jafar::rtslam::QuickHarrisDetector Class Reference

Quick Harris detector class. More...

---

Detailed Description

Quick Harris detector class.

Author:

jsola

This class detects the strongest Harris point inside a given region of interest.

The class is called Quick because the algorithm is accelerated using 5 strategies:

• the use of a simple derivative mask [-1 0 1] that avoids products and minimizes sums.
• the use of a square convolution mask of fixed amplitude = 1.
• this mask allows us to compute the convolution via integral images of I_xx, I_xy and I_yy.
• we extract the best point, so we don't need to perform theresholding and sub-maxima suppression (both expensive).
• we purposely use small regions of interest.

Because of simplifications 1. 2. and 3., the result is sub-optimal in the sense of Harris standards, but it gives strong corner points that can be tracked by means of correlation (zncc for example).

Definition at line 58 of file quickHarrisDetector.hpp.

#include <quickHarrisDetector.hpp>

List of all members.

Classes
struct	HQuickData
Public Member Functions
	QuickHarrisDetector (int convolutionBoxSize=5, float threshold=15.0, float edge=2.0)
virtual bool	detectIn (image::Image const &image, feat_img_pnt_ptr_t featPtr, const image::ConvexRoi *roiPtr=0)
Private Member Functions
void	quickDerivatives (const image::Image &image, image::ConvexRoi &roi)
bool	quickConvolutionWithBestPoint (const image::ConvexRoi &roi, int pixMax[2], float &scoreMax)
void	writeHarrisImagesAsPPM (image::ConvexRoi &roi)
Private Attributes
int	m_derivationSize
int	m_convolutionSize
float	m_threshold
float	m_edge
HQuickData *	m_quickData
double	normCoeff
int	m_nConvCoeffs
int	shift_conv
int *	shift_convs
int *	convCoeffs
int	nConvCoeffs
bool	nConvCoeffsCenter
HQuickData **	int_upLeft
HQuickData **	int_upRight
HQuickData **	int_downLeft
HQuickData **	int_downRight

---

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

• modules/rtslam/include/rtslam/quickHarrisDetector.hpp