opentl::modalities::TemplateMap Class Reference

Processing functions related to the template visual feature (cvdata::TemplateMap). More...

Inherits opentl::modalities::Modality.

List of all members.

Public Types
Public Member Functions
int	buildTemplateMap (const TargetPtrVector &targets)
	Collect offline template by sampling pixels from the opengl texture image, and back-warping points onto the 3D mesh.
virtual modalities::Modality *	clone () const
	Clone (it calls the Deep Copy Constructor).
opentl::core::cvdata::TemplateMap *	getTmapData (int targetId)
	Return the template model of a given target.
void	init ()
	Memory allocation and initialization (common to both constructors).
int	LossDetect (const TargetPtrVector &targets)
	Detect target loss, by computing the NCC over the full template.
virtual int	matchFeatLevel (const TargetPtrVector &targets, T_MEAS_FEATPtrVector &outputMeas, std::size_t partitionIdx)
	matchFeatLevel. Match template gray level values with underlying image values (multi-resolution) The overall similarity function can be: Sum of Squared Differences (SSD), Normalized Cross-Correlation (NCC), Mutual Information (MI).
virtual int	matchObjLevel (const TargetPtrVector &targets, T_MEAS_OBJPtrVector &outputMeas, std::size_t partitionIdx)
	matchObjLevel. Find local maximum of feature-level likelihood (i.e. the template similarity function)
virtual int	preProcess (const opentl::core::cvdata::Image &image)
	Get the multi-resolution image pyramid.
void	resetOnlineTemplate (const TargetPtrVector &targets)
	Reset the on-line template to the off-line values.
virtual int	sampleModelFeatures (const TargetPtrVector &targets)
	Compute visible points from the template map at pose p (occlusion query).
	TemplateMap (const TemplateMap &tmap)
	Deep Copy Constructor.
	TemplateMap (opentl::modelprojection::Warp *warp, int camIdx)
	Constructor.
int	updateAllTemplate (const TargetPtrVector &targets)
	Update the complete template gray values (on-line and off-line) from the pre-processed image pyramid.
virtual int	updateModelFeatures (const TargetPtrVector &targets)
	Update the on-line observed gray values (= feature) from the multi-resolution image pyramid.
void	updateOnlineTemplate (const TargetPtrVector &targets, std::vector< boost::shared_ptr< opentl::core::cvdata::Image > > &imageData)
	Update the on-line template gray values from 4 resolution images.
int	warpTemplate (const TargetPtrVector &targets)
	Warp all visible template points.
virtual	~TemplateMap ()
	Destructor.
Protected Attributes
T_MEAS_FEATPtrVector	mFeatLevelMeas
	Internal storage for feature level measurements NOTE: this is needed by the static function "staticSimilarityEval" (for the simplex optimizer).
TargetPtrVector	mTmpTarget
	Temporary state NOTE: this is needed by the static function "staticSimilarityEval" (for the simplex optimizer).

---

Detailed Description

Processing functions related to the template visual feature (cvdata::TemplateMap).

---

Member Enumeration Documentation

enum opentl::modalities::TemplateMap::OfflineParameters

Common flags to all modalities: they specify which field will be filled in the output measurement, inside the matchXLevel() function. Default values = all true.

Enumerator:

param_sampleTemplateFromModel	(bool) If we set template points locally, whether to sample them from model, or load them from file.
param_computeJacobians	(bool) Whether to compute template point Jacobians (using Gauss-Newton) or not (using matchObjLevel).
param_maxPoints	(int) In order to generate a maximum number of template points. (default = -1 -> Unlimited number)
param_nBins	(int) Number of histogram bins (for Mutual Information only).
param_nRes	(int) Number of resolutions.
param_debugShow	(bool) Show debug window (optimization sample, etc).
param_templateFilenames	(std::vector(std::string) ) Filenames (indexed by target ID) where to load/store model template points
OFFLINE_COUNT

Reimplemented from opentl::modalities::Modality.

enum opentl::modalities::TemplateMap::OnlineParameters

Enumerator:

param_featLevelCov	(double) Feature-level covariance (gray-values).
param_objLevelCov	(double) Object-level covariance (incremental pose-space).
param_fixedNumberIterations	(int) Fixed number of iterations for the optimization algorithm (default = -1 -> Variable number)
param_simFunc	(SimFuncType) Similarity function for template matching.
param_updateTemplate	(bool) Whether to update on-line template values.
param_simplexDelta	(std::vector(std::vector(double) ) ) Initial simplexes (for optimization).
param_smoothGauss	(std::vector(int) ) Gauss filter size (for multi-resolution).
param_subsample	(std::vector(int) ) Subsampling factor (for faster optimization).
param_minNCC	(double) Threshold for the final NCC value (loss detection).
param_woff	(double) Weight for off-line/on-line template fusion.
param_noisySample	(bool) Switch the subsampling index (noisy optimization) or not.
ONLINE_COUNT

Reimplemented from opentl::modalities::Modality.

enum opentl::modalities::TemplateMap::SimFuncType

Enumerator:

MI
SSD
NCC

---

Constructor & Destructor Documentation

opentl::modalities::TemplateMap::TemplateMap	(	opentl::modelprojection::Warp *	warp,
		int	camIdx
	)

Constructor.

opentl::modalities::TemplateMap::TemplateMap

(

const TemplateMap &

tmap

)

Deep Copy Constructor.

virtual opentl::modalities::TemplateMap::~TemplateMap

(

)

[virtual]

Destructor.

