opentl::modalities::HoughLines Class Reference

Inherits opentl::modalities::Modality.

List of all members.

Public Types
Public Member Functions
virtual modalities::Modality *	clone () const
	Clone this class and all potential childs RECURSIVELY!! (deep copy).
opentl::core::cvdata::VisContourSamplePts *	getContourData (int s=0)
	HoughLines (const HoughLines &c)
	Deep Copy Constructor.
	HoughLines (const ObjModelPtrVector &objModels, opentl::modelprojection::Warp *warp, opentl::modelprojection::GLScene *scene, opentl::modelprojection::GLRenderer *glRender, int camIdx, modelprojection::ContourSampler *contourSampler=NULL)
	Constructor.
virtual void	init ()
	Allocate data structures required by this class.
virtual int	matchFeatLevel (const TargetPtrVector &targets, T_MEAS_FEATPtrVector &outputMeas, std::size_t partitionIdx)
	Matching on feature level match projected edge lines + hough transform with detected image hough lines.
virtual int	preProcess (const opentl::core::cvdata::Image &image, const std::vector< std::vector< int > > &preProcessROIs)
	Compute the Hough map of I (e.g. with Gray+Canny+HoughLines2), and store it into mImageDebugOutput (when Debug is enabled --matchF_enableDebugOutput--).
virtual int	sampleModelFeatures (const TargetPtrVector &targets)
	Do visible edge sample hough lines computation.
void	setMeasStd (double std)
virtual	~HoughLines ()
	Destructor.
Public Attributes
opentl::core::cvdata::Image *	mImageDebugOutput
	Debug Image output.

---

Member Enumeration Documentation

enum opentl::modalities::HoughLines::HougLineDetectorType

Possible Hough Lines modes for image feature detection.

Enumerator:

HL_STD	For this moment only HL_PROBABILISTIC is available
HL_PROBABILISTIC
HL_MULTISCALE
HL_GRADIENT

enum opentl::modalities::HoughLines::OfflineParameters

Enumerator:

houghlines_generate_contourSampler	(bool) If true, create the visibility algorithm internally; else, use a pre-defined one (contourSampler)
houghlines_construct_loadShaderCodeFromFile	(bool) Load Shader code from File
houghlines_construct_sampleSilhouetteEdgesOnly	(bool) Sample silhouette edged only
houghlines_construct_MaxSamplePointsPerTarget	(int) maximum sample points per target
houghlines_sample_discardBackgroundEdgeWithinPixelRange	(unsigned int) discard background edge within pixel range
houghlines_sample_thetaDegRidge
houghlines_sample_thetaDegValley
houghlines_detectorType	Define the type of the HL detector Standard, Probabilistic or Multi-Scale, for the moment only the PROBABILISTIC Method is implemented.
houghlines_rho_resolution	Distance resolution in pixel-related units.
houghlines_theta_resolution	Angle resolution measured in radians.
houghlines_accum_threshold	Threshold parameter. A line is returned by the function if the corresponding accumulator value is greater than threshold.
houghlines_min_segment_length	the Minimum length of detected segments.
houghlines_max_segment_gap	the maximum gap between line segments lying on the same line to treat them as a single line segment (i.e. to join them).
houghlines_search_window_factor	the % of the Screen bounding_box area that is used as a search window e.g. 0.1 is equivalent to 10% of the object model bounding box area.
houghlines_max_error_slope	the maximum slope error (in order to match edges in radians, always positive ).
OFFLINE_COUNT

Reimplemented from opentl::modalities::Modality.

enum opentl::modalities::HoughLines::OnlineParameters

Enumerator:

houghlines_sample_computeScreenPointJacobians	(bool) compute screen point jacobians
houghlines_preProcess_cannyThreshold1	(double) canny threshold1
houghlines_preProcess_cannyThreshold2	(double) canny threshold2
houghlines_preProcess_cannyAperture_size	Aperture parameter for the Sobel operator.
houghlines_matchF_alpha	(double) Missing detection rate
houghlines_matchF_enableDebugOutput	(bool) enable debug output
houghlines_matchFeatLevel_useFixedCov	(bool) use fixed covariance
houghlines_matchFeatLevel_fixedCov	(double) fixed covariance value
houghlines_CovarianceMatrixValues	(opentl::math::Vector4) Values of the main diagonal of Covariance Matrix: Rslope_error(grad),Rx_cm_error(pixels),Ry_cm_error(pixels),Rlength_error(pixels)
ONLINE_COUNT

Reimplemented from opentl::modalities::Modality.

---

Constructor & Destructor Documentation

opentl::modalities::HoughLines::HoughLines	(	const ObjModelPtrVector &	objModels,
		opentl::modelprojection::Warp *	warp,
		opentl::modelprojection::GLScene *	scene,
		opentl::modelprojection::GLRenderer *	glRender,
		int	camIdx,
		modelprojection::ContourSampler *	contourSampler = NULL
	)

Constructor.

opentl::modalities::HoughLines::HoughLines

(

const HoughLines &

c

)

Deep Copy Constructor.

virtual opentl::modalities::HoughLines::~HoughLines

(

)

[virtual]

Destructor.

---

Member Function Documentation

virtual modalities::Modality* opentl::modalities::HoughLines::clone

(

)

const [virtual]

Clone this class and all potential childs RECURSIVELY!! (deep copy).

Implements opentl::modalities::Modality.

opentl::core::cvdata::VisContourSamplePts* opentl::modalities::HoughLines::getContourData

(

int

s = 0

)

[inline]

virtual void opentl::modalities::HoughLines::init

(

)

[virtual]

Allocate data structures required by this class.

Reimplemented from opentl::modalities::Modality.

virtual int opentl::modalities::HoughLines::matchFeatLevel	(	const TargetPtrVector &	targets,
		T_MEAS_FEATPtrVector &	outputMeas,
		std::size_t	partitionIdx
	)			[virtual]

Matching on feature level

• match projected edge lines + hough transform with detected image hough lines.

Parameters:

	targets	Vector of targets
	outputMeas	Feature-space measurements and residuals (one per target and internal state)

Reimplemented from opentl::modalities::Modality.

virtual int opentl::modalities::HoughLines::preProcess	(	const opentl::core::cvdata::Image &	image,
		const std::vector< std::vector< int > > &	preProcessROIs
	)			[virtual]

Compute the Hough map of I (e.g. with Gray+Canny+HoughLines2), and store it into mImageDebugOutput (when Debug is enabled --matchF_enableDebugOutput--).

Parameters:

	image	Input sensor data (e.g. camera image in RGB)
	preProcessROIs	Regions of interest (x0,y0,width,height), per target

Reimplemented from opentl::modalities::Modality.

virtual int opentl::modalities::HoughLines::sampleModelFeatures

(

const TargetPtrVector &

targets

)

[virtual]

Do visible edge sample hough lines computation.

Parameters:

targets

Vector of targets

Reimplemented from opentl::modalities::Modality.

void opentl::modalities::HoughLines::setMeasStd

(

double

std

)

[inline]

---

Member Data Documentation

opentl::core::cvdata::Image* opentl::modalities::HoughLines::mImageDebugOutput

Debug Image output.