Plugin lcvfeatures2d

This module contains elements for feature detection and matching. It resembles open cv's features 2D module.

import lcvfeatures2d 1.0

Summary

TypeKeypointListView	View for a list of keypoints.
TypeFeatureDetectorSelection	Default text color
TypeDescriptorExtractorSelection	Contains a selection for a descriptor extractor.
TypeFeatureObjectList	List of detected features for an object.
TypeSelectionArea	Area that can be selected through a rectangle
TypeKeyPoint	Wrapper for a found keypoint.
TypeFeatureDetector	Detector of features within an image. This is an abstract type.
TypeFastFeatureDetector	FAST FeatureDetector
TypeBriskFeatureDetector	Brisk FeatureDetector
TypeOrbFeatureDetector	Orb FeatureDetector
TypeMSerFeatureDetector	MSer FeatureDetector
TypesimpleBlobDetector	Implements a simple algorithm for extracting blobs from an image.
TypeDescriptorExtractor	Abstract base class for computing descriptors from an images keypoints.
TypeBriskDescriptorExtractor	Decsriptor extractor for the Brisk algorithm.
TypeOrbDescriptorExtractor	Decsriptor extractor for the Orb algorithm.
TypeDMatchVector	Vector of matches.
TypeDescriptorMatcher	Abstract base class for matching keypoint descriptors.
TypeBruteForceMatcher	Finds the closest descriptor match.
TypeFlannBasedMatcher	Finds the closest descriptor k matches.
TypeDrawMatches	Draws matches between two sets of keypoints that were detected and matched.
TypeDescriptorMatchFilter	Filter for descriptor matches.
TypeKeypointsToSceneMap	Contains a keypoints to scene map.
TypeMatchesToLocalKeypoint	Triggered when output is changed
TypeKeypointHomography	Performs a homography based on the keypoints to scene.

KeypointListView type

Inherits

Column

Property	color headerColor
Property	color headerTextColor
Property	color backgroundColor
Property	color itemBackgroundColor
Property	color selectedItemBackgroundColor
Property	MathDraw keypointHighlighter
Property	FeatureDetector detector
Property	DescriptorExtractor extractor
Property	variant descriptorValues
Property	alias currentIndex

Signal	keypointMouseEnter(int index, point pt)
Signal	keypointMouseExit(int index, point pt)
Signal	keypointMouseSelected(int index, point pt)

View for a list of keypoints.

color headerColor property

Color for the header of the list.

color headerTextColor property

Color for the text.

color backgroundColor property

Main background color.

color itemBackgroundColor property

Background color for each item.

color selectedItemBackgroundColor property

Background color of selected item.

MathDraw keypointHighlighter property

Draws keypoints on a highlighter.

FeatureDetector detector property

Detector used.

DescriptorExtractor extractor property

Extractor used.

variant descriptorValues property

Given descriptor values.

keypointMouseEnter(int index, point pt) signal

Triggered when the mouse entered a keypoint region.

keypointMouseExit(int index, point pt) signal

Triggered when the mouse exited a keypoint section.

keypointMouseSelected(int index, point pt) signal

Triggered when a keypoint region was selected.

alias currentIndex property

Current index of the selected keypoint.

FeatureDetectorSelection type

Inherits

QtQuick.Rectangle

Property	string stateId
Property	Mat detectorInput
Property	alias selectedName
Property	alias selectedDetector
Property	alias selectedPanelModel
Property	alias selectedIndex
Property	color backgroundColor
Property	color textColor
Property	int dropBoxHeight

Signal	configurationUpdate
Signal	comboClicked()

string stateId property

Assigned when staticLoad is active.

configurationUpdate signal

Signal for configuration update.

Mat detectorInput property

Input used for the detector.

alias selectedName property

Name of the detector.

alias selectedDetector property

Selected detector.

alias selectedPanelModel property

Selected panel model.

alias selectedIndex property

Selected index.

color backgroundColor property

Background color used throughout the selections.

color textColor property

Default text color

int dropBoxHeight property

Height of the dropBox when selecting diferent feature detector.

comboClicked() signal

Emited when selection happens.

DescriptorExtractorSelection type

Inherits

QtQuick.Rectangle

Property	string stateId
Property	FeatureDetector detector
Property	alias selectedName
Property	alias selectedExtractor
Property	alias selectedPanelModel
Property	alias selectedIndex
Property	color backgroundColor
Property	color textColor
Property	int dropBoxHeight

Signal	configurationUpdate
Signal	comboClicked()

Contains a selection for a descriptor extractor.

string stateId property

Assigned when staticLoad is active.

configurationUpdate signal

Signal for configuration update.

FeatureDetector detector property

Detector used.

alias selectedName property

Name of the extractor.

alias selectedExtractor property

Selected extractor.

alias selectedPanelModel property

Selected panel model.

alias selectedIndex property

Selected index.

color backgroundColor property

Background color used throughout the selections.

color textColor property

Default text color.

int dropBoxHeight property

Height of the dropBox when selecting diferent feature detector.

comboClicked() signal

Emited when selection happens.