---

Member Function Documentation

int opentl::modalities::TemplateMap::buildTemplateMap

(

const TargetPtrVector &

targets

)

Collect offline template by sampling pixels from the opengl texture image, and back-warping points onto the 3D mesh.

Parameters:

targets

Input target vector

virtual modalities::Modality* opentl::modalities::TemplateMap::clone

(

)

const [virtual]

Clone (it calls the Deep Copy Constructor).

Implements opentl::modalities::Modality.

opentl::core::cvdata::TemplateMap* opentl::modalities::TemplateMap::getTmapData

(

int

targetId

)

[inline]

Return the template model of a given target.

Parameters:

targetId

Unique target ID number

void opentl::modalities::TemplateMap::init

(

)

[virtual]

Memory allocation and initialization (common to both constructors).

Reimplemented from opentl::modalities::Modality.

int opentl::modalities::TemplateMap::LossDetect

(

const TargetPtrVector &

targets

)

Detect target loss, by computing the NCC over the full template.

Parameters:

targets

Input target vector

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

matchFeatLevel. Match template gray level values with underlying image values (multi-resolution) The overall similarity function can be: Sum of Squared Differences (SSD), Normalized Cross-Correlation (NCC), Mutual Information (MI).

Parameters:

	targets	Input vector of targets
	outputMeas	Output feature-level measurements (gray-level pairs, Jacobians and UNIQUE residual = overall template similarity) NOTE: The second index of outputMeas (state inside the target) is not used, and always set to 0.

Reimplemented from opentl::modalities::Modality.

virtual int opentl::modalities::TemplateMap::matchObjLevel	(	const TargetPtrVector &	targets,
		T_MEAS_OBJPtrVector &	outputMeas,
		std::size_t	partitionIdx
	)			[virtual]

matchObjLevel. Find local maximum of feature-level likelihood (i.e. the template similarity function)

Parameters:

	targets	Input vector of targets
	outputMeas	Output object-level measurements (predicted and estimated pose, and residual = incremental pose) NOTE: The second index of outputMeas (state inside the target) is not used, and always set to 0.

Reimplemented from opentl::modalities::Modality.

virtual int opentl::modalities::TemplateMap::preProcess

(

const opentl::core::cvdata::Image &

image

)

[virtual]

Get the multi-resolution image pyramid.

Parameters:

sensData

Input sensor data

void opentl::modalities::TemplateMap::resetOnlineTemplate

(

const TargetPtrVector &

targets

)

Reset the on-line template to the off-line values.

Parameters:

targets

Input target vector

virtual int opentl::modalities::TemplateMap::sampleModelFeatures

(

const TargetPtrVector &

targets

)

[virtual]

Compute visible points from the template map at pose p (occlusion query).

Parameters:

targets

Input target vector

Reimplemented from opentl::modalities::Modality.

int opentl::modalities::TemplateMap::updateAllTemplate

(

const TargetPtrVector &

targets

)

Update the complete template gray values (on-line and off-line) from the pre-processed image pyramid.

Parameters:

targets

Input target vector

virtual int opentl::modalities::TemplateMap::updateModelFeatures

(

const TargetPtrVector &

targets

)

[virtual]

Update the on-line observed gray values (= feature) from the multi-resolution image pyramid.

Parameters:

targets

Input target vector

Reimplemented from opentl::modalities::Modality.

void opentl::modalities::TemplateMap::updateOnlineTemplate	(	const TargetPtrVector &	targets,
		std::vector< boost::shared_ptr< opentl::core::cvdata::Image > > &	imageData
	)

Update the on-line template gray values from 4 resolution images.

Parameters:

	targets	Input target vector
	imageData	Input multi-resolution images from which to sample visible points

int opentl::modalities::TemplateMap::warpTemplate

(

const TargetPtrVector &

targets

)

Warp all visible template points.

Parameters:

targets

Input target vector

---

Member Data Documentation

T_MEAS_FEATPtrVector opentl::modalities::TemplateMap::mFeatLevelMeas [protected]

Internal storage for feature level measurements NOTE: this is needed by the static function "staticSimilarityEval" (for the simplex optimizer).

TargetPtrVector opentl::modalities::TemplateMap::mTmpTarget [protected]

Temporary state NOTE: this is needed by the static function "staticSimilarityEval" (for the simplex optimizer).