I need to track some moving objects so want to use one of background subtraction algorithms implemented in opencv. Saw some examples of how they work and it seems like GSOC is the one I need (the best result for my purposes), but can't find any good explanation of the way it works. Documentation says like this:
Implementation of the different yet better algorithm which is called GSOC, as it was implemented during GSOC and was not originated from any paper.
This algorithm demonstrates better performance on CDNET 2014 dataset compared to other algorithms in OpenCV.
The most informative source was doc, but still not enough to change the parameters reasonably:
@param mc Whether to use camera motion
@param nSamples Number of samples to maintain at each point of the frame.
@param replaceRate Probability of replacing the old sample - how fast the model will update itself.
@param propagationRate Probability of propagating to neighbors.
@param hitsThreshold How many positives the sample must get before it will be considered as a possible replacement.
@param alpha Scale coefficient for threshold.
@param beta Bias coefficient for threshold.
@param blinkingSupressionDecay Blinking supression decay factor.
@param blinkingSupressionMultiplier Blinking supression multiplier.
@param noiseRemovalThresholdFacBG Strength of the noise removal for background points.
@param noiseRemovalThresholdFacFG Strength of the noise removal for foreground points.
I tried to google, but achieved nothing.
May anybody share some knowledge about the algorithm?