FeatureObjectList type

Inherits

QtQuick.Rectangle

Property	FeatureDetector featureDetector
Property	DescriptorExtractor descriptorExtractor
Property	alias objectList
Property	alias selectedIndex
Property	FeatureDetector trainFeatureDetector
Property	DescriptorExtractor trainDescriptorExtractor
Property	FeatureDetector queryFeatureDetector
Property	var imageSource
Property	var querySource
Property	real minMatchDistanceCoeff
Property	real matchNndrRation
Property	KeyPointVector drawQueryKeypoints
Property	int drawMatchIndex
Property	string stateId

Signal	objectAdded(Mat descriptors, var points, var color)
Signal	objectListLoaded(MatList list, var keypoints, var corners, var colors)
Signal	objectListCreated()
Signal	objectListCreated()

List of detected features for an object.

FeatureDetector featureDetector property

FeatureDetector used.

DescriptorExtractor descriptorExtractor property

DescriptorExtractor used.

objectAdded(Mat descriptors, var points, var color) signal

Triggered when an object was added.

objectListLoaded(MatList list, var keypoints, var corners, var colors) signal

Triggered when the object list was loaded.

objectListCreated() signal

Triggered when the object list was created.

alias objectList property

Actual list.

alias selectedIndex property

Index of the selected item.

{qmlType:FeatureObjectMatch} {qmlInherits:QtQuick.Rectangle} {qmlBrief:Object matcher for a list.

FeatureDetector trainFeatureDetector property

FeatureDetector used for training.

DescriptorExtractor trainDescriptorExtractor property

DescriptorExtractor used for training.

FeatureDetector queryFeatureDetector property

FeatureDetector used for querying.

var imageSource property

Image source.

var querySource property

Query source.

real minMatchDistanceCoeff property

Property for the actual matcher.

real matchNndrRation property

Property for the actual matcher.

objectListCreated() signal

Emited when the list is created.

KeyPointVector drawQueryKeypoints property

Keypoints recieved from the trainFeatureDetector.

int drawMatchIndex property

Index where to draw the matches at.

{qmlProperty:Index of the training image matches}.

string stateId property

Static state id. See StaticItem for more details.

SelectionArea type

Inherits

QtQuick.MouseArea

Property	color selectionColor
Property	real selectionOpacity
Property	Rectangle highlightItem

Signal

selected(int x, int y, int width, int height)

Area that can be selected through a rectangle

color selectionColor property

Color of the selection.

real selectionOpacity property

Opacity of the selection.

selected(int x, int y, int width, int height) signal

Triggered when a selection happens.

Rectangle highlightItem property

Contains the rectangle of the highlighted item.

KeyPoint type

Inherits

QtObject

Property	Point2f pt
Property	float size
Property	float angle
Property	float response
Property	int octave
Property	int classId

Wrapper for a found keypoint.

Point2f pt property

Coordinates of the keypoint.

float size property

Diameter of the meaningful keypoint neighborhood.

float angle property

Angle the keypoint was detected at.

float response property

The response by which the most strong keypoints have been selected. Can be used for the further sorting or subsampling.

int octave property

Keypoint octave.

int classId property

Id of the detected class for the keypoint.

FeatureDetector type

Inherits

Item

Property	Mat input
Property	output
Property	Mat mask
Property	params
Property	keypoints

Detector of features within an image. This is an abstract type.

Mat input property

Image to detect the keypoints in.

output property

Drawn features from the input to another image.

Mat mask property

Limited amount of detections for a specific area.

params property

Parameters for detection.

keypoints property

Given keypoints.

FastFeatureDetector type

Inherits

FeatureDetector

FAST FeatureDetector

Initialization parameters:

• int threshold

• bool nonmaxSuppression

BriskFeatureDetector type

Inherits

FeatureDetector

Brisk FeatureDetector

Feature detector for the Brisk algorithm.

Initialization parameters:

• int thresh
• int octave
• float patternScale

OrbFeatureDetector type

Inherits

FeatureDetector

Orb FeatureDetector

Feature detector for the Orb algorithm.

Initialization parameters:

• int nfeatures
• float scaleFactor
• int nlevels
• int edgeThreshold
• int firstLevel
• int WTA_K
• int scoreType

MSerFeatureDetector type

Inherits

FeatureDetector

MSer FeatureDetector

Feature detector for the MSer algorithm:

• int delta
• int minArea
• int maxArea
• float maxVariation
• float minDiversity
• int maxEvolution
• real areaThreshold
• real minMargin
• int edgeBlurSize

simpleBlobDetector type

Inherits

Implements a simple algorithm for extracting blobs from an image.

Algorithm:

1. Convert the source image to binary images by applying thresholding with several thresholds from minThreshold (inclusive) to maxThreshold (exclusive) with distance thresholdStep between neighboring thresholds.

2. Extract connected components from every binary image by findContours and calculate their centers.

3. Group centers from several binary images by their coordinates. Close centers form one group that corresponds to one blob, which is controlled by the minDistBetweenBlobs parameter.

