OpenCV Good Features To Track. More...
#include <ossimOpenCVGoodFeaturesToTrack.h>
Public Member Functions | |
| ossimOpenCVGoodFeaturesToTrack (ossimObject *owner=NULL) | |
| ossimString | getShortName () const |
| ossimString | getLongName () const |
|
virtual ossimRefPtr < ossimImageData > | getTile (const ossimIrect &tileRect, ossim_uint32 resLevel=0) |
| virtual void | initialize () |
| virtual ossimScalarType | getOutputScalarType () const |
| ossim_uint32 | getNumberOfOutputBands () const |
| virtual bool | saveState (ossimKeywordlist &kwl, const char *prefix=0) const |
| virtual bool | loadState (const ossimKeywordlist &kwl, const char *prefix=0) |
Public Attributes | |
| std::vector< ossimDpt > | theKeyPoints |
Protected Member Functions | |
| void | runUcharTransformation (ossimImageData *tile) |
Protected Attributes | |
| ossimRefPtr< ossimImageData > | theTile |
| double | theQualityLevel |
| double | theMinDistance |
| int | theBlockSize |
| int | theHarrisFlag |
| double | theHarrisFreeParameter |
OpenCV Good Features To Track.
Determines strong corners on an image.
It only supports a 8-bit or floating-point 32-bit single-channel image.
| quality_level | Multiplier for the max/min eigenvalue; specifies the minimal accepted quality of image corners | |
| min_distance | Limit, specifying the minimum possible distance between the returned corners; Euclidian distance is used | |
| block_size | Size of the averaging block, passed to the underlying CornerMinEigenVal or CornerHarris used by the function | |
| use_harris | If nonzero, Harris operator (CornerHarris) is used instead of default CornerMinEigenVal | |
| k | Free parameter of Harris detector; used only if useHarris!=0 |
If useHarris=0, the function finds the corners with big eigenvalues in the image. The function first calculates the minimal eigenvalue for every source image pixel using the CornerMinEigenVal function and stores them in eigImage. Then it performs non-maxima suppression (only the local maxima in 3x3 neighborhood are retained). The next step rejects the corners with the minimal eigenvalue less than qualityLevel·max(eigImage(x,y)). Finally, the function ensures that the distance between any two corners is not smaller than minDistance. The weaker corners (with a smaller min eigenvalue) that are too close to the stronger corners are rejected.
If useHarris=1, the function runs the Harris edge detector on the image. Similarly to CornerMinEigenVal, for each pixel it calculates a 2x2 gradient covariation matrix M over a blockSizexblockSize neighborhood. Then, it stores
to the destination image. Corners in the image can be found as the local maxima of the destination image.
| bool ossimOpenCVGoodFeaturesToTrack::loadState | ( | const ossimKeywordlist & | kwl, | |
| const char * | prefix = 0 | |||
| ) | [virtual] |
Method to the load (recreate) the state of an object from a keyword list. Return true if ok or false on error.
1.6.1
