Motion Analysis and Object Tracking

Acc

Comments from the Wiki

void cvAcc(const CvArr* image, CvArr* sum, const CvArr* mask=NULL)

Adds a frame to an accumulator.

Parameters:

• image – Input image, 1- or 3-channel, 8-bit or 32-bit floating point. (each channel of multi-channel image is processed independently)
• sum – Accumulator with the same number of channels as input image, 32-bit or 64-bit floating-point
• mask – Optional operation mask

The function adds the whole image image or its selected region to the accumulator sum :

MultiplyAcc

Comments from the Wiki

void cvMultiplyAcc(const CvArr* image1, const CvArr* image2, CvArr* acc, const CvArr* mask=NULL)

Adds the product of two input images to the accumulator.

Parameters:

• image1 – First input image, 1- or 3-channel, 8-bit or 32-bit floating point (each channel of multi-channel image is processed independently)
• image2 – Second input image, the same format as the first one
• acc – Accumulator with the same number of channels as input images, 32-bit or 64-bit floating-point
• mask – Optional operation mask

The function adds the product of 2 images or their selected regions to the accumulator acc :

RunningAvg

Comments from the Wiki

void cvRunningAvg(const CvArr* image, CvArr* acc, double alpha, const CvArr* mask=NULL)

Updates the running average.

Parameters:

• image – Input image, 1- or 3-channel, 8-bit or 32-bit floating point (each channel of multi-channel image is processed independently)
• acc – Accumulator with the same number of channels as input image, 32-bit or 64-bit floating-point
• alpha – Weight of input image
• mask – Optional operation mask

The function calculates the weighted sum of the input image image and the accumulator acc so that acc becomes a running average of frame sequence:

where regulates the update speed (how fast the accumulator forgets about previous frames).

SquareAcc

Comments from the Wiki

void cvSquareAcc(const CvArr* image, CvArr* sqsum, const CvArr* mask=NULL)

Adds the square of the source image to the accumulator.

Parameters:

• image – Input image, 1- or 3-channel, 8-bit or 32-bit floating point (each channel of multi-channel image is processed independently)
• sqsum – Accumulator with the same number of channels as input image, 32-bit or 64-bit floating-point
• mask – Optional operation mask

The function adds the input image image or its selected region, raised to power 2, to the accumulator sqsum :