SwisTrack/Components/MotionTemplateParticleDetector

Description

edit

This isn't actually a tracker but a particle detecter. It emits particles when there is motion in the image, calculated by finding gradients on frame-differences of images over multiple timescales. See the OpenCV book for more information. It also associates the particles with a color histogram if it's given a foreground model in mDataStructureImageBinary.

Parameters

edit

Note: I use default values for all parameters. Read the openCV book and documentation for more details - I wrote this component following the section in the openCV book on motion templates.

DiffThreshold

edit

Threshold to use for frame differencing.

MhiDuration

edit

passed to cvUPdateMotionHistory. "Maximal duration of motion track in the same units as timestamp."

SegmentThreshold

edit

passed to cvSegmentMotion. "Segmentation threshold; recommended to be equal to the interval between motion history "steps" or greater. "

MaxTimeDelta

edit

passed to cvCalcMotionGradient. "The function finds minimum (m(x,y)) and maximum (M(x,y)) MHI values over each pixel (x,y) neighborhood and assumes the gradient is valid only if min(delta1,delta2) <= M(x,y)-m(x,y) <= max(delta1,delta2)."

MinTimeDelta

edit

passed to cvCalcMotionGradient. "The function finds minimum (m(x,y)) and maximum (M(x,y)) MHI values over each pixel (x,y) neighborhood and assumes the gradient is valid only if min(delta1,delta2) <= M(x,y)-m(x,y) <= max(delta1,delta2)."