Class SuperpixelSEEDS

Class implementing the SEEDS (Superpixels Extracted via Energy-Driven Sampling) superpixels algorithm described in @cite VBRV14.

The algorithm uses an efficient hill-climbing algorithm to optimize the superpixels' energy function that is based on color histograms and a boundary term, which is optional.The energy function encourages superpixels to be of the same color, and if the boundary term is activated, the superpixels have smooth boundaries and are of similar shape. In practice it starts from a regular grid of superpixels and moves the pixels or blocks of pixels at the boundaries to refine the solution.The algorithm runs in real-time using a single CPU.

Inheritance
System.Object
DisposableObject
DisposableCvObject
Algorithm
SuperpixelSEEDS
Implements
Inherited Members
Namespace: OpenCvSharp.XImgProc
Assembly: OpenCvSharp.dll
Syntax
public class SuperpixelSEEDS : Algorithm, ICvPtrHolder

Constructors

| Improve this Doc View Source

SuperpixelSEEDS(IntPtr)

Creates instance by raw pointer

Declaration
protected SuperpixelSEEDS(IntPtr p)
Parameters
Type Name Description
IntPtr p

Methods

| Improve this Doc View Source

Create(Int32, Int32, Int32, Int32, Int32, Int32, Int32, Boolean)

Initializes a SuperpixelSEEDS object.

The function initializes a SuperpixelSEEDS object for the input image. It stores the parameters of the image: image_width, image_height and image_channels.It also sets the parameters of the SEEDS superpixel algorithm, which are: num_superpixels, num_levels, use_prior, histogram_bins and double_step.

The number of levels in num_levels defines the amount of block levels that the algorithm use in the optimization.The initialization is a grid, in which the superpixels are equally distributed through the width and the height of the image.The larger blocks correspond to the superpixel size, and the levels with smaller blocks are formed by dividing the larger blocks into 2 x 2 blocks of pixels, recursively until the smaller block level. An example of initialization of 4 block levels is illustrated in the following figure.

Declaration
public static SuperpixelSEEDS Create(int imageWidth, int imageHeight, int imageChannels, int numSuperpixels, int numLevels, int prior = 2, int histogramBins = 5, bool doubleStep = false)
Parameters
Type Name Description
System.Int32 imageWidth

Image width.
System.Int32 imageHeight

Image height.
System.Int32 imageChannels

Number of channels of the image.
System.Int32 numSuperpixels

Desired number of superpixels. Note that the actual number may be smaller due to restrictions(depending on the image size and num_levels). Use getNumberOfSuperpixels() to get the actual number.
System.Int32 numLevels

Number of block levels. The more levels, the more accurate is the segmentation, but needs more memory and CPU time.
System.Int32 prior

enable 3x3 shape smoothing term if >0. A larger value leads to smoother shapes. prior must be in the range[0, 5].
System.Int32 histogramBins

Number of histogram bins.
System.Boolean doubleStep

If true, iterate each block level twice for higher accuracy.
Returns
Type Description
SuperpixelSEEDS
| Improve this Doc View Source

DisposeManaged()

Releases managed resources

Declaration
protected override void DisposeManaged()
Overrides
| Improve this Doc View Source

DisposeUnmanaged()

Declaration
protected override void DisposeUnmanaged()
Overrides
| Improve this Doc View Source

Get()

Declaration
public override IntPtr Get()
Returns
Type Description
IntPtr
| Improve this Doc View Source

GetLabelContourMask(OutputArray, Boolean)

Returns the mask of the superpixel segmentation stored in SuperpixelSEEDS object. The function return the boundaries of the superpixel segmentation.

Declaration
public virtual void GetLabelContourMask(OutputArray image, bool thickLine = true)
Parameters
Type Name Description
OutputArray image

Return: CV_8U1 image mask where -1 indicates that the pixel is a superpixel border, and 0 otherwise.
System.Boolean thickLine

If false, the border is only one pixel wide, otherwise all pixels at the border are masked.
| Improve this Doc View Source

GetLabels(OutputArray)

Returns the segmentation labeling of the image. Each label represents a superpixel, and each pixel is assigned to one superpixel label.

The function returns an image with ssthe labels of the superpixel segmentation. The labels are in the range[0, getNumberOfSuperpixels()].

Declaration
public virtual void GetLabels(OutputArray labelsOut)
Parameters
Type Name Description
OutputArray labelsOut

Return: A CV_32UC1 integer array containing the labels of the superpixel segmentation.The labels are in the range[0, getNumberOfSuperpixels()].
| Improve this Doc View Source

GetNumberOfSuperpixels()

Calculates the superpixel segmentation on a given image stored in SuperpixelSEEDS object.

The function computes the superpixels segmentation of an image with the parameters initialized with the function createSuperpixelSEEDS().

Declaration
public virtual int GetNumberOfSuperpixels()
Returns
Type Description
System.Int32
| Improve this Doc View Source

Iterate(InputArray, Int32)

Input image. Supported formats: CV_8U, CV_16U, CV_32F. Image size & number of channels must match with the initialized image size & channels with the function createSuperpixelSEEDS(). It should be in HSV or Lab color space.Lab is a bit better, but also slower.

Declaration
public virtual void Iterate(InputArray img, int numIterations = 10)
Parameters
Type Name Description
InputArray img

Supported formats: CV_8U, CV_16U, CV_32F. Image size & number of channels must match with the initialized image size & channels with the function createSuperpixelSEEDS(). It should be in HSV or Lab color space.Lab is a bit better, but also slower.
System.Int32 numIterations

Number of pixel level iterations. Higher number improves the result.

Implements