NormalDetector Class Reference

#include <NormalDetector.h>

Inheritance diagram for NormalDetector:
Inheritance graph
[legend]

List of all members.

Public Member Functions

unsigned int getWindowSize () const
 NormalDetector (const PeakFinder *peak, unsigned int scales=5, double sigma=1.6, double step=1.4, unsigned int window=3, SmoothingFilterFamily filterType=BESSEL)
void setWindowSize (unsigned int size)

Protected Member Functions

virtual void computeDifferentialBank ()=0
virtual unsigned int computeInterestPoints (const LaserReading &reading, const std::vector< double > &signal, std::vector< InterestPoint * > &point, std::vector< std::vector< unsigned int > > &indexes, std::vector< unsigned int > &maxRangeMapping) const
virtual void computeSignal (const LaserReading &reading, std::vector< double > &signal, std::vector< unsigned int > &maxRangeMapping) const

Protected Attributes

unsigned int m_windowSize

Detailed Description

Representation of a general detector based on the normal signal. The class represents a general detector based on the normal signal. It computes the normal signal and define the general interface for detection. The concrete detectors provides the precise differential invariant.

Author:
Gian Diego Tipaldi

Definition at line 43 of file NormalDetector.h.


Constructor & Destructor Documentation

NormalDetector::NormalDetector ( const PeakFinder peak,
unsigned int  scales = 5,
double  sigma = 1.6,
double  step = 1.4,
unsigned int  window = 3,
SmoothingFilterFamily  filterType = BESSEL 
)

Constructor. Constructs and initialize a general detector based on a normal signal.

Parameters:
peak The peak finder used to detect maxima in the signal.
scales The number of different scales to consider.
sigma The standard deviation of the smoothing kernel for the initial scale ($ t_0 $ in the paper).
step The scale increment at every new scale ($ t_i $ in the paper). The standard deviation of the kernel at scale $ s $ is $ t_0 \cdot (t_i)^s $
window The window size for the local line fitting.
filterType The smoothing kernel used in the detector.

Definition at line 6 of file NormalDetector.cpp.


Member Function Documentation

virtual void NormalDetector::computeDifferentialBank (  )  [protected, pure virtual]

Precomputes the bank of differential operators. It defines which family of interest point detector to use (blob, edge, ridge, ...).

Implements MultiScaleDetector.

Implemented in NormalBlobDetector, and NormalEdgeDetector.

unsigned int NormalDetector::computeInterestPoints ( const LaserReading reading,
const std::vector< double > &  signal,
std::vector< InterestPoint * > &  point,
std::vector< std::vector< unsigned int > > &  indexes,
std::vector< unsigned int > &  maxRangeMapping 
) const [protected, virtual]

Computes the interst point locations and (when possible) orientation. The points are extracted from the laser reading according to the indexes.

Implements MultiScaleDetector.

Definition at line 72 of file NormalDetector.cpp.

void NormalDetector::computeSignal ( const LaserReading reading,
std::vector< double > &  signal,
std::vector< unsigned int > &  maxRangeMapping 
) const [protected, virtual]

Computes the monodimensional signal from which extracts the features.

Implements MultiScaleDetector.

Definition at line 22 of file NormalDetector.cpp.

unsigned int NormalDetector::getWindowSize (  )  const [inline]

Gets the window size for the local line fitting.

Definition at line 62 of file NormalDetector.h.

void NormalDetector::setWindowSize ( unsigned int  size  )  [inline]

Sets the window size for the local line fitting.

Definition at line 58 of file NormalDetector.h.


Member Data Documentation

unsigned int NormalDetector::m_windowSize [protected]

The window size for the local line fitting.

Definition at line 71 of file NormalDetector.h.


The documentation for this class was generated from the following files:
 All Classes Files Functions Variables Typedefs Enumerations Enumerator Defines


flirtlib
Author(s): Bhaskara Marthi, Gian Diego Tipaldi
autogenerated on Fri Jan 11 11:15:48 2013