The BackgroundSubtractorCNT related code is in here.
Classes  
class  BackgroundSubtractorCNT 
Background subtraction based on counting. More...  
Functions  
BGSUBCNT_EXPORTS_W Ptr< BackgroundSubtractorCNT >  createBackgroundSubtractorCNT (int minPixelStability=15, bool useHistory=true, int maxPixelStability=15 *60, bool isParallel=true) 
Create background subtraction based on counting. More...  
Function Documentation
BGSUBCNT_EXPORTS_W Ptr<BackgroundSubtractorCNT> cv::bgsubcnt::createBackgroundSubtractorCNT  (  int  minPixelStability = 15 , 
bool  useHistory = true , 

int  maxPixelStability = 15 *60 , 

bool  isParallel = true 

) 
 Parameters

minPixelStability number of frames with same pixel color to consider stable useHistory determines if we're giving a pixel credit for being stable for a long time maxPixelStability maximum allowed credit for a pixel in history isParallel determines if we're parallelizing the algorithm
 Returns
 a smart pointer to a BackgroundSubtractorCNT
 Note
 The default values assume 15 FPS, in which a pixel which keeps it's value for ~ 1 second is a stable background.
For history, a stable pixel will keep counting frames up to maxPixelStability. Changes will try to decrement the count, but as long as it is above minPixelStability, is will remain stable. for example, if FPS * is 15, then maxPixelStability of 15*60 means that a changes of ~ 60 seconds will make this pixel nonstable background.
Effect of learningRate in apply(..., learningRate) 
 If learningRate == 1, then the algorithm is as stated above.
 If learningRate == 0, it is as if you used 'useHistory = false'.
 If 0 < learningRate < 1, then maxPixelStability = "initial maxPixelStability" * learningRate
 Examples:
 main.cpp.
Generated by 1.8.11