This Class is design for CSV reading features. More...

#include <csvKeypointDetector.h>

Inheritance diagram for isae::CsvKeypointDetector:

Collaboration diagram for isae::CsvKeypointDetector:

Public Member Functions
	CsvKeypointDetector (int n, int n_per_cell, double max_matching_dist=64)

void	customDetectAndCompute (const cv::Mat &img, const cv::Mat &mask, std::vector< std::shared_ptr< AFeature >> &features) override

void	computeDescriptor (const cv::Mat &img, std::vector< std::shared_ptr< AFeature >> &features) override
	Virtual function to compute descriptors for a set of features. More...

void	init () override
	Virtual function to initialize the feature detector. More...

double	computeDist (const cv::Mat &desc1, const cv::Mat &desc2) const override
	Virtual function to compute the distance between two feature descriptors. More...

Public Member Functions inherited from isae::ACustomFeatureDetector
	ACustomFeatureDetector (int n, int n_per_cell)

void	detectAndCompute (const cv::Mat &img, const cv::Mat &mask, std::vector< cv::KeyPoint > &keypoints, cv::Mat &descriptors, int n_points=0)
	Virtual function to detect and compute features in an image. More...

std::vector< std::shared_ptr< AFeature > >	detectAndComputeGrid (const cv::Mat &img, const cv::Mat &mask, std::vector< std::shared_ptr< AFeature >> existing_features=std::vector< std::shared_ptr< AFeature >>())
	Virtual function to detect and compute features in a grid (bucketting). More...

Public Member Functions inherited from isae::AFeatureDetector
EIGEN_MAKE_ALIGNED_OPERATOR_NEW	AFeatureDetector ()

	AFeatureDetector (int n, int n_per_cell)

	~AFeatureDetector ()

size_t	getNbDesiredFeatures ()

double	getMaxMatchingDist () const

bool	getFeaturesInBox (int x, int y, int w, int h, const std::vector< std::shared_ptr< AFeature >> &features, std::vector< std::shared_ptr< AFeature >> &features_in_box) const
	Get features from a feature set in a bounding box defined by (x, y, w, h). More...

void	deleteUndescribedFeatures (std::vector< std::shared_ptr< AFeature >> &features)

Additional Inherited Members
Static Public Member Functions inherited from isae::AFeatureDetector
static void	KeypointToFeature (std::vector< cv::KeyPoint > keypoints, cv::Mat descriptors, std::vector< std::shared_ptr< AFeature >> &features, const std::string &featurelabel="pointxd")
	Convert OpenCV keypoints and descriptors to a vector of AFeature pointers. More...

static void	FeatureToKeypoint (std::vector< std::shared_ptr< AFeature >> features, std::vector< cv::KeyPoint > &keypoints, cv::Mat &descriptors)
	Convert a vector of AFeature pointers to OpenCV keypoints and descriptors. More...

static void	FeatureToP2f (std::vector< std::shared_ptr< AFeature >> features, std::vector< cv::Point2f > &p2fs)
	Convert a vector of AFeature pointers to a vector of cv::Point2f. More...

Protected Member Functions inherited from isae::ACustomFeatureDetector
const int	getDefaultNorm () const

Protected Attributes inherited from isae::ACustomFeatureDetector
int	_defaultNorm

Protected Attributes inherited from isae::AFeatureDetector
int	_n_total
	the maximum amount of features the detector should find for any given image More...

int	_n_per_cell
	the number of features per cell More...

double	_max_matching_dist
	distance threshold for matching More...

Detailed Description

This Class is design for CSV reading features.

This is how it should be used: -> The convention is: timestamp.csv for each image -> The variable _folder_path indicates the folder where the csv are stored -> in customdetectAndCompute the cv::Mat contains a double with the timestamp of the image

Thus SLAMCore should be slightly edited to create the timestamp cv::Mat and pass it as argument in detectfeatures Moreover, klt tracking cannot be used because detectAndComputeAdditionnal won't work

Example:

CsvKeypointDetector csv_detector(1000); cv::Mat ts_mat = cv::Mat::zeros(1,1,CV_32F); ts_mat.at<double>(0,0) = (double)f->getTimestamp(); csv_detector.customDetectAndCompute(ts_mat, ts_mat, features); f->getSensors().at(i)->addFeatures("pointxd", features);

Constructor & Destructor Documentation

◆ CsvKeypointDetector()

isae::CsvKeypointDetector::CsvKeypointDetector	(	int	n,
		int	n_per_cell,
		double	max_matching_dist = `64`
	)

inline

Member Function Documentation

◆ computeDescriptor()

void isae::CsvKeypointDetector::computeDescriptor	(	const cv::Mat &	img,
		std::vector< std::shared_ptr< AFeature >> &	features
	)

overridevirtual

Virtual function to compute descriptors for a set of features.

Parameters

img	The input image from which to compute descriptors.
features	A vector of features for which to compute descriptors.

Implements isae::ACustomFeatureDetector.

◆ computeDist()

double isae::CsvKeypointDetector::computeDist	(	const cv::Mat &	desc1,
		const cv::Mat &	desc2
	)		const

overridevirtual

Virtual function to compute the distance between two feature descriptors.

Parameters

desc1	The first feature descriptor.
desc2	The second feature descriptor.

Implements isae::AFeatureDetector.

◆ customDetectAndCompute()

void isae::CsvKeypointDetector::customDetectAndCompute	(	const cv::Mat &	img,
		const cv::Mat &	mask,
		std::vector< std::shared_ptr< AFeature >> &	features
	)

overridevirtual

Implements isae::ACustomFeatureDetector.

◆ init()

void isae::CsvKeypointDetector::init ( )

overridevirtual

Virtual function to initialize the feature detector.

This method should be called before using the detector.

Implements isae::AFeatureDetector.

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

/home/deos/ce.debeunne/colcon_ws/src/SaDVIO/cpp/include/isaeslam/featuredetectors/custom_detectors/csvKeypointDetector.h
/home/deos/ce.debeunne/colcon_ws/src/SaDVIO/cpp/src/featuredetectors/custom_detectors/csvKeypointDetector.cpp

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ CsvKeypointDetector()

Member Function Documentation

◆ computeDescriptor()

◆ computeDist()

◆ customDetectAndCompute()

◆ init()