opencv  2.2.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
Public Member Functions | Protected Member Functions | List of all members
cv::DynamicAdaptedFeatureDetector Class Reference

an adaptively adjusting detector that iteratively detects until the desired number of features are detected. Beware that this is not thread safe - as the adjustment of parameters breaks the const of the detection routine... /TODO Make this const correct and thread safe More...

#include <features2d.hpp>

Inheritance diagram for cv::DynamicAdaptedFeatureDetector:
cv::FeatureDetector

Public Member Functions

 DynamicAdaptedFeatureDetector (const Ptr< AdjusterAdapter > &adjaster, int min_features=400, int max_features=500, int max_iters=5)
 
- Public Member Functions inherited from cv::FeatureDetector
void detect (const Mat &image, vector< KeyPoint > &keypoints, const Mat &mask=Mat()) const
 
void detect (const vector< Mat > &images, vector< vector< KeyPoint > > &keypoints, const vector< Mat > &masks=vector< Mat >()) const
 
virtual void read (const FileNode &)
 
virtual void write (FileStorage &) const
 
virtual ~FeatureDetector ()
 

Protected Member Functions

virtual void detectImpl (const Mat &image, vector< KeyPoint > &keypoints, const Mat &mask=Mat()) const
 

Additional Inherited Members

- Static Public Member Functions inherited from cv::FeatureDetector
static Ptr< FeatureDetectorcreate (const string &detectorType)
 
- Static Protected Member Functions inherited from cv::FeatureDetector
static void removeInvalidPoints (const Mat &mask, vector< KeyPoint > &keypoints)
 

Detailed Description

an adaptively adjusting detector that iteratively detects until the desired number of features are detected. Beware that this is not thread safe - as the adjustment of parameters breaks the const of the detection routine... /TODO Make this const correct and thread safe

sample usage:

will create a detector that attempts to find 100 - 110 FAST Keypoints, and will at most run FAST feature detection 10 times until that number of keypoints are found Ptr<FeatureDetector> detector(new DynamicAdaptedFeatureDetector(new FastAdjuster(20,true),100, 110, 10));

Constructor & Destructor Documentation

cv::DynamicAdaptedFeatureDetector::DynamicAdaptedFeatureDetector ( const Ptr< AdjusterAdapter > &  adjaster,
int  min_features = 400,
int  max_features = 500,
int  max_iters = 5 
)
Parameters
adjasteran AdjusterAdapter that will do the detection and parameter adjustment
max_featuresthe maximum desired number of features
max_itersthe maximum number of times to try to adjust the feature detector params for the FastAdjuster this can be high, but with Star or Surf this can get time consuming
min_featuresthe minimum desired features

Member Function Documentation

virtual void cv::DynamicAdaptedFeatureDetector::detectImpl ( const Mat image,
vector< KeyPoint > &  keypoints,
const Mat mask = Mat() 
) const
protectedvirtual

Implements cv::FeatureDetector.


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