4. From the groups, estimate final centers of blobs and their radiuses and return as locations and sizes of keypoints.

This class performs several filtrations of returned blobs. You should set filterBy to true/false to turn the corresponding filtration on or off.

Params:

• filterByInertia
• filterByConvexity
• filterByColor
• filterByCircularity
• filterByArea

DescriptorExtractor type

Inherits

Item

Property	keypoints
Property	descriptors
Property	params
Property	isBinary

Abstract base class for computing descriptors from an images keypoints.

keypoints property

Detected keypoints of an image.

descriptors property

Computed result.

params property

Parameters given according to the type of descriptor extractor.

isBinary property

Wether this DescriptorExtractor is of binary type.

BriskDescriptorExtractor type

Inherits

DescriptorExtractor

Decsriptor extractor for the Brisk algorithm.

OrbDescriptorExtractor type

Inherits

DescriptorExtractor

Decsriptor extractor for the Orb algorithm.

Params:

• int patchSize

DMatchVector type

Inherits

Item

Vector of matches.

DescriptorMatcher type

Inherits

Item

Abstract base class for matching keypoint descriptors.

It has two groups of match methods: for matching descriptors of an image with another image or with an image set.

Params:

• queryDescriptors Query set of descriptors.
• knn Count of best matches found per each query descriptor or less if a query descriptor has less than k possible matches in total.

BruteForceMatcher type

Inherits

DescriptorMatcher

Finds the closest descriptor match.

Params:

• int normType
• bool crossCheck

FlannBasedMatcher type

Inherits

DescriptorMatcher

Finds the closest descriptor k matches.

Initialize params:

• KDTree

  • int trees

• HierarchicalClustering

• Lsh

  • int tableNumber
  • int keySize
  • int multiProbeLevel

DrawMatches type

Inherits

MatDisplay

Property	KeyPointVector keypoints1
Property	KeyPointVector keypoints2
Property	DMatchVector matches1to2
Property	int matchIndex

Draws matches between two sets of keypoints that were detected and matched.

You can specify the match index to focus on specific match when drawing.

KeyPointVector keypoints1 property

Keypoints from the first source.

KeyPointVector keypoints2 property

Keypoints from the second source

DMatchVector matches1to2 property

Matches from the first source to second one.

int matchIndex property

Draw matches at this specified index.

DescriptorMatchFilter type

Inherits

Item

Property	DMatchVector matches1to2
Property	DMatchVector matches1to2Out
Property	real minDistanceCoeff
Property	real maxDistance
Property	real nndrRatio

Filter for descriptor matches.

DMatchVector matches1to2 property

Matches from the first source to second one.

DMatchVector matches1to2Out property

Output of matches1to2.

real minDistanceCoeff property

Minimum distance that the match has to the actual outcome.

real maxDistance property

Maximum distance allowed betwen set of two matches.

real nndrRatio property

The match betwen the first match and it's next consecutive match.

KeypointsToSceneMap type

Inherits

QtObject

Property

int size()

Contains a keypoints to scene map.

int size() property

Size of the vector of the KeypointsToScene object.

MatchesToLocalKeypoint type

Inherits

QtObject

Property	DMatchVector matches1to2
Property	list trainKeypointVectors
Property	KeyPointVector queryKeypointVector
Property	KeyPointToSceneMap output

Signal	matches1to2Changed()
Signal	trainKeypointVectorsChanged()
Signal	queryKeypointVectorChanged()
Signal	outputChanged()

Maps matches to local keypoint.

DMatchVector matches1to2 property

Matches from the first source to second one.

list trainKeypointVectors property

List of trained keypoint vectors.

KeyPointVector queryKeypointVector property

Query keypoint vector.

KeyPointToSceneMap output property

The mapped object.

matches1to2Changed() signal

Triggered when matches1to2 changed.

trainKeypointVectorsChanged() signal

Trigered when trainKeypointVectors is changed

queryKeypointVectorChanged() signal

Trigered when queryKeypointVector is changed

outputChanged() signal

Triggered when output is changed

KeypointHomography type

Inherits

MatDisplay

Property	KeyPointToSceneMap keypointsToScene
Property	Mat queryImage
Property	Array objectCorners
Property	Array objectColors

Signal	keypointsToSceneChanged()
Signal	queryImageChanged()
Signal	objectCornersChanged()
Signal	objectColorsChanged()

Performs a homography based on the keypoints to scene.

KeyPointToSceneMap keypointsToScene property

Keypoints to scene object.

Mat queryImage property

Query image used.

Array objectCorners property

An array of 4 points describing the obejct corners

Array objectColors property

Array of object colors.

keypointsToSceneChanged() signal

Triggered when KeypointsToScene is changed.

queryImageChanged() signal

Triggered when QueryImage is changed.

objectCornersChanged() signal

Trigered when objectCorners is changed.

objectColorsChanged() signal

Trigered when objectColors is changed.