Segmentation Package

Segmentation Package

ColorSegmentation Module

class SimpleCV.Segmentation.ColorSegmentation.ColorSegmentation

Bases: SimpleCV.Segmentation.SegmentationBase.SegmentationBase

Perform color segmentation based on a color model or color provided. This class uses ColorModel.py to create a color model.

addImage(img)

Add a single image to the segmentation algorithm

addToModel(data)

getRawImage()

Return the segmented image with white representing the foreground and black the background.

getSegmentedBlobs()

return the segmented blobs from the fg/bg image

getSegmentedImage(whiteFG=True)

Return the segmented image with white representing the foreground and black the background.

isError()

Returns true if the segmentation system has detected an error. Eventually we’ll consruct a syntax of errors so this becomes more expressive

isReady()

Returns true if the camera has a segmented image ready.

mBlobMaker = []

mColorModel = []

mCurImg = []

mError = False

mTruthImg = []

reset()

Perform a reset of the segmentation systems underlying data.

resetError()

Clear the previous error.

subtractModel(data)

DiffSegmentation Module

class SimpleCV.Segmentation.DiffSegmentation.DiffSegmentation(grayOnly=False, threshold=(10, 10, 10))

Bases: SimpleCV.Segmentation.SegmentationBase.SegmentationBase

This method will do image segmentation by looking at the difference between two frames.

grayOnly - use only gray images. threshold - The value at which we consider the color difference to be significant enough to be foreground imagery.

The general usage is

>>> segmentor = DiffSegmentation()
>>> cam = Camera()
>>> while(1):
>>>    segmentor.addImage(cam.getImage())
>>>    if(segmentor.isReady()):
>>>        img = segmentor.getSegmentedImage()

addImage(img)

Add a single image to the segmentation algorithm

getRawImage()

Return the segmented image with white representing the foreground and black the background.

getSegmentedBlobs()

return the segmented blobs from the fg/bg image

getSegmentedImage(whiteFG=True)

Return the segmented image with white representing the foreground and black the background.

isError()

Returns true if the segmentation system has detected an error. Eventually we’ll consruct a syntax of errors so this becomes more expressive

isReady()

Returns true if the camera has a segmented image ready.

mBlobMaker = None

mColorImg = None

mCurrImg = None

mDiffImg = None

mError = False

mGrayOnlyMode = True

mLastImg = None

mThreshold = 10

reset()

Perform a reset of the segmentation systems underlying data.

resetError()

Clear the previous error.

RunningSegmentation Module

class SimpleCV.Segmentation.RunningSegmentation.RunningSegmentation(alpha=0.7, thresh=(20, 20, 20))

Bases: SimpleCV.Segmentation.SegmentationBase.SegmentationBase

RunningSegmentation performs segmentation using a running background model. This model uses an accumulator which performs a running average of previous frames where: accumulator = ((1-alpha)input_image)+((alpha)accumulator)

addImage(img)

Add a single image to the segmentation algorithm

getRawImage()

Return the segmented image with white representing the foreground and black the background.

getSegmentedBlobs()

return the segmented blobs from the fg/bg image

getSegmentedImage(whiteFG=True)

Return the segmented image with white representing the foreground and black the background.

isError()

Returns true if the segmentation system has detected an error. Eventually we’ll consruct a syntax of errors so this becomes more expressive

isReady()

Returns true if the camera has a segmented image ready.

mAlpha = 0.1

mBlobMaker = None

mCurrImg = None

mDiffImg = None

mError = False

mGrayOnly = True

mModelImg = None

mReady = False

mThresh = 10

reset()

Perform a reset of the segmentation systems underlying data.

resetError()

Clear the previous error.

SegmentationBase Module

class SimpleCV.Segmentation.SegmentationBase.SegmentationBase

Bases: object

Right now I am going to keep this class as brain dead and single threaded as possible just so I can get the hang of abc in python. The idea behind a segmentation object is that you pass it frames, it does some sort of operations and you get a foreground / background segemnted image. Eventually I would like these processes to by asynchronous and multithreaded so that they can raise specific image processing events.

addImage(img)

Add a single image to the segmentation algorithm

getRawImage()

Return the segmented image with white representing the foreground and black the background.

getSegmentedBlobs()

return the segmented blobs from the fg/bg image

getSegmentedImage(whiteFG=True)

Return the segmented image with white representing the foreground and black the background.

isError()

Returns true if the segmentation system has detected an error. Eventually we’ll consruct a syntax of errors so this becomes more expressive

isReady()

Returns true if the camera has a segmented image ready.

classmethod load(fname)

load segmentation settings to file.

reset()

Perform a reset of the segmentation systems underlying data.

resetError()

Clear the previous error.

save(fname)

Save segmentation settings to file.