opentl::modalities::SurfFeatures Class Reference

Inherits opentl::modalities::Modality.

List of all members.

Classes
class	SURFKeyframe
Public Types
Public Member Functions
virtual modalities::Modality *	clone () const
	Clone this class and all potential childs RECURSIVELY!! (deep copy).
virtual void	init ()
	Initialize class.
virtual int	matchFeatLevel (const TargetPtrVector &targets, T_MEAS_FEATPtrVector &outputMeas, std::size_t partitionIdx)
	Feature-level matching.
virtual int	matchObjLevel (const TargetPtrVector &targets, T_MEAS_OBJPtrVector &outputMeas, std::size_t partitionIdx)
	Feature-level matching.
virtual int	preProcess (const opentl::core::cvdata::Image &image, const std::vector< std::vector< int > > &preProcessROIs)
	Detect SURF keypoints in the current image.
virtual int	sampleModelFeatures (const TargetPtrVector &targets)
	Detect SURF keypoints from the texture map, and back-project them in object space NOTE: If this function is called with multiple targets, it will add a keyframe for each of them. Therefore, in this case the option "addKeyframes" MUST be set true, otherwise an exception will be raised.
	SurfFeatures (const SurfFeatures &c)
	Copy constructor.
	SurfFeatures (opentl::modelprojection::WarpBack *warpBack, int camIdx, opentl::modelprojection::GLRenderer *renderer)
	Constructor.
virtual	~SurfFeatures ()
	Destructor.

---

Member Enumeration Documentation

enum opentl::modalities::SurfFeatures::OfflineParameters

Enumerator:

OFFLINE_COUNT

Reimplemented from opentl::modalities::Modality.

enum opentl::modalities::SurfFeatures::OnlineParameters

Enumerator:

addKeyframes	(bool) Whether to add a new keyframe, each time sampleModelFeatures is called. Default = false.
matchFeatMinInliers	(unsigned int) Minimum number of inliers for successful matching. Default = 10. Minimum = 8 (for RANSAC)
matchFeatRansac	(bool) Whether to apply RANSAC with planar homography, for rejecting outliers. Default = true.
matchFeatCov	(double) Inverse covariance of feature-level residuals (R)
matchObjCov	(double) Covariance of object-level residuals (R)
useFLANN	(bool) Whether to use approximate nearest neighbor search for matching
drawCorresp	(bool) Whether to draw the correspondences after matching
ONLINE_COUNT

Reimplemented from opentl::modalities::Modality.

---

Constructor & Destructor Documentation

opentl::modalities::SurfFeatures::SurfFeatures	(	opentl::modelprojection::WarpBack *	warpBack,
		int	camIdx,
		opentl::modelprojection::GLRenderer *	renderer
	)

Constructor.

opentl::modalities::SurfFeatures::SurfFeatures

(

const SurfFeatures &

c

)

Copy constructor.

virtual opentl::modalities::SurfFeatures::~SurfFeatures

(

)

[virtual]

Destructor.

---

Member Function Documentation

virtual modalities::Modality* opentl::modalities::SurfFeatures::clone

(

)

const [inline, virtual]

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

Implements opentl::modalities::Modality.

virtual void opentl::modalities::SurfFeatures::init

(

)

[virtual]

Initialize class.

Reimplemented from opentl::modalities::Modality.

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

Feature-level matching.

Parameters:

	targets	Input vector of targets
	outputMeas	Output matched SURF features, for each target and state hypothesis
	partitionIdx	Input partition number (for multi-threading)

Reimplemented from opentl::modalities::Modality.

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

Feature-level matching.

Parameters:

	targets	Input vector of targets
	outputMeas	Output estimated state for each target
	partitionIdx	Input partition number (for multi-threading)

Reimplemented from opentl::modalities::Modality.

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

Detect SURF keypoints in the current image.

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::SurfFeatures::sampleModelFeatures

(

const TargetPtrVector &

targets

)

[virtual]

Detect SURF keypoints from the texture map, and back-project them in object space NOTE: If this function is called with multiple targets, it will add a keyframe for each of them. Therefore, in this case the option "addKeyframes" MUST be set true, otherwise an exception will be raised.

Reimplemented from opentl::modalities::Modality.