/,
3/*int _blockSize*/, true/*useHarrisDetector*/, 0.04/*k*/ );
}
return fd;
}
}