http://www.emgu.com
Create a Good Feature to Track detector

Namespace: Emgu.CV.Features2D
Assembly: Emgu.CV (in Emgu.CV.dll) Version: 2.4.10.1935 (2.4.10.1935)

Syntax

C#
public GFTTDetector(
	int maxCorners,
	double qualityLevel,
	double minDistance,
	int blockSize,
	bool useHarrisDetector,
	double k
)
Visual Basic
Public Sub New ( 
	maxCorners As Integer,
	qualityLevel As Double,
	minDistance As Double,
	blockSize As Integer,
	useHarrisDetector As Boolean,
	k As Double
)
Visual C++
public:
GFTTDetector(
	int maxCorners, 
	double qualityLevel, 
	double minDistance, 
	int blockSize, 
	bool useHarrisDetector, 
	double k
)
F#
new : 
        maxCorners : int * 
        qualityLevel : float * 
        minDistance : float * 
        blockSize : int * 
        useHarrisDetector : bool * 
        k : float -> GFTTDetector

Parameters

maxCorners
Type: System..::..Int32
The maximum number of features to be detected. Use 1000 for default
qualityLevel
Type: System..::..Double
Multiplier for the maxmin eigenvalue; specifies minimal accepted quality of image corners. Use 0.01 for default.
minDistance
Type: System..::..Double
Limit, specifying minimum possible distance between returned corners; Euclidian distance is used. Use 1 for default
blockSize
Type: System..::..Int32
Size of the averaging block, passed to underlying cvCornerMinEigenVal or cvCornerHarris used by the function. Use 3 for default
useHarrisDetector
Type: System..::..Boolean
If true, will use Harris corner detector. Use false as default
k
Type: System..::..Double
K, use 0.04 for default

Remarks

The function first calculates the minimal eigenvalue for every source image pixel using cvCornerMinEigenVal function and stores them in eig_image. Then it performs non-maxima suppression (only local maxima in 3x3 neighborhood remain). The next step is rejecting the corners with the minimal eigenvalue less than quality_level?max(eig_image(x,y)). Finally, the function ensures that all the corners found are distanced enough one from another by considering the corners (the most strongest corners are considered first) and checking that the distance between the newly considered feature and the features considered earlier is larger than min_distance. So, the function removes the features than are too close to the stronger features

See Also